Building data evaluation method, device, equipment, medium and program product

Abstract

The invention relates to the technical field of engineering construction, and discloses a building data evaluation method, device and equipment, a medium and a program product. The method comprises the following steps: obtaining building data and a preset evaluation index of a to-be-evaluated area; performing index disassembly on the building data according to a preset evaluation index to obtain a plurality of indexes and factors corresponding to the indexes, and determining factor values corresponding to the indexes; performing conversion processing on the factor values to obtain index scores corresponding to the indexes; and generating a building evaluation result of the to-be-evaluated area based on the index score. By implementing the technical scheme of the invention, comprehensive evaluation of the building data can be realized, and an accurate building evaluation result can be generated.

Description

Technical Field

[0001] The present invention relates to the technical field of engineering construction, and in particular to a method, device, equipment, medium and program product for evaluating building data. Background Art

[0002] When developing or maintaining a region, engineering and construction companies usually need to inquire about the region's economy, investment, bidding information, and policy conditions, as well as the main customers, competitors, and project data in the enterprise system, or obtain information through offline communication. After integration and judgment, this information is used to decide on the resources to be invested in the region.

[0003] At present, engineering construction companies can only manually collect online and offline information and combine it with experience in market assessment, which leads to poor timeliness of information and difficulty in comprehensively comparing markets across the country. At the same time, potential business opportunities, customers and competitors are difficult to accurately identify, and influencing factors and data are scattered, affecting the comprehensiveness and accuracy of the assessment. Summary of the invention

[0004] In view of this, the present invention provides a construction data evaluation method, device, equipment, medium and program product to solve the problem of how to improve the timeliness, comprehensiveness and accuracy of information in construction data evaluation of engineering construction enterprises.

[0005] In a first aspect, the present invention provides a method for evaluating building data, comprising: obtaining building data of an area to be evaluated and preset evaluation indicators; decomposing the building data according to the preset evaluation indicators to obtain multiple indicators and factors corresponding to each indicator, and determining the factor value corresponding to each indicator; respectively transforming the factor values ​​to obtain indicator scores corresponding to each indicator; and generating building evaluation results for the area to be evaluated based on the indicator scores.

[0006] The building data evaluation method provided by the embodiment of the present invention can provide consistent evaluation standards and reduce human errors by presetting evaluation indicators and systematic factor decomposition. The conversion process ensures the comparability of various indicators, and the evaluation results generated in the end are more objective and accurate. In addition, the calculation and judgment basis of each step can be clearly tracked, which improves the transparency and reliability of the evaluation.

[0007] In an optional embodiment, the indicator includes a predictive indicator, and the factor value includes a first factor value corresponding to the predictive indicator; determining the factor value corresponding to each indicator includes: extracting business object data corresponding to the predictive indicator from the building data; performing data processing on the business object data to obtain the prediction probability corresponding to each business object; accumulating the prediction probabilities to obtain the expected value corresponding to the predictive indicator; and processing the expected value to obtain the first factor value.

[0008] The building data evaluation method provided by the embodiment of the present invention can more accurately estimate the actual impact of indicators and improve the prediction ability of evaluation by extracting business object data and calculating prediction probabilities. By using predictive indicators and their corresponding factor values, the evaluation results can be dynamically adjusted according to the latest data to make them closer to the actual situation. Accumulating and processing the prediction probabilities can systematically integrate the data of different business objects and improve the consistency and comprehensiveness of the evaluation. The prediction value based on actual data reduces the influence of subjective judgment and makes the evaluation results more objective and reliable.

[0009] In an optional implementation, the expected value is processed to obtain the first factor value, including: normalizing the expected value to obtain a proportion value corresponding to the predictive indicator; and determining the expected value and the proportion value as the first factor value.

[0010] The evaluation method for building data provided by the embodiment of the present invention adjusts the expected value to a unified scale through normalization processing, so that different indicators are comparable and the consistency of data is improved. Through the proportion value, the importance or influence of each predictive indicator in the whole can be intuitively understood, which is convenient for evaluation and analysis. The consistency of factor values ​​in different data sets and time points is ensured, and the stability and reliability of the evaluation results are enhanced.

[0011] In an optional implementation, the indicator also includes a statistical indicator, and the factor value also includes a second factor value corresponding to the statistical indicator; determining the factor value corresponding to each indicator includes: extracting attribute data corresponding to the statistical indicator from the building data; and classifying and counting the attribute data to obtain the second factor value.

[0012] The building data evaluation method provided by the embodiment of the present invention can determine the second factor value of the statistical index based on the actual data by classifying and counting the attribute data, thereby enhancing the objectivity of the evaluation. Classification and statistics enable data of different attributes to be systematically sorted and analyzed, thereby improving the clarity of data processing. The data after classification and statistics can more conveniently compare different indicators, supporting more comprehensive evaluation and analysis.

[0013] In an optional implementation, the factor values ​​are transformed respectively to obtain the indicator scores corresponding to the various indicators, including: for any indicator, preprocessing the factor values ​​corresponding to the indicator to obtain multiple third factor values ​​corresponding to the indicator; performing data processing on the multiple third factor values ​​to determine the optimal solution distance and the worst solution distance; and determining the indicator score according to the sum of the optimal solution distance and the worst solution distance.

[0014] The building data evaluation method provided by the embodiment of the present invention can comprehensively reflect different aspects of the index by processing multiple third factor values, thereby improving the accuracy of the evaluation. Determining the optimal solution distance and the worst solution distance is helpful for relative comparison and quantifying the performance range and difference of the index. The index score is calculated based on the optimal solution and the worst solution distance, making the final result more representative and reasonable. The optimal solution and the worst solution distance can be adjusted according to the change of data, thereby improving the flexibility and real-time performance of the evaluation.

[0015] In an optional implementation, data processing is performed on the third factor value to determine the optimal solution distance and the worst solution distance, including: determining the optimal value and the worst value from multiple third factor values; determining the optimal solution distance based on the difference between the optimal value and the third factor value; and determining the worst solution distance based on the difference between the worst value and the third factor value.

[0016] The building data evaluation method provided by the embodiment of the present invention can clearly set the reference point of the evaluation by determining the best value and the worst value, so that the performance of the indicator has a clear basis for comparison. Calculating the best solution distance and the worst solution distance can accurately reflect the difference between the third factor value and the extreme situation, and help identify the extreme performance in the data. By calculating the distance based on the actual data, a more accurate indicator score can be provided, reducing subjective bias.

