Index data determination method and device, equipment and computer storage medium
Through feature extraction and matrix operation of regional division grid and target model, the problem of inaccurate assessment results in traditional assessment plans is solved, personalized indicator data allocation is realized, and the accuracy and fairness of assessment results are improved.
Patent Information
- Application Number
- CN202411181843.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-27
- Publication Date
- 2024-11-29
AI Technical Summary
Traditional business performance assessment plans rely on managers' experience, resulting in inaccurate assessment results and failure to consider the specific environment and conditions of the operating unit.
The target area is divided into multiple assessment objects through the regional division grid. The target model is used to extract and matrix operations on historical business data and market environment data, and determine and allocate personalized indicator data to improve the accuracy of assessment results.
The accuracy and fairness of the assessment results are improved, so that each assessment object can obtain appropriate indicator data based on its unique historical operating data and market environment, thereby more accurately reflecting its operating results.
Smart Images

Figure CN119047920A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of computers, and in particular to a method, device, equipment, computer storage medium and computer program product for determining indicator data. Background Art
[0002] At present, the management usually adopts the scheme of formulating operating assessment indicators to assess the assessment objects, such as the scheme of formulating operating assessment indicators such as net profit, sales volume, customer unit price, business volume, return on investment, etc. The management distributes the key performance indicators (KPI) of the assessment indicators to the assessment objects. After the assessment objects receive the assessment KPIs, they carry out targeted operating work according to the assessment indicators, so as to achieve the expected operating results of the management.
[0003] However, the management mainly relies on the experience of managers to formulate the assessment index data for the assessment objects, which makes the process of formulating the assessment index data unfair and leads to inaccurate assessment results. Summary of the invention
[0004] The embodiments of the present disclosure provide a method, apparatus, device, computer storage medium, and computer program product for determining indicator data, which can improve the accuracy of assessment results.
[0005] In a first aspect, an embodiment of the present disclosure provides a method for determining indicator data, the method comprising:
[0006] The target area is divided by using the area division grid to obtain multiple assessment objects;
[0007] Inputting the historical operating data and market environment data corresponding to the multiple assessment objects into the target model, extracting features from the historical operating data and market environment data through the target model, and obtaining feature data;
[0008] Perform matrix operations on the characteristic data through the target model to obtain the target parameters, and determine multiple indicator data based on the target function corresponding to the target parameters;
[0009] Assign multiple indicator data to corresponding assessment objects.
[0010] In one practicable implementation, the region division grid includes a square grid, and the target region is divided by the region division grid to obtain multiple assessment objects, including:
[0011] Multiple continuous square grids are superimposed on the target area and divided into multiple assessment objects.
[0012] In one practicable implementation, before inputting the historical operating data and market environment data corresponding to the plurality of assessment objects into the target model, the method further includes:
[0013] Perform text filtering on historical operating data and market environment data to obtain filtered data;
[0014] Normalize the filtered data to obtain normalized historical operating data and market environment data;
[0015] The historical operating data and market environment data corresponding to the multiple assessment objects are respectively input into the target model, and the feature data are extracted from the historical operating data and market environment data through the target model to obtain feature data, including:
[0016] The normalized historical operating data and market environment data corresponding to the multiple assessment objects are respectively input into the target model, and the features of the historical operating data and market environment data are extracted through the target model to obtain feature data.
[0017] In one practicable implementation, text filtering is performed on historical operating data and market environment data to obtain filtered data, including:
[0018] Filter out non-repetitive and complete data from historical operating data and market environment data to obtain filtered data;
[0019] The filtered data is mapped using a character mapping method, and the mapped result is matched with a keyword to obtain the filtered data.
[0020] In one practicable implementation, the filtered data is normalized to obtain normalized historical operating data and market environment data, including:
[0021] Perform feature extraction on the filtered data to obtain target feature data;
[0022] Convert target feature data into corresponding semantic information;
[0023] The semantic information is processed using a normalization model based on a recurrent neural network to obtain a processing result;
[0024] Based on the processing results, normalized historical operating data and market environment data are obtained.
