Index screening method and device based on dichotomy model, equipment and medium

Abstract

The invention relates to the technical field of big data and digital medical treatment. The invention discloses an index screening method and device based on a binary classification model, equipment and a medium, and the method comprises the steps: obtaining an index set and a scene set, the index set comprises a plurality of indexes, and the scene set comprises a plurality of scenes; searching a related data set of a target index in a target scene in a preset database according to the index and the scene; calculating an index threshold value of the target index in the target scene according to the related data set of the target index in the target scene based on a dichotomy model; and screening the indexes in the index set according to the index threshold of the target index in the target scene based on an index threshold reference value. The automatic configuration of the threshold value of each index in the evaluation process is realized, time and labor are saved, and the accuracy is also improved. And through screening, indexes with relatively low contribution to evaluation are screened out, so that the evaluation cost is reduced, and the evaluation efficiency is improved.

Description

Technical Field

[0001] The present application relates to the field of big data and digital medical technology, and specifically, to an indicator screening method, device, equipment and medium based on a binary classification model. Background Art

[0002] In order to ensure the achievement of project goals, an evaluation system needs to be developed to manage daily business when carrying out the project. The evaluation system needs to evaluate the promotion of business based on more than 1,000 indicators in different scenarios. The evaluation process involves the configuration of thresholds for each indicator. The current practice is to manually set them based on historical experience, which is time-consuming, labor-intensive and error-prone. In addition, the existing system involves a large number of indicators, and the contribution of each indicator to the evaluation is different. Calculating each indicator will increase the evaluation cost and reduce the evaluation efficiency. Especially in the era of rapid development of digital medicine, how to quickly and efficiently evaluate medical projects is a technical problem that needs to be solved urgently. Summary of the invention

[0003] In view of the above situation, the embodiments of the present application provide an indicator screening method, device, equipment and medium based on a binary classification model, which aims to solve the above problem or at least partially solve the above problem.

[0004] In a first aspect, the present application provides an indicator screening based on a binary classification model, including:

[0005] Acquire an indicator set and a scenario set, wherein the indicator set includes a plurality of indicators, and the scenario set includes a plurality of scenarios;

[0006] According to the indicator and the scenario, searching for a relevant data set of the target indicator in the target scenario in a preset database;

[0007] Based on the binary classification model, according to the relevant data set of the target indicator in the target scenario, the indicator threshold of the target indicator in the target scenario is calculated;

[0008] Based on the indicator threshold reference value, the indicators in the indicator set are screened according to the indicator threshold of the target indicator in the target scenario.

[0009] Preferably, based on the binary classification model, according to the relevant data set of the target indicator in the target scenario, the indicator threshold of the target indicator in the target scenario is calculated, including:

[0010] Based on a preset classification rule, the data of the target indicator in the relevant data set of the target scenario are divided into a first category and a second category;

[0011] Calculate the mean and probability of the data belonging to the first category, the mean and probability of the data belonging to the second category, and the standard deviation of the data of the target indicator in the relevant data set of the target scenario;

[0012] According to the mean and probability of the data belonging to the first category, the mean and probability of the data belonging to the second category, and the standard deviation of the data of the target indicator in the relevant data set of the target scenario, the indicator threshold of the target indicator in the target scenario is calculated.

[0013] Preferably, calculating the indicator threshold of the target indicator in the target scene according to the mean and probability of the data belonging to the first category, the mean and probability of the data belonging to the second category, and the standard deviation of the data of the target indicator in the relevant data set of the target scene includes:

[0014] Calculate an initial indicator threshold of the target indicator in the target scenario according to the mean and probability of the data belonging to the first category, the mean and probability of the data belonging to the second category, and the standard deviation of the data of the target indicator in the relevant data set of the target scenario;

[0015] According to the threshold conversion rule, the initial indicator threshold of the target indicator in the target scenario is converted into the indicator threshold of the target indicator in the target scenario, wherein the initial indicator threshold is within a first range and the indicator threshold is within a second range.

[0016] Preferably, based on the indicator threshold reference value, the indicators in the indicator set are screened according to the indicator threshold of the target indicator in the target scenario, including:

[0017] According to the indicator threshold of the target indicator in the target scenario, the indicator thresholds of all the indicators corresponding to the target scenario are obtained;

[0018] Based on the indicator threshold reference value, among the indicator thresholds of all the indicators corresponding to the target scenario, filter out the indicator threshold in the target scenario that is greater than the indicator threshold reference value;

[0019] The index to be filtered out from the index set is determined according to the filtered index threshold.