[0017] In an optional implementation, generating a building assessment result for the area to be assessed based on the indicator scores includes: determining the weights corresponding to the various indicators; performing weighted processing based on the weights to obtain a total portrait score corresponding to the area to be assessed; and generating a building assessment result based on the total portrait score.

[0018] The building data evaluation method provided by the embodiment of the present invention can comprehensively evaluate the impact of different indicators on the overall building performance by determining the weight of each indicator to ensure a comprehensive evaluation. Weighting each indicator makes the evaluation result more consistent with the actual situation and importance, avoiding the deviation that may be caused by simple averaging. Calculating the total portrait score provides a comprehensive evaluation result, making complex evaluation data more intuitive and easy to understand. By generating a building evaluation result, the overall performance of the area to be evaluated can be clearly reflected, helping decision-making and optimization.

[0019] In an optional implementation, the weights corresponding to the various indicators are determined, including: obtaining the number of indicators and feature evaluation data; determining a consistency indicator based on the difference between the feature evaluation data and the number of indicators; determining a random consistency indicator corresponding to the number of indicators; and obtaining a weight based on the normalization results of the consistency indicator and the random consistency indicator.

[0020] The building data evaluation method provided by the embodiment of the present invention ensures that the weight determination process has a systematic basis and reduces subjectivity by obtaining the number of indicators and characteristic evaluation data. By comparing the consistency index and the random consistency index, the rationality and consistency of the weight can be ensured, and the reliability of the evaluation result can be improved. The normalization processing method standardizes the calculation of the weight and avoids the influence of the difference in indicator scale. Comprehensive consideration of consistency and randomness makes the final weight distribution more accurate and scientific.

[0021] In an optional embodiment, weights are obtained based on the normalized results of the consistency index and the random consistency index, including: determining the ratio of the consistency index to the random consistency index as the consistency ratio; when the consistency ratio is less than a preset threshold, normalizing the feature evaluation data to obtain the weights corresponding to each indicator.

[0022] The building data evaluation method provided by the embodiment of the present invention can quantify the consistency level in the evaluation process and ensure the rationality of weight distribution by calculating the ratio of the consistency index to the random consistency index. The calculation of the consistency ratio provides an objective basis and reduces the subjective judgment in the weight determination process. By setting a preset threshold, the consistency level requirement can be controlled to ensure that the weight calculation is performed only when the consistency is high enough, thereby enhancing the stability and reliability of the evaluation. The feature evaluation data is normalized so that the weight calculation is not affected by the scale of the original data, thereby improving the consistency and comparability of the results.

[0023] In an optional implementation, obtaining building data of the area to be evaluated includes: obtaining initial data of the area to be evaluated; and performing data management on the initial data to obtain building data.

[0024] The building data evaluation method provided by the embodiment of the present invention can ensure that the data used is accurate and reliable through the acquisition of initial data and subsequent data governance, thereby improving the credibility of the evaluation results. The data governance process helps to clean up and correct errors and inconsistencies in the data, avoiding evaluation deviations caused by data problems.

[0025] In an optional implementation, data governance is performed on the initial data to obtain building data, including: data cleansing the initial data to obtain first data; data standardization of the first data to obtain second data; data association of the second data to obtain third data; and field expansion of the third data to obtain building data.

[0026] The building data evaluation method provided by the embodiment of the present invention gradually improves the data quality and integrity through the phased processing of cleaning, standardization, association and field expansion. Each phase processes a specific problem to improve the accuracy and consistency of the data. The field expansion phase increases the level of detail of the data, making the final data more comprehensive and useful. The systematic processing flow helps to identify and solve potential problems in the data and ensure the high quality of the final data.

[0027] In a second aspect, the present invention provides an evaluation device for building data, comprising: an acquisition module for acquiring market analysis data and a preset evaluation index system; wherein the evaluation index system includes multiple initial evaluation indexes, and the initial evaluation index includes multiple initial evaluation factors; a determination module for determining the initial factor value corresponding to each initial evaluation factor based on the market analysis data and the evaluation index system; wherein the initial factor value is used to quantify the initial evaluation factor; a conversion module for converting the initial factor value into an indicator score of a target evaluation index corresponding to the target evaluation factor; and a generation module for generating an evaluation report for a target area based on the indicator score.

[0028] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the method for evaluating building data of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0029] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the method for evaluating building data of the first aspect or any corresponding embodiment thereof.

[0030] In a fifth aspect, the present invention provides a computer program product, comprising computer instructions for causing a computer to execute the method for evaluating building data of the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0032] Figure 1 is a schematic flow chart of a method for evaluating building data according to an embodiment of the present invention;

[0033] Figure 2 is a flow chart of another method for evaluating building data according to an embodiment of the present invention;

[0034] Figure 3 is a flow chart of another method for evaluating building data according to an embodiment of the present invention;

[0035] Figure 4 is a schematic diagram of three calculation methods according to an embodiment of the present invention;

[0036] Figure 5 is a structural block diagram of a device for evaluating building data according to an embodiment of the present invention;

[0037] Figure 6 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0038] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0039] When developing or maintaining a region, engineering and construction companies usually need to obtain information about the region's economy, investment, bidding information, and policies from the Internet or information provider's website, and at the same time consult the main customers, competitors, and project data in their own systems. In addition, companies can also obtain relevant information through offline communication. By integrating this data, companies can make more scientific decisions about resource investment in the region.

[0040] At present, when evaluating a regional market, engineering construction companies usually rely on manually collected online and offline information and make judgments based on experience, which results in poor timeliness of information and inability to fully cover all prefecture-level cities. In addition, existing methods are difficult to effectively identify potential business opportunities, customers, and competitors, affecting the comprehensiveness and accuracy of regional assessments. Data factors are scattered and lack a unified collection, collation, and analysis method, which limits the application of big data and machine learning technologies and makes it impossible to efficiently generate regional market portraits to assist decision-making.

[0041] In view of this, the technical solution of the present invention aims at the shortcomings of market assessment in the construction industry, comprehensively considers factors such as regional economy, policies, engineering market opportunities, customers and competitors, and uses big data and machine learning technology to uniformly collect, process and analyze data to form regional scores, thus solving the problems of timeliness and one-sidedness of manually collected data.

[0042] According to an embodiment of the present invention, an embodiment of a method for evaluating building data is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0043] In this embodiment, a method for evaluating building data is provided, which can be used for computer equipment, such as desktop computers, notebook computers, etc. Figure 1 is a flow chart of a method for evaluating building data according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0044] Step S101, obtaining building data of the area to be evaluated and preset evaluation indicators.