[0025] In one achievable implementation, a target model is used to perform matrix operations on feature data to obtain target parameters, and multiple indicator data are determined based on a target function corresponding to the target parameters, including:
[0026] Obtain assessment indicators from the assessment indicator library;
[0027] Based on the characteristic data corresponding to the historical operating data and the market environment data, matrix operations are performed on the characteristic data by minimizing the error sum of squares method to obtain the regression coefficients corresponding to the characteristic data;
[0028] Based on the regression coefficients corresponding to the characteristic data, a plurality of objective functions corresponding to the assessment indicators are determined, wherein each objective function corresponds to an assessment object;
[0029] Based on multiple objective functions, indicator data corresponding to multiple assessment objects are determined.
[0030] In one practicable implementation, after allocating the plurality of indicator data to corresponding assessment objects, the method further includes:
[0031] Collect the latest operating data of multiple assessment objects in real time;
[0032] Based on the latest operating data and indicator data, weighted calculations are performed to obtain assessment scores for multiple assessment objects.
[0033] In a second aspect, an embodiment of the present disclosure provides a device for determining indicator data, the device comprising:
[0034] A division module is used to divide the target area using a regional division grid to obtain multiple assessment objects;
[0035] An input module is used to input the historical operating data and market environment data corresponding to the multiple assessment objects into the target model, and extract features from the historical operating data and market environment data through the target model to obtain feature data;
[0036] An operation module, used to perform matrix operation on the feature data through the target model to obtain the target parameters, and determine multiple indicator data based on the target function corresponding to the target parameters;
[0037] The allocation module is used to allocate multiple indicator data to corresponding assessment objects.
[0038] In a third aspect, an embodiment of the present disclosure provides a device for determining indicator data, the device comprising a processor and a memory storing computer program instructions; the processor reads and executes the computer program instructions to implement a method for determining indicator data as described in any one of the first aspects.
[0039] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, a method for determining indicator data as described in any one of the first aspects is implemented.
[0040] In a fifth aspect, an embodiment of the present disclosure provides a computer program product, including a computer program, which, when executed by a processor, implements a method for determining indicator data as described in any one of the first aspects.
[0041] The disclosed embodiments provide a method, device, equipment, computer storage medium and computer program product for determining indicator data. The target area is divided by a regional division grid to obtain multiple assessment objects. The historical operating data and market environment data corresponding to the multiple assessment objects are respectively input into the target model, and the historical operating data and market environment data are extracted by the target model to obtain feature data. The target model performs matrix operations on the feature data to obtain target parameters, and multiple indicator data are determined based on the target function corresponding to the target parameters. The multiple indicator data are assigned to the corresponding assessment objects. The disclosed embodiments divide the target area into multiple assessment objects by a regional division grid, so that each assessment object has corresponding historical operating data and market environment data, and then the corresponding indicator data is assigned to each assessment object according to the target model, thereby improving the accuracy of the assessment results. BRIEF DESCRIPTION OF THE DRAWINGS
[0042] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the following is a brief introduction to the drawings required for use in the embodiment of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0043] Figure 1 It is a flowchart of a method for determining indicator data provided by an embodiment of the present disclosure;
[0044] Figure 2 is a schematic diagram of historical business data provided by an embodiment of the present disclosure;
[0045] Figure 3 It is a flowchart of a text filtering method provided by an embodiment of the present disclosure;
[0046] Figure 4 is a flowchart of another text filtering method provided by an embodiment of the present disclosure;
[0047] Figure 5 is a schematic diagram of an objective function provided by an embodiment of the present disclosure;
[0048] Figure 6 is a structural diagram of a device for determining indicator data provided by an embodiment of the present disclosure;
[0049] Figure 7 It is a structural diagram of an indicator data determination device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION
[0050] The features and exemplary embodiments of various aspects of the present invention will be described in detail below. In order to make the purpose, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present invention, rather than to limit the present invention. For those skilled in the art, the present invention can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present invention by illustrating examples of the present invention.
[0051] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.
[0052] Before describing the technical solutions provided by the embodiments of the present disclosure, in order to facilitate understanding of the embodiments of the present disclosure, the present disclosure specifically describes the problems existing in the related technologies:
[0053] Traditional business performance appraisal plans usually adopt the formulation of business appraisal indicators, such as net profit, sales volume, average customer spending, business volume, return on investment, etc. The management allocates the KPI of the appraisal indicator to the appraisal object. After the appraisal object receives the appraisal KPI, it performs targeted business work according to the appraisal indicator items. During the appraisal period, the management counts the completion value of the appraisal indicator. By comparing the completion value of the appraisal object with the KPI target value, the management intuitively reflects the operating results and performance of the appraisal object, and is used to calculate and compare the operating performance of the appraisal object, and rewards and punishments are given through ranking.