[0020] Preferably, based on the indicator threshold reference value, the indicators in the indicator set are screened according to the indicator threshold of the target indicator in the target scenario, including:

[0021] According to the indicator threshold of the target indicator in the target scenario, multiple indicator thresholds of the target indicator in all scenarios are obtained;

[0022] Determine the maximum value among the multiple indicator thresholds, that is, the optimal threshold of the target indicator;

[0023] According to the optimal threshold of the target indicator, the optimal threshold of all indicators is obtained;

[0024] Based on the indicator threshold reference value, the optimal thresholds of all indicators are screened, and according to the screening result, the indicators screened from the indicator set are determined.

[0025] Preferably, based on the indicator threshold reference value, the optimal thresholds of all indicators are screened, and according to the screening results, the indicators screened from the indicator set are determined, including:

[0026] Sorting the optimal thresholds of all indicators, and selecting the optimal thresholds that are greater than the indicator threshold reference values;

[0027] The index selected from the index set is determined according to the selected optimal threshold.

[0028] Preferably, the method further comprises:

[0029] Obtain project progress indicators;

[0030] According to the project progress indicator, the indicator threshold reference value is determined.

[0031] In a second aspect, an indicator screening device based on a binary classification model is provided, comprising:

[0032] An acquisition module, used to acquire an indicator set and a scenario set, wherein the indicator set includes a plurality of indicators and the scenario set includes a plurality of scenarios;

[0033] A search module, used to search for a relevant data set of a target indicator in a target scenario in a preset database according to the indicator and the scenario;

[0034] A calculation module, used to calculate the indicator threshold of the target indicator in the target scene based on a binary classification model and according to a relevant data set of the target indicator in the target scene;

[0035] The screening module is used to screen the indicators in the indicator set based on the indicator threshold reference value and the indicator threshold of the target indicator in the target scenario.

[0036] In a third aspect, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the indicator screening method based on the binary classification model as described in the first aspect are implemented.

[0037] In a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the indicator screening method based on the binary classification model as described in the first aspect are implemented.

[0038] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects:

[0039] This application is based on a binary classification model to calculate the indicator threshold of the target indicator in the target scenario, and to screen the indicators in the indicator set based on the indicator threshold reference value. This achieves the automatic configuration of the thresholds of each indicator in the evaluation process, saving time and effort and improving accuracy. In addition, by screening the indicators through the indicator threshold reference value, the indicators with less contribution to the evaluation are screened out, reducing the evaluation cost and improving the evaluation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0041] Figure 1 It is a schematic diagram of an application environment of an indicator screening method based on a binary classification model in one embodiment of the present invention;

[0042] Figure 2 It is a flow chart of an indicator screening method based on a binary classification model in one embodiment of the present invention;

[0043] Figure 3 yes Figure 2 A schematic flow chart of a specific implementation of step S30;

[0044] Figure 4 It is a structural schematic diagram of an indicator screening device based on a binary classification model in one embodiment of the present invention;

[0045] Figure 5 is a schematic diagram of a structure of a computer device in one embodiment of the present invention;

[0046] Figure 6 It is another structural schematic diagram of a computer device in one embodiment of the present invention. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0048] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that such use is interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the term "including" and its variants are to be interpreted as open-ended terms meaning "including but not limited to".

[0049] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0050] As mentioned above, the indicator thresholds in the current evaluation system need to be manually configured, which is time-consuming, labor-intensive and error-prone, and the large number of indicators affects the evaluation efficiency. In order to solve this technical problem, the embodiment of the present application provides an indicator screening method based on a binary classification model.

[0051] The index screening method based on the binary classification model provided in the embodiment of the present invention can be applied to Figure 1 In an application environment, the device communicates with the server through a network. The server can obtain an indicator set and a scenario set through the device, wherein the indicator set includes multiple indicators, and the scenario set includes multiple scenarios; according to the indicators and the scenarios, the relevant data set of the target indicator in the target scenario is searched in the preset database; based on the binary classification model, the indicator threshold of the target indicator in the target scenario is calculated according to the relevant data set of the target indicator in the target scenario; based on the indicator threshold reference value, the indicators in the indicator set are screened according to the indicator threshold of the target indicator in the target scenario. The present application is based on a binary classification model to calculate the indicator threshold of the target indicator in the target scenario, and based on the indicator threshold reference value, the indicators in the indicator set are screened. The automatic configuration of the threshold values ​​of each indicator in the evaluation process is realized, which saves time and effort and also improves accuracy. Moreover, the indicators are screened by the indicator threshold reference value, and the indicators with less contribution to the evaluation are screened out, which reduces the evaluation cost and improves the evaluation efficiency.