[0045] The construction data of the area to be evaluated refers to detailed information about all construction projects in a specific area. Specifically, the construction industry's evaluation of a certain area needs to take into account multiple factors. It is necessary to obtain external information related to the industry, including regional policies, investment scale, economic development status, number of projects, project scale, qualification requirements, and the number, category and relevant amount of bidding and winning companies. These data can be obtained from websites or platforms with access rights. In addition, it is also necessary to extract relevant information such as historical bidding, winning bids, customers, personnel and qualifications from the engineering construction company's own CRM system or project management system. Among them, crawler technology, text processing technology, interface acquisition technology and other means can be used to obtain the construction data of the area to be evaluated, and the collected data can be stored in the data warehouse for unified management.

[0046] The preset evaluation indicators are the standards or parameters used to measure and evaluate the construction market situation in the region to be evaluated. Specifically, a series of relevant evaluation indicators can be determined by studying the regional economy, market dynamics, and policy environment, combined with expert opinions and industry standards, such as the number of projects, project scale, investment amount, and qualification requirements.

[0047] Step S102, decomposing the building data according to the preset evaluation index, obtaining multiple indexes and factors corresponding to each index, and determining the factor value corresponding to each index.

[0048] Indicators are key parameters used to measure and describe data when evaluating the construction market. Factors are specific data or parameters used to describe and measure indicators. Specifically, the collected construction data is disassembled and classified according to the preset evaluation indicators. The purpose of disassembly is to break down the construction data into smaller and more specific parts, so that each part can be analyzed for specific indicators and specific factors.

[0049] The factor value is the specific value or description of each indicator in the actual data, which is used to represent the actual situation of the indicator. Specifically, the data related to the factor value is extracted from the collected building data, and the data is analyzed. According to the different types of indicators, different data processing methods are used to calculate the factor value of each indicator.

[0050] Step S103: transform the factor values ​​respectively to obtain the indicator scores corresponding to the indicators.

[0051] The indicator score is the quantitative result obtained after the factor value is transformed, which is used to express the overall score or evaluation result of each indicator. Specifically, each factor value is transformed to standardize it to a unified scale. The transformed factor values ​​are summarized or calculated to obtain the indicator score of each indicator.

[0052] Step S104: generating a building assessment result for the area to be assessed based on the index score.

[0053] The building assessment result refers to the overall assessment result based on the comprehensive scores of each indicator, which is used to comprehensively evaluate and analyze the buildings in the assessment area. Specifically, the indicator scores of each indicator are combined into an overall assessment score through weighted average or other statistical methods. For example, the building assessment result can be displayed in the form of a total score or rating (such as 1 to 100 points), or it can be displayed using a graded evaluation system, such as "excellent", "good", "medium", and "poor" grades, which are not limited here.

[0054] The building data evaluation method provided by the embodiment of the present invention can provide consistent evaluation standards and reduce human errors by presetting evaluation indicators and systematic factor decomposition. The conversion process ensures the comparability of various indicators, and the evaluation results generated in the end are more objective and accurate. In addition, the calculation and judgment basis of each step can be clearly tracked, which improves the transparency and reliability of the evaluation.

[0055] In this embodiment, a method for evaluating building data is provided, which can be used for computer equipment, such as desktop computers, notebook computers, etc. Figure 2 is a flow chart of a method for evaluating building data according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:

[0056] Step S201, obtaining building data of the area to be evaluated and preset evaluation indicators.

[0057] Specifically, the above step S201 includes:

[0058] Step S2011, obtaining initial data of the area to be evaluated.

[0059] Initial data is the data collected about the buildings in the area to be assessed. It is original, unprocessed information and comes from different sources. Specifically, initial data can include architectural design drawings, construction records, material lists, building physical properties, environmental conditions, etc. These data can be obtained from sources such as the architectural design team, construction units, and building management systems.

[0060] Step S2012, perform data management on the initial data to obtain building data.

[0061] Specifically, the initial data after collection is uniformly stored and calculated in the data warehouse. However, due to the large number of data sources, the standards, formats, scopes, and coding of the initial data are varied. Data governance means are needed to integrate and standardize the data from different data sources for use in subsequent steps. Because the initial data has been stored in the data warehouse, big data related technologies such as hive sql or spark can be used for related calculations. The building data obtained after data governance calculation forms a unified and related data table stored in the data warehouse.

[0062] The building data evaluation method provided by the embodiment of the present invention can ensure that the data used is accurate and reliable through the acquisition of initial data and subsequent data governance, thereby improving the credibility of the evaluation results. The data governance process helps to clean up and correct errors and inconsistencies in the data, avoiding evaluation deviations caused by data problems.

[0063] In some optional implementations, the above step S2012 includes:

[0064] Step a1, performing data cleaning on the initial data to obtain first data.

[0065] The first data refers to the data set after the initial data has been cleaned, removing test data, invalid data and duplicates, ensuring the initial accuracy and validity of the data. Specifically, identify and remove non-standard content in the initial data, such as test data, invalid data or failed data. It needs to be processed according to the different characteristics of the data source. For example, remove data marked as "test", filter out data related to non-construction fields, and deduplicate duplicate data (such as corporate information). After completion, the first data that has been initially cleaned will be obtained.

[0066] Step a2, normalizing the first data to obtain second data.

[0067] Secondary data refers to a data set that has been normalized based on primary data, with a unified code, format, unit, and precision, making the data more consistent and comparable. Specifically, during the data normalization phase, primary data needs to be standardized, including code, region name, date format, amount unit, etc. By ensuring that all data has a consistent format and metric, subsequent data statistics and calculations can be facilitated.

[0068] Step a3, performing data association on the second data to obtain third data.

[0069] The third data refers to a data set after data association is completed on the basis of the second data, and the relevant information from different data sources is associated according to a specific dimension to form a comprehensive data set. Specifically, data association involves associating the second data from different sources according to a specific dimension. For example, the bidding information is associated with the corresponding winning bid, bidding, enterprise and personnel information to form a comprehensive data set. Among them, a unified code or name can be used to match the second data to obtain a third data that integrates various information.

[0070] Step a4, expanding the fields of the third data to obtain building data.

[0071] Specifically, in the field expansion stage, the third data is further enriched based on business needs. For example, the project scale field is added according to the bidding amount and enterprise situation, or the bidding activities within a certain time window are counted. This can add more useful fields and statistical information to the data set, thereby obtaining the final construction data.