[0054] However, this type of assessment method does not take into account the differences in innate conditions such as the operating environment, customer base, resource input, business trends, etc. of each business unit. It relies on managers' experience to manually assign KPIs, which does not match the actual basic conditions and resource conditions of each business unit, resulting in inaccurate assessment results.
[0055] The embodiments of the present disclosure provide a method, apparatus, device, computer storage medium and computer program product for determining indicator data, which can solve the above-mentioned technical problems existing in the related technologies.
[0056] The disclosed embodiment uses a regional division grid to divide the target area to obtain multiple assessment objects. The historical operating data and market environment data corresponding to the multiple assessment objects are respectively input into the target model, and the historical operating data and market environment data are extracted through the target model to obtain feature data. The target model performs matrix operations on the feature data to obtain target parameters, and multiple indicator data are determined based on the target function corresponding to the target parameters. The multiple indicator data are assigned to the corresponding assessment objects. The disclosed embodiment divides the target area into multiple assessment objects through a regional division grid, so that each assessment object has corresponding historical operating data and market environment data, and then the corresponding indicator data is assigned to each assessment object according to the target model, thereby improving the accuracy of the assessment results.
[0057] Figure 1 FIG. 1 is a flow chart showing a method for determining indicator data provided by an embodiment of the present disclosure. Figure 1 , the method may include steps S110-S140.
[0058] S110: Divide the target area by using the area division grid to obtain multiple assessment objects.
[0059] Based on the regional division grid, the target area is divided by the regional division grid to obtain multiple assessment objects, wherein each assessment object includes multiple regional division grids, and each assessment object represents a business unit.
[0060] The size and density of the area division grid are preset. The target area can be an administrative area or a logical management area.
[0061] The assessment objects include business data and resource data. By dividing the administrative areas using grids, multiple assessment objects with corresponding business data and resource data are obtained. After the assessment objects are produced and operated for a period of time according to the corresponding business data and resource data, the corresponding historical operation data is obtained.
[0062] S120: Inputting the historical operating data and market environment data corresponding to the multiple assessment objects into the target model, extracting features from the historical operating data and market environment data through the target model, and obtaining feature data.
[0063] After obtaining the historical operating data and market environment data corresponding to the multiple assessment objects, the historical operating data and market environment data corresponding to the multiple assessment objects are input into the target model. The target model is used to extract feature data corresponding to the assessment indicators required for this assessment from the historical operating data and market environment data.
[0064] In one embodiment, the historical business data may include user data, business acceptance data, product data, sales volume data, financial indicator data, customer satisfaction data, and other data.
[0065] Market environment data may include environment type data such as residential area, commercial area, development area, etc.
[0066] The characteristic data may be monthly sales volume in sales volume data, market environment data including environment type data, and product color, product model and price in product data.
[0067] The historical operating data and market environment data corresponding to multiple assessment objects are respectively input into the target model. Based on the obtained assessment indicator for this time, namely sales volume, characteristic data corresponding to the sales volume are extracted from the characteristics of the historical operating data and market environment data according to the target model to obtain characteristic data such as monthly sales volume, product color, product model, price, and environmental type data. Among them, monthly sales volume is regarded as an independent variable, and product color, product model, price, and environmental type data are regarded as dependent variables.
[0068] In one example, a scatter plot of historical operating data is shown in Figure 2 As shown, the horizontal axis represents the monthly sales volume, and the vertical axis represents the month. The corresponding sales volume in January is 6530, the corresponding sales volume in February is 4560, the corresponding sales volume in March is 2110, the corresponding sales volume in April is 3340, the corresponding sales volume in May is 4520, the corresponding sales volume in June is 5530, the corresponding sales volume in July is 5100, the corresponding sales volume in August is 5210, the corresponding sales volume in September is 5530, and the corresponding sales volume in October is 5460.
[0069] S130: Obtain target parameters by performing matrix operations on the feature data, and determine a plurality of indicator data based on the target function corresponding to the target parameters.
[0070] In one embodiment, the matrix vector corresponding to the extracted feature data is subjected to matrix operation based on the minimum square error method to obtain the target parameter.
[0071] In one example, the target parameter may be a regression coefficient, and the target function corresponding to the target parameter may be a multivariate linear regression equation.