[0052] The device side may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, and portable wearable devices. The server side may be implemented by an independent server or a server cluster consisting of multiple servers. The present invention is described in detail below through specific embodiments.

[0053] See also Figure 2 As shown, Figure 2 A flowchart of an indicator screening method based on a binary classification model provided in an embodiment of the present invention includes the following steps:

[0054] S10: Acquire an indicator set and a scenario set, wherein the indicator set includes a plurality of indicators, and the scenario set includes a plurality of scenarios.

[0055] Specifically, indicators are used in the evaluation system to evaluate the status of projects during the project implementation process, so as to better manage daily operations. For example, with the development of digital medicine, indicators may include total outpatient visits, outpatient registrations, outpatient doctor workload, outpatient drug usage, etc. Scenarios are specific implementation situations during the project implementation process. In this embodiment, scenarios can be different institutions, for example, scenarios can be different hospitals. Indicators are used to evaluate the daily management of hospitals and the operating status of hospital projects.

[0056] Specifically, after obtaining the indicator set and the scenario set, a mapping relationship between the indicator and the scenario is established. For example, as shown in Table 1, there are m indicators and n organizations under the jurisdiction of the enterprise, forming an indicator system matrix X = (x ij ) m×n , where (i=1…m, j=1…n).

[0057] Table 1 Index system matrix

[0058]

[0059] S20: According to the indicator and the scenario, searching for a relevant data set of the target indicator in the target scenario in a preset database.

[0060] Specifically, the data sets related to the indicators and scenarios are pre-stored in the database, and after storage, the mapping relationship between the storage location and the indicators and scenarios is set. For example, the indicator threshold of indicator 1 in institution 1 is x 11 , in order to obtain x 11 , you need to first get x 11Related data sets, the target indicator at this time is indicator 1, and the target scenario is institution 1. If indicator 1 is the total number of outpatient visits, then the related data set of indicator 1 in institution 1 is the data set of the total number of outpatient visits in institution 1. Furthermore, if the preset database stores the daily data of the total number of outpatient visits in institution 1 within 3 months, then indicator 1 in the related data set of institution 1 includes 90 total number of outpatient visits data.

[0061] S30: Based on the binary classification model, according to the relevant data set of the target indicator in the target scenario, calculate the indicator threshold of the target indicator in the target scenario.

[0062] Specifically, the binary classification model is a common model in supervised learning, which is used to predict two categories of a discrete target variable (for example, yes / no, positive / negative, success / failure, etc.).

[0063] Furthermore, in this embodiment, the binary classification model is used to predict the category of the target variable as meeting the standard / not meeting the standard.

[0064] Specifically, Figure 3 As shown, step S30 calculates the indicator threshold of the target indicator in the target scene based on the binary classification model according to the relevant data set of the target indicator in the target scene, including:

[0065] S31: Based on the pre-set classification rules, the data of the target indicator in the relevant data set of the target scenario are divided into the first category and the second category; further, the first category is up to standard, and the second category is not up to standard. Further, based on the pre-set classification benchmark value, the data of the target indicator in the relevant data set of the target scenario are divided into the first category and the second category. For example, indicator 1 in the relevant data set of institution 1 includes 90 total outpatient visit data, and the classification benchmark value is the outpatient visit data that meets the standard. Each total outpatient visit data is judged as up to standard or not up to standard, and finally the total outpatient visit data that meets the standard is classified into the first category, and the total outpatient visit data that does not meet the standard is classified into the second category.

[0066] S32: Calculate the mean and probability of the data belonging to the first category, the mean and probability of the data belonging to the second category, and the standard deviation of the data of the target indicator in the relevant data set of the target scenario. For example, calculate the mean and probability of the total number of outpatient visits that meet the standard, the mean and probability of the total number of outpatient visits that do not meet the standard, and the standard deviation of the total number of outpatient visits of 90 outpatient visits. The standard deviation is calculated according to the following formula:

[0067]

[0068] Where σ is the standard deviation of the continuous variable y; y is the mean of y; and n is the number of data.