[0072] In the above implementation, the data quality and integrity are gradually improved through the phased processing of cleaning, standardization, association and field expansion. Each stage addresses specific issues and improves the accuracy and consistency of the data. The field expansion stage increases the level of detail of the data, making the final data more comprehensive and useful. The systematic processing flow helps to identify and solve potential problems in the data and ensure the high quality of the final data.

[0073] Step S2013, obtain the preset evaluation index. For details, see Figure 1 Step S101 of the illustrated embodiment will not be described in detail here.

[0074] Step S202: Decompose the building data according to the preset evaluation index to obtain multiple indexes and factors corresponding to each index, and determine the factor value corresponding to each index.

[0075] Specifically, the above step S202 includes:

[0076] Step S2021, decomposing the building data into indicators according to preset evaluation indicators to obtain multiple indicators and factors corresponding to each indicator; wherein the indicators include predictive indicators and statistical indicators.

[0077] Predictive indicators are indicators obtained by modeling and predicting data, and are used to estimate what may happen in the future. For example, they can be business opportunity indicators, customer situation indicators, and competitor situation indicators. Statistical indicators are indicators that obtain corresponding factor values ​​by directly performing statistical calculations on building data. They do not rely on prediction models, but are based on actual data statistical results. For example, they can be openness indicators and opportunity index indicators. Specifically, the building data is decomposed according to the preset evaluation indicators to obtain multiple predictive indicators and factors corresponding to each predictive indicator, as well as multiple statistical indicators and factors corresponding to each statistical indicator.

[0078] For example, the recommended values ​​for engineering construction enterprises (taking the perspective of private enterprises as an example) to judge regional market conditions can be broken down into five indicators and corresponding factors, as shown in Table 1:

[0079] Table 1

[0080]

[0081]

[0082] Among them, the indicators include openness, opportunity index, business opportunity situation, customer situation and competition situation, etc. The openness reflects the degree of monopoly of the region on local construction enterprises and the degree of tolerance to foreign enterprises; the opportunity index indicates the market space for construction enterprises in the region; the business opportunity situation describes the potential business opportunities in the region; the customer situation involves the actual and potential customers of the construction enterprises in the region; and the competition situation reveals the actual and potential competitors of the construction enterprises in the region.

[0083] Specifically, the business opportunity situation can be broken down into factors such as "number of potential business opportunities", "proportion of number of potential business opportunities", "amount of potential business opportunities", and "proportion of amount of potential business opportunities"; the customer situation can be broken down into factors such as "number of customers", "proportion of number of customers", "amount of customer business opportunities", and "proportion of amount of customer business opportunities"; the competition situation can be broken down into factors such as "number of competitors", and "proportion of number of competitors". The degree of openness can be broken down into factors such as "proportion of winning bids of enterprises from other provinces", "proportion of winning candidates from other provinces", "proportion of winning bids of enterprises in the province other than the city", "proportion of winning candidates in the province other than the city", and "concentration of winning bids". The opportunity index can be broken down into factors such as "proportion of winning bids of private enterprises", "proportion of winning bid amounts of private enterprises", "proportion of the largest number of winning bids of private enterprises from other provinces", "proportion of the largest number of winning bids of private enterprises in the province other than the city", "average number of winning bids of enterprises", and "concentration of winning bids".

[0084] Step S2022, determining the first factor value corresponding to each predictive indicator.

[0085] The first factor value refers to the result obtained by the prediction model, which is used to quantify possible future trends or potential market opportunities. The first factor value is the result of the predictive indicator, reflecting what may happen in the future. Specifically, a suitable prediction model or algorithm is selected to process the building data, and the results of the prediction model are used to calculate the first factor value of each predictive indicator.

[0086] In some optional implementations, the above step S2022 includes:

[0087] Step b1, extracting business object data corresponding to the predictive index from the building data.

[0088] Business object data refers to data related to predictive indicators extracted from building data. Specifically, specific field information related to the calculation of predictive indicators is extracted from the database storing building data, such as project name, historical bidding records, budget, competition situation, etc. Relevant data is screened out according to the needs of predictive indicators, and the screened data is integrated to form a business object data set containing all relevant information.

[0089] Step b2: Process the business object data to obtain the prediction probability corresponding to each business object.

[0090] The prediction probability is the probability of each business object succeeding or meeting a certain condition, calculated based on the business object data. Specifically, select, create, and process features for prediction from the business object data, such as project size, budget, bidding unit history, etc., to improve the performance of the model. Determine a suitable machine learning model (such as logistic regression, decision tree, random forest, etc.), and train it with data processed by feature engineering to obtain a data training model. Use the trained model to predict each business object and obtain the success probability of each object.

[0091] Step b3, accumulate the predicted probabilities to obtain the expected value corresponding to the predictive indicator.

[0092] The expected value is the cumulative result of the predicted probability values ​​of all business objects, representing the overall predicted result or expected amount. Specifically, the predicted probabilities of all business objects are added together to obtain the expected value corresponding to the predictive indicator.

[0093] Step b4, processing the expected value to obtain the first factor value.

[0094] Specifically, the first factor value may be the expected value itself, or a result obtained by further calculation or conversion according to specific business logic and requirements.

[0095] In the above implementation, by extracting business object data and calculating prediction probabilities, the actual impact of indicators can be estimated more accurately, improving the prediction ability of the evaluation. Using predictive indicators and their corresponding factor values, the evaluation results can be dynamically adjusted according to the latest data to make them closer to the actual situation. Accumulating and processing the prediction probabilities can systematically integrate the data of different business objects and improve the consistency and comprehensiveness of the evaluation. The prediction value based on actual data reduces the influence of subjective judgment and makes the evaluation results more objective and reliable.

[0096] In some optional implementations, the above step b4 includes:

[0097] Step c1, normalize the expected value to obtain the proportion value corresponding to the predictive indicator.

[0098] The expected value is normalized and converted into a percentage value for easy comparison and analysis. Specifically, the expected value can be standardized to a range (e.g., 0 to 1) to make it comparable with other indicators.

[0099] Step c2: determine the expected value and the proportion value as the first factor value.

[0100] The normalized proportion value and the expected value are combined to determine the final first factor value. Specifically, the result is converted into a final numerical value to describe the performance of the predictive indicator.

[0101] For example, when the predictive indicator is the business opportunity situation, the potential business opportunities are calculated, and the number of business opportunities released in a time window history that are suitable for the enterprise is calculated, and the probability value P of each business opportunity that the enterprise may win the bid is calculated. i , and then calculate the corresponding factor value.