[0072] The process of determining multiple indicator data based on the objective function corresponding to the target parameter is: Determine the target function based on the target parameter, as shown in formula (1), the process of determining the target function based on the target parameter: Substitute the target parameter into formula (1) to obtain the target function f(x i ).
[0073] f(x i)= w1x1+ w2x2+…+ w k x k +b (1)
[0074] Among them, w1…w k and b represent regression coefficients.
[0075] The process of determining multiple indicator data according to the objective function is: k Substituting into formula (1), we get the index data f(x i ).
[0076] In one example, feature data x1...x k It can be data such as product price, product logo, product type, etc. The indicator data f(x i ) can be monthly sales volume, w1…w k The regression coefficients represented by and b can be weight coefficients such as 0.1, 0.5 or 0.6.
[0077] S140: Allocate multiple indicator data to corresponding assessment objects.
[0078] After the target model determines multiple indicator data, the indicator data is sent to the corresponding assessment object through the system, so that the assessment object operates according to the assigned indicator data.
[0079] The disclosed embodiment divides the target area into multiple assessment objects through a grid, so that each assessment object has corresponding historical operating data and market environment data, and then allocates corresponding indicator data to each assessment object according to the target model, thereby improving the accuracy of the assessment results.
[0080] In one embodiment, after the indicator data is obtained, the interquartile range (IQR) method or the Z-score method may be used to detect outliers in the indicator data, and the outliers may be removed or replaced according to business logic.
[0081] In one embodiment, the area division grid includes a square grid, and the target area is divided by the area division grid to obtain a plurality of assessment objects, which may include step S111.
[0082] S111: Overlaying a plurality of continuous square grids on the target area, and dividing the target area to obtain a plurality of assessment objects.
[0083] In one embodiment, a plurality of continuous square grids with an area of 0.25 square kilometers are superimposed on the target area, and a corresponding relationship between the grids and the target area is established according to longitude and latitude to obtain a plurality of assessment objects.
[0084] The size range of the grid is not fixed. The smaller the grid is, the more accurate the corresponding business data and resource data of each assessment object will be.
[0085] The disclosed embodiment can determine multiple assessment objects by superimposing multiple continuous square grids onto the target area, so that each assessment object has corresponding historical operating data and market environment data, thereby facilitating subsequent assessment based on the corresponding historical operating data and market environment data of each assessment object and improving the accuracy of the assessment results.
[0086] In one embodiment, before the historical operating data and market environment data corresponding to the multiple assessment objects are respectively input into the target model, steps S150 and S160 may be included. Figure 3 shown.
[0087] S150: Perform text filtering on the historical operating data and market environment data to obtain filtered data.
[0088] After obtaining the historical operating data and market environment data corresponding to the multiple assessment objects, text filtering is performed on the historical operating data and market environment data to select required data as filtering data.
[0089] In one embodiment, the required data includes data in a correct format, non-duplicate data, and complete data.
[0090] In one embodiment, the data can be filtered for text by a data cleaning tool. In one example, the OpenRefine data cleaning tool can be used for text filtering.
[0091] In one embodiment, Figure 4 As shown, text filtering is performed on historical operating data and market environment data to obtain filtered data, which may include step S151 and step S152.
[0092] S151: Filter out non-repetitive and complete data from historical operating data and market environment data to obtain filtered data.
[0093] In one example, the OpenRefine data cleaning tool is used to filter out duplicate, incorrectly formatted, and incomplete data from historical operating data and market environment data to obtain filtered data.
[0094] S152: Map the filtered data using a character mapping method, and match the mapping result with the keyword to obtain filtered data.
[0095] In one embodiment, after obtaining the filtered data, the filtered data may be mapped using a regular expression, and the mapped result may be matched with a keyword to extract the required information and obtain the filtered data.
[0096] In another embodiment, during the screening of historical business data and market environment data, text conversion may be performed such as removing blanks, translating Hypertext Markup Language (HTML) codes, etc., to improve the regularity of text data and the quality of clustering results.
[0097] The disclosed embodiment can improve data quality by screening historical business data and market environment data, filtering out incorrect data format, duplicate data and incomplete data. The data corresponding to the current assessment index is obtained by matching the keywords corresponding to the current assessment index with the screened data, thereby improving the accuracy and completeness of the data.
[0098] S160: Normalize the filtered data to obtain normalized historical operating data and market environment data.
[0099] After obtaining the filtered data, the filtered data is normalized to obtain normalized historical operating data and market environment data.