[0069] S33: Calculate the indicator threshold of the target indicator in the target scene according to the mean and probability of the data belonging to the first category, the mean and probability of the data belonging to the second category, and the standard deviation of the data of the target indicator in the relevant data set of the target scene. Specifically, the indicator threshold of the target indicator in the target scene is calculated by the following formula:

[0070]

[0071] in:

[0072] y x ' ＝1 is the mean value of y when x=1, y x ' ＝0 is the mean value of y when x=0;

[0073] p x＝1 is the probability that x=1, p x＝0 is the probability of x=0;

[0074] σ is the standard deviation of the continuous variable y, that is

[0075] When x=1, it is the first category; when x=0, it is the second category.

[0076] For example, if 45 of the 90 outpatient visits meet the standard and 45 do not, then y x＝1 is the mean of the 45 data that meet the standard; y x ' ＝0 is the mean of the 45 data that do not meet the standard; p x＝1 is the probability of reaching the target, i.e. 0.5; p x＝0 is the probability of not meeting the standard, which is 0.5.

[0077] Specifically, step S33 calculates the indicator threshold of the target indicator in the target scene according to the mean and probability of the data belonging to the first category, the mean and probability of the data belonging to the second category, and the standard deviation of the data of the target indicator in the relevant data set of the target scene, including:

[0078] S331: Calculate an initial indicator threshold of the target indicator in the target scenario according to the mean and probability of the data belonging to the first category, the mean and probability of the data belonging to the second category, and the standard deviation of the data of the target indicator in the relevant data set of the target scenario;

[0079] S332: According to a threshold conversion rule, convert the initial indicator threshold of the target indicator in the target scenario into an indicator threshold of the target indicator in the target scenario, wherein the initial indicator threshold is within a first range and the indicator threshold is within a second range.

[0080] Specifically, the initial indicator threshold of the target indicator in the target scene is obtained according to formula (1) and formula (2). The initial indicator threshold is in the first range (-1, 1), and it needs to be converted to the second range (1, 10). The converted value is the indicator threshold of the target indicator in the target scene. Specifically, the threshold conversion rule is a preset linear transformation formula.

[0081] Converting the initial indicator threshold value within the first range into the indicator threshold value within the second range is beneficial to evaluating the contribution of the indicator.

[0082] S40: Based on the indicator threshold reference value, the indicators in the indicator set are screened according to the indicator threshold of the target indicator in the target scenario.

[0083] In one embodiment, for a scenario, all indicators applied in the scenario can be evaluated and screened. Specifically, step S40 screens the indicators in the indicator set based on the indicator threshold reference value and the indicator threshold of the target indicator in the target scenario, including:

[0084] S41: According to the indicator threshold of the target indicator in the target scenario, the indicator thresholds of all the indicators corresponding to the target scenario are obtained. Specifically, as shown in Table 1, when the target scenario is institution 1 and the target indicator is any one of indicators 1 to m, the indicator threshold of the corresponding target indicator in the target scenario is calculated. The indicator thresholds corresponding to the m indicators are calculated in sequence to obtain the indicator thresholds of the m indicators corresponding to institution 1, and are filled into the row corresponding to institution 1.

[0085] S42: Based on the indicator threshold reference value, among the indicator thresholds of all the indicators corresponding to the target scenario, filter out the indicator thresholds in the target scenario that are greater than the indicator threshold reference value. Specifically, the indicator threshold reference value is a preset value and can be set according to demand. For example, when the indicator threshold reference value is 2, the indicator thresholds greater than 2 among the indicator thresholds of the m indicators corresponding to institution 1 are filtered out. Further, in combination with Table 1, if the indicator thresholds of all indicators corresponding to institution 1 are x 11 to x 1m , then at x 11 to x 1m Filter out indicator thresholds greater than 2.

[0086] S43: Determine the index to be screened out from the index set according to the screened index threshold.

[0087] Specifically, at this time, there is a one-to-one mapping relationship between the indicator threshold and the indicator, and the corresponding indicator can be determined according to the screened indicator threshold.

[0088] In one embodiment, all indicators in the application scenarios can be evaluated and screened for multiple scenarios, so that the indicators can cover all scenarios. Specifically, step S40 screens the indicators in the indicator set based on the indicator threshold reference value and the indicator threshold of the target indicator in the target scenario, including:

[0089] S41′: According to the indicator threshold of the target indicator in the target scenario, a plurality of indicator thresholds of the target indicator in all scenarios are obtained.