[0102] Specifically, based on the historical bidding and winning data accumulated by the construction enterprises themselves, combined with the regional information, enterprise information, personnel information, etc. in the external industry data, a data set of enterprise bidding and winning bids is constructed. The positive samples are the winning bids of the enterprises, and the negative samples are the unsuccessful bids of the enterprises. The bidding information, regional information, and personnel information are associated around these bidding information to form sample data. The features of the data set are processed by common feature engineering methods such as null values, outliers, category one-hot, discretization, etc. according to the features under the feature domains such as bidding information, regional information, and personnel information, and the sample set is divided into training samples and test samples.

[0103] Use the XGBoost algorithm model to build a model, input the training samples into the model training, use the test samples to evaluate the model, and use common evaluation indicators such as AUC, F1 value, accuracy, etc. to adjust the model parameters and select the better model for use. Use the output model to calculate the possible winning probability value P of all published business opportunities in a certain area within a time window for the enterprise i . Associate the published business opportunities with the relevant enterprise, region, and personnel information to form samples to be predicted, input them into the trained model, and output the probability value.

[0104] “Number of potential business opportunities” is the expected number of business opportunities to be released. n is the number of business opportunities released in a time window; "potential business opportunity amount" is the expected amount of the bidding for the released business opportunity M i is the bidding amount for each published business opportunity; “Potential business opportunity quantity ratio” is E1 / n; “Potential business opportunity amount ratio” is

[0105] For example, when the predictive indicator is customer situation, calculations are performed on potential customers, similar to the steps for calculating potential business opportunities. A potential customer classification model is constructed and the probability of the bidding unit being a potential customer is calculated, and then the relevant factor values ​​under the "customer situation" indicator are calculated.

[0106] Specifically, based on the historical bidding and winning data of construction enterprises, the bidding units of the winning projects are real customers, i.e., positive samples, and the bidding units of the projects that bid but did not win are non-customers, i.e., negative samples. Features and samples are constructed based on the category, region, historical projects, industry, scale, risk and other information related to the customer's enterprise or entity, and the customer classification model is trained. The trained model is combined with the features constructed by the bidding units that publish bidding information in a certain region to calculate the probability value P of customer i in the region becoming a potential customer. i .

[0107] Let n be the number of customers who publish business opportunities in a time window W in a certain region, and the "number of customers" factor is the number of actual customers N1 plus the expected number of potential customers That is, E3+N1; the "customer opportunity amount" factor is the sum of the budget amounts of bidding information released by actual customers, N2, plus the expected budget amounts of bidding information released by potential customers. That is, E4+N2, where M i is the sum of the amounts of tender information released by customer i within W; the factor of “customer quantity ratio” is (E3+N1) / n; the factor of “customer opportunity amount ratio” is

[0108] For example, when the predictive indicator is the competitive situation, the potential competitors are calculated, a potential competitor classification model is constructed, and the probability of the winning bidder being a potential competitor is calculated, and then the relevant factor values ​​under the "competitive situation" indicator are calculated.

[0109] Specifically, the winning bidders (not the company) of the construction enterprise's historical bidding projects are the real competitors, i.e., positive samples. Other bidders that did not win the bid are non-competitors, i.e., negative samples. Features and samples are constructed based on the bidding unit's category, region, historical projects, industry, scale, risk, honor, amount, and other information. The competitor classification model is trained, and the trained model is combined with the features constructed by the winning bidders in the bidding information released in a certain region to calculate the probability value P of the winning bidder in the region becoming a potential competitor. i .

[0110] Let n be the number of all winning enterprises that publish winning bid information in a time window W in a certain region, and the “number of competitors” factor be the actual number of local competitors N3 plus the expected number of potential competitors that the enterprise believes. That is, E5+N3; the “proportion of number of competitors” factor is (E5+N3) / n.

[0111] In the above implementation, the normalization process adjusts the expected value to a uniform scale, making different indicators comparable and improving the consistency of the data. Through the proportion value, the importance or influence of each predictive indicator in the whole can be intuitively understood, which is convenient for evaluation and analysis. The consistency of factor values ​​in different data sets and time points is ensured, and the stability and reliability of the evaluation results are enhanced.

[0112] Step S2023, determining the second factor value corresponding to each statistical indicator.

[0113] The second factor value refers to the result calculated from actual data, which is used to quantify the actual situation of the current market or the existing business environment. The second factor value is the result of a statistical indicator, reflecting the real situation of the current market. Specifically, the required statistical data, namely the second factor value, can be extracted from the building data.

[0114] In some optional implementations, the above step S2023 includes:

[0115] Step d1, extracting attribute data corresponding to statistical indicators from building data.

[0116] Attribute data refers to the specific information and data items used to calculate statistical indicators. Specifically, the specific field information related to the calculation of statistical indicators is extracted from the database storing building data. The relevant data is screened out according to the needs of the statistical indicators, and the screened data is integrated to form an attribute data set containing all relevant information.

[0117] Step d2, classify and count the attribute data to obtain the second factor value.

[0118] Specifically, the extracted attribute data are grouped according to certain features or categories, statistical operations are performed under each category, and the obtained statistics are the second factor values.

[0119] For example, when the statistical indicator is the degree of openness, data such as the number and companies of winning bids and candidate bids are obtained from the data warehouse, and statistics are collected based on the geographical characteristics and types of the winning bidders and candidate bids.

[0120] For example, when the statistical indicator is the opportunity index, data such as quantity, amount, and enterprise related to the winning bid information is obtained from the data warehouse, and statistics are collected on the winning bid quantity, winning bid amount, regional characteristics, and type of the winning bidders.

[0121] In the above implementation, by classifying and counting attribute data, the second factor value of the statistical indicator can be determined based on actual data, thereby enhancing the objectivity of the evaluation. Classification and statistics enable data of different attributes to be systematically sorted and analyzed, thereby improving the clarity of data processing. The data after classification and statistics can more conveniently compare different indicators, thus supporting more comprehensive evaluation and analysis.

[0122] Step S203: transform the factor values ​​to obtain the index scores corresponding to each index. Figure 1 Step S103 of the illustrated embodiment will not be described in detail here.

[0123] Step S204: Generate building assessment results for the area to be assessed based on the index scores. Figure 1 Step S104 of the illustrated embodiment will not be described in detail here.

[0124] In this embodiment, a method for evaluating building data is provided, which can be used for computer equipment, such as desktop computers, notebook computers, etc. Figure 3 is a flow chart of a method for evaluating building data according to an embodiment of the present invention. Figure 3 As shown, the process includes the following steps:

[0125] Step S301, obtain the building data and preset evaluation indicators of the area to be evaluated. Figure 2 Step S201 of the illustrated embodiment will not be described in detail here.