[0100] In one embodiment, normalizing the filtered data to obtain normalized historical operating data and market environment data may include steps S161-S164.
[0101] S161: Extract features from the filtered data to obtain target feature data.
[0102] S162: Convert the target feature data into corresponding semantic information.
[0103] S163: Processing the semantic information using a normalization model based on a recurrent neural network to obtain a processing result.
[0104] S164: Based on the processing results, normalized historical operating data and market environment data are obtained.
[0105] In one embodiment, feature extraction is performed on the filtered data to extract business-related features such as timestamps, holiday information, and marketing activities to obtain target feature data. A normalization model is constructed using recurrent neural network natural language processing technology. The target feature data is converted into semantic information that can be understood by the normalization model, and the semantic information is processed using the normalization model, wherein the processing process includes mapping the feature vector corresponding to the target feature data into a semantic space using word embedding technology, so that different target feature data are interpretable and comparable. After obtaining the processing results, thresholds or parameters are adaptively determined based on the processing results to obtain normalized historical operating data and market environment data.
[0106] The disclosed embodiment obtains normalized historical operating data and market environment data by normalizing the filtered data, so that the target model can process data from different target areas, thereby improving the generalization ability of the target model.
[0107] Inputting historical operating data and market environment data corresponding to a plurality of assessment objects into a target model, extracting features of the historical operating data and market environment data through the target model to obtain feature data may include step S121.
[0108] S121: Inputting normalized historical operating data and market environment data corresponding to a plurality of assessment objects into a target model, extracting features from the historical operating data and market environment data through the target model, and obtaining feature data.
[0109] After obtaining the normalized historical operating data and market environment data, the normalized historical operating data and market environment data corresponding to the multiple assessment objects are input into the target model. Based on the assessment indicators required for this assessment, the target model is used to extract the feature data corresponding to the assessment indicators required for this assessment from the normalized historical operating data and market environment data.
[0110] The disclosed embodiment can improve data quality by performing text filtering on historical business data and market environment data, and can reduce the probability of particularity in the filtered data by normalizing the filtered data, making the data representative.
[0111] In one embodiment, during the process of training the target model, a mean square error evaluation index may be used to measure the assessment accuracy of the target model.
[0112] In one embodiment, a target parameter is obtained by performing matrix operation on the feature data through a target model, and a plurality of indicator data are determined based on a target function corresponding to the target parameter, including steps S131-S134.
[0113] S131: Obtain assessment indicators from the assessment indicator library.
[0114] Obtain the assessment indicators corresponding to the indicator data determined this time from the preset assessment indicator library.
[0115] In one example, the evaluation index library includes: new user development volume, terminal sales volume, broadband acceptance volume, etc.
[0116] In one example, the assessment indicator library can be expanded based on actual business needs.
[0117] S132: Based on the characteristic data corresponding to the historical operating data and the market environment data, matrix operations are performed on the characteristic data by minimizing the sum of squared errors to obtain regression coefficients corresponding to the characteristic data.
[0118] In one embodiment, the target model extracts feature data based on the input historical operating data and market environment data, and the feature data includes dependent variable data and independent variable data. The dependent variable data and the independent variable data are subjected to matrix operations by minimizing the error sum of squares method to obtain the regression coefficient corresponding to the feature data, i.e., the target parameter.
[0119] In one example, the expression of the matrix operation of the feature data by minimizing the sum of squared errors is shown in Formula 2:
[0120] N= (x T x) -1 x T y (2)
[0121] Where N represents the regression coefficient, x represents the matrix vector of the independent variable x, and x T represents the transpose of the matrix vector of the independent variable x, (x T x) -1 represents the inverse of the multiplication of the matrix vector of the independent variable x and the transpose of the matrix vector of the independent variable x, and y represents the matrix vector of the dependent variable y.
[0122] S133: Based on the regression coefficient corresponding to the characteristic data, determine a plurality of objective functions corresponding to the assessment indicators, wherein each objective function corresponds to an assessment object.
[0123] The regression coefficients calculated based on the characteristic data are substituted into formula (1) to construct multiple objective functions related to the assessment indicators, namely, multivariate linear regression equations.
[0124] Among them, each objective function is generated based on the characteristic data extracted from the historical operating data and market environment data of the corresponding assessment object, so each assessment object corresponds to an objective function.