[0126] Step S302: Decompose the building data according to the preset evaluation index, obtain multiple indexes and factors corresponding to each index, and determine the factor value corresponding to each index. Figure 2Step S202 of the illustrated embodiment will not be described in detail here.

[0127] Step S303: transform the factor values ​​respectively to obtain the indicator scores corresponding to the indicators.

[0128] Specifically, the above step S303 includes:

[0129] Step S3031: for any indicator, pre-process the factor value corresponding to the indicator to obtain multiple third factor values ​​corresponding to the indicator.

[0130] Multiple third factor values ​​refer to specific factor values ​​that are further refined under the indicator. For any indicator, the factor value corresponding to the indicator is processed positively and standardized to obtain multiple third factor values ​​corresponding to the indicator. Specifically, there are different methods for positive conversion according to the physical meaning of different factor values ​​under the indicator. The positive conversion methods of each factor value are shown in Table 2. There are three calculation methods involved and the percentage system is used, such as Figure 4 As shown, calculation method 1 is applicable to the factor value of "the bigger the better", using the formula (X-min) / (max-min)×100. For a certain factor, X is the value of a certain region, min is the minimum value of all regions, and max is the maximum value of all regions. Calculation method 2 is applicable to the factor value of "the smaller the better", using the formula (max-X) / (max-min)×100, where the symbol meaning is the same as calculation method 1. Calculation method 3 is applicable to "the closer to the middle, the better", but the "good trend" near the middle is different, using the parabola formula Y=a(Xh) 2 +k, where k = 100, h = (max + min) / 2, a = -400 / (max - min) 2 .

[0131] Table 2

[0132]

[0133]

[0134] Furthermore, the values ​​after normalization may represent quantity, amount, or ratio, and need to be compared under the same metric. Therefore, it is necessary to remove the dimension of the standardized calculation. x i is the value of a factor in a certain region after positive transformation, The square sum of all regions of the factor value is calculated by this formula. The standardized value remains positive. Construct a standard matrix for a certain level of indicators Where n is the number of regions, m is the number of factors that the first-level indicator is broken down into, and z ijis the j factor value of region i after positive and normalization.

[0135] Step S3032: perform data processing on multiple third factor values ​​to determine the optimal solution distance and the worst solution distance.

[0136] The optimal solution distance refers to the distance between the factor value of a certain region and the best (ideal) factor value among all solutions. The worst solution distance refers to the distance between the factor value of a certain region and the worst (worst) factor value among all solutions. Specifically, the ideal solution and the worst solution among multiple third factor values ​​are determined, and the optimal solution distance and the worst solution distance are calculated based on the ideal solution and the worst solution.

[0137] In some optional implementations, the above step S3032 includes:

[0138] Step e1, determining the best value and the worst value from multiple third factor values.

[0139] After constructing the standard matrix Z, for a certain indicator with n regions and m factors, the optimal solution vector Z for each factor can be obtained: + (optimal value) and the worst solution vector Z - (Worst value):

[0140]

[0141]

[0142] Step e2, determining the optimal solution distance based on the difference between the optimal value and the third factor value.

[0143] Specifically, for the i-th region, calculate the optimal solution distance

[0144] Step e3, determining the worst solution distance based on the difference between the worst value and the third factor value.

[0145] Specifically, for the i-th region, calculate the worst solution distance

[0146] In the above implementation, by determining the best value and the worst value, the reference point of the evaluation can be clearly set, so that the performance of the indicator has a clear basis for comparison. Calculating the best solution distance and the worst solution distance can accurately reflect the difference between the third factor value and the extreme case, and help identify extreme performance in the data. By calculating the distance based on actual data, a more accurate indicator score can be provided, reducing subjective bias.

[0147] Step S3033, determining the index score according to the sum of the optimal solution distance and the worst solution distance.

[0148] Specifically, the score of the i-th region is Among them, for the convenience of display and comparison, it can be converted into a percentage system

[0149] The building data evaluation method provided by the embodiment of the present invention can comprehensively reflect different aspects of the index by processing multiple third factor values, thereby improving the accuracy of the evaluation. Determining the optimal solution distance and the worst solution distance is helpful for relative comparison and quantifying the performance range and difference of the index. The index score is calculated based on the optimal solution and the worst solution distance, making the final result more representative and reasonable. The optimal solution and the worst solution distance can be adjusted according to the change of data, thereby improving the flexibility and real-time performance of the evaluation.

[0150] Step S304: Generate a building assessment result for the area to be assessed based on the index score.

[0151] Specifically, the above step S304 includes:

[0152] Step S3041, determine the weight corresponding to each indicator.

[0153] Weight is the relative importance of an indicator in a comprehensive evaluation. It indicates the degree of influence of a certain indicator on the overall evaluation. Specifically, a judgment matrix is ​​constructed, and multiple measurement indicators of the judgment matrix are calculated, such as the maximum characteristic root, consistency index, etc., and the weight corresponding to each indicator is determined based on multiple measurement indicators.

[0154] In some optional implementations, the above step S3041 includes:

[0155] Step f1, obtain the number of indicators and feature evaluation data.

[0156] The number of indicators refers to the total number of indicators used for evaluation. Specifically, the number of indicators to be evaluated is determined, for example, 5. Based on all the indicators, the importance relationship between the first-level indicators of the enterprise is judged by the enterprise's own experts. The standards are shown in Table 3. The judgment matrix A is constructed. 5×5 , where the matrix elements satisfy a ij >0,a ij =1 / a ji , a ii =1 three conditions.

[0157] Table 3

[0158] Scale value meaning 1 Indicates that two elements have the same importance. 3 Indicates that compared with two elements, the former is slightly more important than the latter 5 Indicates that compared with two elements, the former is obviously more important than the latter 7 Indicates that compared with two elements, the former is extremely important than the latter 9 Indicates that compared with two elements, the former is more important than the latter 2,4,6,8 Indicates the middle value of the above adjacent judgments reciprocal Indicates the importance of comparing the corresponding two factors in the order of swapping

[0159] The feature evaluation data is the maximum eigenvalue λ of the judgment matrix A calculated by matrix decomposition method. max .

[0160] Step f2, determining the consistency index based on the difference between the feature evaluation data and the index quantity.

[0161] The consistency index (CI) is a measure used to measure the consistency of the judgment matrix. Specifically, the consistency index is calculated Where n is the number of indicators.

[0162] Step f3, determining the random consistency index corresponding to the number of indicators.

[0163] Random Consistency Index (RI) is used to evaluate the consistency of the judgment matrix. RI is the average consistency index calculated based on the randomly generated judgment matrix, which is used to compare with the CI of the actual judgment matrix. Specifically, the size of the random consistency index RI at n is obtained by looking up the table.

[0164] Step f4, obtaining the weight based on the normalization results of the consistency index and the random consistency index.

[0165] Specifically, the consistency ratio (CR) is calculated according to the consistency index and the random consistency index, and the feature evaluation data is normalized according to the consistency ratio to obtain the weight.

[0166] In the above implementation, by obtaining the number of indicators and feature evaluation data, it is ensured that the weight determination process has a systematic basis and reduces subjectivity. By comparing the consistency index and the random consistency index, the rationality and consistency of the weight can be ensured, and the reliability of the evaluation results can be improved. The normalized processing method standardizes the calculation of the weight and avoids the impact of differences in indicator scales. Comprehensive consideration of consistency and randomness makes the final weight distribution more accurate and scientific.

[0167] In some optional implementations, the above step f4 includes:

[0168] Step g1, determining the ratio of the consistency index to the random consistency index as the consistency ratio.

[0169] Specifically, the consistency ratio CR=CI / RI of the judgment matrix A is calculated.

[0170] Step g2: when the consistency ratio is less than a preset threshold, the feature evaluation data is normalized to obtain the weight corresponding to each indicator.

[0171] Specifically, when CR is less than a preset threshold, it indicates that the consistency of the judgment matrix is ​​within the allowable range, otherwise the judgment matrix needs to be corrected until CR is less than the preset threshold. For example, the preset threshold can be 0.1. When the consistency level is met, the eigenvector corresponding to the maximum eigenroot of the judgment matrix A can be used as the weight vector of the corresponding indicator after normalization.

[0172] In the above implementation, by calculating the ratio of the consistency index to the random consistency index, the consistency level in the evaluation process can be quantified to ensure the rationality of the weight distribution. The calculation of the consistency ratio provides an objective basis and reduces the subjective judgment in the weight determination process. By setting a preset threshold, the consistency level requirement can be controlled to ensure that the weight calculation is performed only when the consistency is high enough, thereby enhancing the stability and reliability of the evaluation. The feature evaluation data is normalized so that the weight calculation is not affected by the scale of the original data, thereby improving the consistency and comparability of the results.

[0173] Step S3042: Perform weighted processing based on the weights to obtain a total portrait score corresponding to the area to be evaluated.

[0174] The total portrait score refers to the comprehensive score obtained by weighting the scores of each indicator according to their weights. Specifically, the regional portrait score of each region is obtained by multiplying the indicator score and the corresponding weight of each indicator.

[0175] Step S3043, generating a building assessment result according to the total portrait score.

[0176] The total portrait score is calculated offline on the big data platform. The scores of each region and the corresponding indicator scores are calculated regularly through scheduled tasks. When used in the business system, the scores can be obtained through interface calls. The recommended scores and indicator scores of each region can be intuitively displayed in the form of a radar chart to compare the situations in certain regions horizontally or vertically. All regions can also be sorted by regional portrait scores, and suitable regions can be recommended to the business system for subsequent reference by business personnel.

[0177] The building data evaluation method provided by the embodiment of the present invention can comprehensively evaluate the impact of different indicators on the overall building performance by determining the weight of each indicator to ensure a comprehensive evaluation. Weighting each indicator makes the evaluation result more consistent with the actual situation and importance, avoiding the deviation that may be caused by simple averaging. Calculating the total portrait score provides a comprehensive evaluation result, making complex evaluation data more intuitive and easy to understand. By generating a building evaluation result, the overall performance of the area to be evaluated can be clearly reflected, helping decision-making and optimization.

[0178] In this embodiment, a building data evaluation device is also provided, which is used to implement the above embodiments and preferred implementations, and the descriptions that have been made will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0179] This embodiment provides a building data evaluation device, such as Figure 5 As shown, including:

[0180] The acquisition module 501 is used to acquire the building data of the area to be evaluated and the preset evaluation index.

[0181] The decomposition module 502 is used to decompose the building data according to the preset evaluation index, obtain multiple indexes and factors corresponding to each index, and determine the factor value corresponding to each index.

[0182] The processing module 503 is used to transform the factor values ​​respectively to obtain the indicator scores corresponding to the various indicators.

[0183] The generating module 504 is used to generate the building assessment result of the area to be assessed based on the index score.

[0184] In some optional embodiments, the disassembly module 502 includes:

[0185] The first extraction submodule is used to extract business object data corresponding to the predictive index from the building data.

[0186] The first data processing submodule is used to process the business object data to obtain the prediction probability corresponding to each business object.

[0187] The accumulation submodule is used to accumulate the predicted probabilities to obtain the expected values ​​corresponding to the predictive indicators.

[0188] The processing submodule is used to process the expected value to obtain the first factor value.

[0189] In some optional implementations, the processing submodule includes:

[0190] The normalization processing unit is used to normalize the expected value to obtain the proportion value corresponding to the predictive indicator.

[0191] The first determining unit is used to determine the expected value and the proportion value as the first factor value.

[0192] In some optional embodiments, the disassembly module 502 further includes:

[0193] The second extraction submodule is used to extract attribute data corresponding to the statistical indicators from the building data.

[0194] The statistical submodule is used to classify and count the attribute data to obtain the second factor value.

[0195] In some optional implementations, the processing module 503 includes:

[0196] The preprocessing submodule is used to preprocess the factor value corresponding to any indicator to obtain multiple third factor values ​​corresponding to the indicator.

[0197] The second data processing submodule is used to perform data processing on multiple third factor values ​​to determine the optimal solution distance and the worst solution distance.

[0198] The first determination submodule is used to determine the index score according to the sum of the optimal solution distance and the worst solution distance.

[0199] In some optional implementations, the second data processing submodule includes:

[0200] The second determining unit is used to determine the best value and the worst value from a plurality of third factor values.

[0201] The third determining unit is used to determine the optimal solution distance based on the difference between the optimal value and the third factor value.

[0202] The fourth determining unit is used to determine the worst solution distance based on the difference between the worst value and the third factor value.

[0203] In some optional implementations, the generating module 504 includes:

[0204] The second determination submodule is used to determine the weight corresponding to each indicator.

[0205] The weighted processing submodule is used to perform weighted processing based on weights to obtain a total image score corresponding to the area to be evaluated.

[0206] The generation submodule is used to generate building assessment results based on the total portrait score.