[0125] In one example, the objective function is shown in Figure 5 As shown, the horizontal axis represents the monthly sales volume, and the vertical axis represents the month. The corresponding sales volume in January is 6530, the corresponding sales volume in February is 4560, the corresponding sales volume in March is 2110, the corresponding sales volume in April is 3340, the corresponding sales volume in May is 4520, the corresponding sales volume in June is 5530, the corresponding sales volume in July is 5100, the corresponding sales volume in August is 5210, the corresponding sales volume in September is 5530, and the corresponding sales volume in October is 5460. Figure 5 The straight line in the middle is the objective function, which is determined based on the sales volume of the above 10 months.
[0126] S134: Based on multiple objective functions, determine indicator data corresponding to multiple assessment objects.
[0127] According to the obtained multiple objective functions, preset independent variables are input into each objective function respectively to determine the indicator data corresponding to the assessment object.
[0128] The disclosed embodiment can improve the accuracy of the assessment result by selecting assessment indicators, determining feature data and multiple objective functions corresponding to the assessment indicators, and finally determining indicator data corresponding to multiple assessment objects according to the multiple objective functions.
[0129] In one embodiment, after allocating the plurality of indicator data to the corresponding assessment objects, step S170 and step S180 are further included.
[0130] S170: Collect the latest business data of multiple assessment objects in real time.
[0131] In one embodiment, the latest operating data of multiple assessment objects are collected in real time through the CRM, BOSS, asset management, billing, and financial system interfaces of the assessment objects.
[0132] S180: Perform weighted calculation based on the latest operating data and indicator data to obtain assessment scores for multiple assessment objects.
[0133] In one embodiment, a linear or high-ratio scoring method may be used to perform weighted calculations on the operating conditions of the assessment objects to which the indicator data are assigned, to obtain assessment scores of multiple assessment objects, and the indicator data may be adjusted according to the assessment scores.
[0134] In one example, the expression of the linear score is shown in Formula 3:
[0135] E= ((U1-L1)*P1) / (K1-L1) (3)
[0136] Among them, E is the performance score, U1 is the actual operating data, L1 is the benchmark data, P1 is the preset weight, and K1 is the allocated indicator data.
[0137] In one example, the expression for the higher score is shown in Formula 4:
[0138] F=10*(V-MIN) / (MAX-MIN) (4)
[0139] Among them, F is the performance score, V is the assigned indicator data, MIN is the minimum completion amount of the indicator, and MAX is the maximum completion amount of the indicator.
[0140] The disclosed embodiment collects the latest operating data of multiple assessment objects, performs weighted operations based on the latest operating data and indicator data, and obtains assessment scores for multiple assessment objects, thereby facilitating subsequent adjustment of the indicator data based on the scoring situation and improving the accuracy of the assessment results.
[0141] like Figure 6 As shown, the embodiment of the present disclosure further provides a device 600 for determining indicator data, and the device 600 for determining indicator data includes:
[0142] A division module 601 is used to divide the target area using a region division grid to obtain multiple assessment objects;
[0143] An input module 602 is used to input the historical operating data and market environment data corresponding to the multiple assessment objects into the target model, and extract features from the historical operating data and market environment data through the target model to obtain feature data;
[0144] An operation module 603 is used to perform matrix operation on the feature data through a target model to obtain a target parameter, and determine a plurality of indicator data based on a target function corresponding to the target parameter;
[0145] The allocation module 604 is used to allocate multiple indicator data to corresponding assessment objects.
[0146] In some embodiments, the partitioning module 601 is specifically configured to:
[0147] Multiple continuous square grids are superimposed on the target area and divided into multiple assessment objects.
[0148] In some embodiments, the indicator data determination device includes a filtering module, the filtering module is used to perform text filtering on the historical operating data and the market environment data to obtain filtered data;
[0149] Normalize the filtered data to obtain normalized historical operating data and market environment data;
[0150] The historical operating data and market environment data corresponding to the multiple assessment objects are respectively input into the target model, and the feature data are extracted from the historical operating data and market environment data through the target model to obtain feature data, including:
[0151] The normalized historical operating data and market environment data corresponding to the multiple assessment objects are respectively input into the target model, and the features of the historical operating data and market environment data are extracted through the target model to obtain feature data.
[0152] In some embodiments, the indicator data determination device includes a screening module, the screening module is used to screen out non-repetitive and complete data from the historical business data and the market environment data to obtain screened data;
[0153] The filtered data is mapped using a character mapping method, and the mapping result is matched with the keyword to obtain the filtered data.