[0207] In some optional implementations, the second determining submodule includes:

[0208] The acquisition unit is used to obtain the indicator quantity and feature evaluation data.

[0209] The fifth determining unit is used to determine the consistency index according to the difference between the feature evaluation data and the index quantity.

[0210] The sixth determining unit is used to determine a random consistency indicator corresponding to the indicator quantity.

[0211] The seventh determination unit is used to obtain the weight based on the normalization processing results of the consistency index and the random consistency index.

[0212] In some optional implementations, the seventh determining unit includes:

[0213] The first determining subunit is used to determine the ratio of the consistency index to the random consistency index as the consistency ratio.

[0214] The second determination subunit is used to normalize the feature evaluation data to obtain the weight corresponding to each indicator when the consistency ratio is less than a preset threshold.

[0215] In some optional implementations, the acquisition module 501 includes:

[0216] The acquisition submodule is used to obtain the initial data of the area to be evaluated.

[0217] The data governance submodule is used to perform data governance on the initial data to obtain building data.

[0218] In some optional implementations, the data governance submodule includes:

[0219] The data cleaning unit is used to clean the initial data to obtain first data.

[0220] The data normalization unit is used to perform data normalization on the first data to obtain the second data.

[0221] The data association unit is used to perform data association on the second data to obtain third data.

[0222] The field expansion unit is used to expand the fields of the third data to obtain building data.

[0223] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0224] The building data evaluation device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0225] The building data evaluation device provided by the embodiment of the present invention can provide consistent evaluation standards and reduce human errors by presetting evaluation indicators and systematic factor decomposition. The conversion process ensures the comparability of various indicators, and the evaluation results generated in the end are more objective and accurate. In addition, the calculation and judgment basis of each step can be clearly tracked, which improves the transparency and reliability of the evaluation.

[0226] The embodiment of the present invention also provides a computer device having the above Figure 5 An evaluation device for building data is shown.

[0227] See also Figure 6 , Figure 6 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 6 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 6 A processor 10 is taken as an example.

[0228] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0229] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.

[0230] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0231] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0232] The computer device also includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Figure 6 The example of connecting through bus is taken in the following.

[0233] The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator bar, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device can be a touch screen.

[0234] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0235] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0236] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for evaluating building data, characterized in that: The method comprises: Obtain building data and preset evaluation indicators for the area to be evaluated; Decomposing the building data according to preset evaluation indicators to obtain multiple indicators and factors corresponding to each indicator, and determining the factor value corresponding to each indicator; The factor values ​​are transformed respectively to obtain the indicator scores corresponding to the various indicators; A building assessment result of the area to be assessed is generated based on the indicator score.

2. The method according to claim 1, characterized in that The indicator includes a predictive indicator, and the factor value includes a first factor value corresponding to the predictive indicator; The determining of the factor value corresponding to each of the indicators includes: Extracting business object data corresponding to the predictive indicator from the building data; Processing the business object data to obtain prediction probabilities corresponding to each business object; Accumulating the predicted probabilities to obtain an expected value corresponding to the predictive indicator; The expected value is processed to obtain the first factor value.

3. The method according to claim 2, characterized in that The processing of the expected value to obtain the first factor value includes: Normalizing the expected value to obtain a percentage value corresponding to the predictive indicator; The expected value and the proportion value are determined as the first factor value.

4. The method according to claim 2, characterized in that The indicator further includes a statistical indicator, and the factor value further includes a second factor value corresponding to the statistical indicator; and determining the factor value corresponding to each of the indicators includes: Extracting attribute data corresponding to the statistical indicator from the building data; Classify and count the attribute data to obtain the second factor value.

5. The method according to claim 1, characterized in that The converting of the factor values ​​to obtain the index scores corresponding to the respective indexes includes: For any one of the indicators, preprocess the factor value corresponding to the indicator to obtain a plurality of third factor values ​​corresponding to the indicator; Performing data processing on the plurality of third factor values ​​to determine an optimal solution distance and a worst solution distance; The indicator score is determined according to the sum of the optimal solution distance and the worst solution distance.

6. The method according to claim 5, characterized in that The performing data processing on the third factor value to determine the optimal solution distance and the worst solution distance includes: determining a best value and a worst value from among the plurality of third factor values; Determining the optimal solution distance based on a difference between the optimal value and the third factor value; The worst solution distance is determined based on a difference between the worst value and the third factor value.

7. The method according to claim 1, characterized in that The generating of the building assessment result of the area to be assessed based on the indicator score includes: Determine the weight corresponding to each of the indicators; Performing weighted processing based on the weights to obtain a total portrait score corresponding to the area to be evaluated; The building assessment result is generated according to the total portrait score.

8. The method according to claim 7, characterized in that The determining of the weights corresponding to the indicators includes: Obtain indicator quantity and feature evaluation data; Determining a consistency index based on the feature evaluation data and the difference between the indicator quantity; determining a random consistency index corresponding to the number of indicators; The weight is obtained based on the normalization result of the consistency index and the random consistency index.

9. The method according to claim 8, characterized in that The normalization processing result based on the consistency index and the random consistency index is used to obtain the weight, including: determining a ratio of the consistency index to the random consistency index as a consistency ratio; When the consistency ratio is less than a preset threshold, the feature evaluation data is normalized to obtain the weights corresponding to the various indicators.

10. The method according to claim 1, characterized in that The step of obtaining building data of the area to be evaluated includes: Acquiring initial data of the area to be evaluated; Perform data management on the initial data to obtain the building data.

11. The method according to claim 10, characterized in that The performing data management on the initial data to obtain the building data includes: Performing data cleaning on the initial data to obtain first data; performing data normalization on the first data to obtain second data; Performing data association on the second data to obtain third data; The third data is subjected to field expansion to obtain the building data.

12. A building data evaluation device, characterized in that: The device comprises: An acquisition module is used to obtain the building data of the area to be evaluated and the preset evaluation indicators; A disassembly module is used to disassemble the building data according to preset evaluation indicators, obtain multiple indicators and factors corresponding to each indicator, and determine the factor value corresponding to each indicator; A processing module, used to transform the factor values ​​respectively to obtain the indicator scores corresponding to the various indicators; A generating module is used to generate a building assessment result of the area to be assessed based on the indicator score.

13. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the building data evaluation method according to any one of claims 1 to 11 by executing the computer instructions.

14. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the building data evaluation method according to any one of claims 1 to 11.

15. A computer program product, characterized in that The method comprises computer instructions for causing a computer to execute the building data evaluation method according to any one of claims 1 to 11.

Images