[0154] In some embodiments, the indicator data determination device includes an extraction module, the extraction module is used to extract features from the filtered data to obtain target feature data;
[0155] Convert target feature data into corresponding semantic information;
[0156] The semantic information is processed using a normalization model based on a recurrent neural network to obtain a processing result;
[0157] Based on the processing results, normalized historical operating data and market environment data are obtained.
[0158] In some embodiments, the indicator data determination device includes an acquisition module, and the acquisition module is used to obtain the assessment indicator from the assessment indicator library;
[0159] Based on the characteristic data corresponding to the historical operating data and the market environment data, matrix operations are performed on the characteristic data by minimizing the error sum of squares method to obtain the regression coefficients corresponding to the characteristic data;
[0160] Based on the regression coefficients corresponding to the characteristic data, a plurality of objective functions corresponding to the assessment indicators are determined, wherein each objective function corresponds to an assessment object;
[0161] Based on multiple objective functions, indicator data corresponding to multiple assessment objects are determined.
[0162] In some embodiments, the device for determining indicator data includes a collection module, which is used to collect the latest business data of multiple assessment objects in real time, and perform weighted operations based on the latest business data and indicator data to obtain assessment scores of the multiple assessment objects.
[0163] Figure 6Each module / unit in the device shown has the function of realizing Figures 1 to 3 The functions of each step executed by the application system in the present invention can achieve the corresponding technical effects. For the sake of brevity, they will not be repeated here.
[0164] Figure 7 A schematic diagram of the hardware structure for determining indicator data provided by an embodiment of the present disclosure is shown.
[0165] The indicator data determination device may include a processor 701 and a memory 702 storing computer program instructions.
[0166] Specifically, the processor 701 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.
[0167] The memory 702 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 702 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 702 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 702 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 702 is a non-volatile solid-state memory.
[0168] The memory 702 may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk storage medium device, an optical storage medium device, a flash memory device, an electrical, optical or other physical / tangible memory storage device. Therefore, generally, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to one aspect of the present disclosure.
[0169] The processor 701 implements any one of the methods for determining indicator data in the above embodiments by reading and executing computer program instructions stored in the memory 702 .
[0170] In one example, the indicator data determination device may further include a communication interface 703 and a bus 704. Figure 7 As shown, the processor 701, the memory 702, and the communication interface 703 are connected via a bus 704 and communicate with each other.
[0171] The communication interface 703 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.
[0172] Bus 704 includes hardware, software or both, and couples the components of online data traffic billing equipment to each other. For example, but not limitation, the bus may include Accelerated Graphics Port (AGP) or other graphics bus, Enhanced Industry Standard Architecture (EISA) bus, Front Side Bus (FSB), Hyper Transport (HT) interconnection, Industry Standard Architecture (ISA) bus, InfiniBand interconnection, Low Pin Count (LPC) bus, Memory bus, Micro Channel Architecture (MCA) bus, Peripheral Component Interconnect (PCI) bus, PCI-Express (PCI-X) bus, Serial Advanced Technology Attachment (SATA) bus, Video Electronics Standards Association Local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 704 may include one or more buses. Although the embodiment of the present invention describes and illustrates a specific bus, the present invention considers any suitable bus or interconnection. In addition, in conjunction with the determination method of the indicator data in the above embodiment, the present application embodiment also provides a computer storage medium to realize. The computer storage medium stores computer program instructions; when the computer program instructions are executed by the processor, any one of the methods for determining indicator data in the above embodiments is implemented.
[0173] An embodiment of the present application also provides a computer program product, including a computer program, which implements any one of the methods for determining indicator data in the above embodiments when the computer program is executed by a processor.
[0174] It should be clear that the present invention is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present invention.
[0175] The functional blocks shown in the above structural block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), appropriate firmware, plug-in, function card, etc. When implemented in software, the elements of the present invention are programs or code segments used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or communication link by a data signal carried in a carrier. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, read-only memory (Read-Only Memory, ROM), flash memory, erasable read-only memory (Erasable ReadOnly Memory, EROM), floppy disks, compact disc read-only memory (Compact Disc Read-Only Memory, CD-ROM), optical discs, hard disks, optical fiber media, radio frequency (Radio Frequency, RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.
[0176] It should also be noted that the exemplary embodiments mentioned in the present invention describe some methods or systems based on a series of steps or devices. However, the present invention is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiments, or in a different order from the embodiments, or several steps can be performed simultaneously.
[0177] Aspects of the present disclosure are described above with reference to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiment of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs a specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.
[0178] The above is only a specific implementation of the present invention. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the system, module and unit described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here. It should be understood that the protection scope of the present invention is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be covered within the protection scope of the present invention.
Claims
1. A method for determining indicator data, characterized in that: include: The target area is divided by using the area division grid to obtain multiple assessment objects; Inputting the historical operating data and market environment data corresponding to the multiple assessment objects into the target model, and extracting features from the historical operating data and market environment data through the target model to obtain feature data; Performing matrix operations on the characteristic data through a target model to obtain target parameters, and determining a plurality of indicator data based on a target function corresponding to the target parameters; The multiple indicator data are allocated to corresponding assessment objects.
2. The method according to claim 1, characterized in that The area division grid includes a square grid, and the target area is divided by using the area division grid to obtain multiple assessment objects, including: A plurality of continuous square grids are superimposed on the target area, and the target area is divided to obtain the plurality of assessment objects.
3. The method according to claim 1, characterized in that Before inputting the historical operating data and market environment data respectively corresponding to the plurality of assessment objects into the target model, the method further comprises: Performing text filtering on the historical operating data and market environment data to obtain filtered data; The filtered data is normalized to obtain normalized historical operating data and market environment data; the historical operating data and market environment data corresponding to the multiple assessment objects are input into the target model, and the historical operating data and market environment data are extracted through the target model to obtain feature data, including: The normalized historical operating data and market environment data corresponding to the multiple assessment objects are input into the target model, and the feature extraction of the historical operating data and market environment data is performed through the target model to obtain feature data.
4. The method according to claim 3, characterized in that The text filtering of the historical operating data and market environment data to obtain filtered data includes: Filter out non-repetitive and complete data from the historical operating data and market environment data to obtain filtered data; The filtered data is mapped using a character mapping method, and the mapping result is matched with a keyword to obtain the filtered data.
5. The method according to claim 3, characterized in that: The normalizing of the filtered data to obtain normalized historical operating data and market environment data includes: Performing feature extraction on the filtered data to obtain target feature data; Converting the target feature data into corresponding semantic information; Processing the semantic information using a normalization model based on a recurrent neural network to obtain a processing result; Based on the processing results, the normalized historical operating data and market environment data are obtained.
6. The method according to claim 1, characterized in that The target model is used to perform matrix operations on the feature data to obtain target parameters, and multiple indicator data are determined based on the target function corresponding to the target parameters, including: Obtain assessment indicators from the assessment indicator library; Based on the characteristic data corresponding to the historical operating data and the market environment data, performing matrix operations on the characteristic data by minimizing the error sum of squares method to obtain regression coefficients corresponding to the characteristic data; Based on the regression coefficient corresponding to the characteristic data, determining a plurality of objective functions corresponding to the assessment indicators, wherein each objective function corresponds to an assessment object; Based on the multiple objective functions, indicator data corresponding to the multiple assessment objects are determined.
7. The method according to claim 1, characterized in that After allocating the plurality of indicator data to corresponding assessment objects, the method further includes: Collecting the latest operating data of the multiple assessment objects in real time; A weighted calculation is performed based on the latest operating data and indicator data to obtain assessment scores for the multiple assessment objects.
8. A device for determining indicator data, characterized in that: The device comprises: A division module, the division module is used to divide the target area by using a regional division grid to obtain multiple assessment objects; An input module, the input module is used to input the historical business data and market environment data corresponding to the multiple assessment objects into the target model, and extract features from the historical business data and market environment data through the target model to obtain feature data; A calculation module, the calculation module is used to perform matrix operation on the feature data through a target model to obtain a target parameter, and determine a plurality of indicator data based on a target function corresponding to the target parameter; An allocation module is used to allocate the multiple indicator data to corresponding assessment objects.
9. A device for determining indicator data, characterized in that: The device includes: a processor, and a memory storing computer program instructions; the processor reads and executes the computer program instructions to implement the method for determining indicator data according to any one of claims 1-7.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the method for determining indicator data according to any one of claims 1 to 7 is implemented.
11. A computer program product, characterized in that It includes a computer program, which, when executed by a processor, implements the method for determining indicator data according to any one of claims 1 to 7.