[0090] Specifically, as shown in Table 1, when the target scenario is any one of institution 1 to institution n and the target indicator is any one of indicator 1 to indicator m, the indicator threshold of the corresponding target indicator in the corresponding target scenario is calculated. The indicator thresholds corresponding to the m indicators in n scenarios are calculated in sequence and filled into the rows corresponding to institution 1 to institution n.

[0091] S42′: Determine the maximum value among the multiple indicator thresholds, that is, the optimal threshold of the target indicator; specifically, the target indicator is any one of indicators 1 to m, and the corresponding scenario is the maximum value of the indicator when the institution 1 to institution n. For example, if the target indicator is indicator 1, then the optimal threshold of the target indicator is x 11 to x n1 The maximum value in .

[0092] S43′: According to the optimal threshold of the target indicator, the optimal threshold of all indicators is obtained; for example, the optimal threshold of all indicators is the optimal threshold of indicator 1,..., the optimal threshold of indicator i,..., the optimal threshold of indicator m, and a total of m optimal thresholds are obtained.

[0093] S44′: Based on the indicator threshold reference value, the optimal thresholds of all indicators are screened, and according to the screening result, the indicators screened from the indicator set are determined.

[0094] Specific examples include:

[0095] S441: sorting the optimal thresholds of all indicators, and selecting the optimal thresholds that are greater than the indicator threshold reference values;

[0096] S442: Determine the index to be screened out from the index set according to the screened out optimal threshold.

[0097] Specifically, for example, an optimal threshold value greater than the index threshold reference value is selected from m optimal threshold values. Since there is a one-to-one mapping relationship between the optimal threshold value and the index, the corresponding index can be obtained according to the selected optimal threshold value.

[0098] Specifically, the method further includes:

[0099] Obtain project progress indicators;

[0100] According to the project progress indicator, the indicator threshold reference value is determined.

[0101] Specifically, the project progress indicator is a dimensionless number that shows the progress of the project, which can be set in advance, and the mapping relationship between the project progress indicator and the indicator threshold reference value can be set. For example, the indicator threshold reference value can be set to 2 at the beginning of the project, the indicator threshold reference value can be set to 4 in the middle of the project, and the indicator threshold reference value can be set to 6 in the stable optimization period of the project.

[0102] It can be seen that in the above scheme, this application is based on a binary classification model to calculate the indicator threshold of the target indicator in the target scenario, and based on the indicator threshold reference value, the indicator in the indicator set is screened. The threshold automatic configuration of each indicator in the evaluation process is realized, which saves time and effort and improves accuracy. In addition, the indicators are screened by the indicator threshold reference value, and the indicators with less contribution to the evaluation are screened out, which reduces the evaluation cost and improves the evaluation efficiency. It greatly reduces the participation of manual experience judgment and redundant indicators in the contribution evaluation, which can reduce 30% of useless indicators, reduce the effect of manual evaluation indicators, and greatly increase the data processing efficiency.

[0103] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0104] In one embodiment, a device for selecting an indicator based on a binary classification model is provided, and the device for selecting an indicator based on a binary classification model corresponds one-to-one to the method for selecting an indicator based on a binary classification model in the above embodiment. Figure 4 As shown, the index screening device based on the binary classification model includes an acquisition module 101, a search module 102, a calculation module 103, and a screening module 104. The detailed description of each functional module is as follows:

[0105] An acquisition module 101 is used to acquire an indicator set and a scenario set, wherein the indicator set includes a plurality of indicators and the scenario set includes a plurality of scenarios;

[0106] A search module 102 is used to search for a relevant data set of a target indicator in a target scenario in a preset database according to the indicator and the scenario;

[0107] A calculation module 103 is used to calculate an indicator threshold of the target indicator in the target scenario based on a binary classification model and according to a relevant data set of the target indicator in the target scenario;

[0108] The screening module 104 is used to screen the indicators in the indicator set based on the indicator threshold reference value and the indicator threshold of the target indicator in the target scenario.

[0109] The computing module 103 is further configured to:

[0110] Based on a preset classification rule, the data of the target indicator in the relevant data set of the target scenario are divided into a first category and a second category;

[0111] Calculate the mean and probability of the data belonging to the first category, the mean and probability of the data belonging to the second category, and the standard deviation of the data of the target indicator in the relevant data set of the target scenario;

[0112] According to the mean and probability of the data belonging to the first category, the mean and probability of the data belonging to the second category, and the standard deviation of the data of the target indicator in the relevant data set of the target scenario, the indicator threshold of the target indicator in the target scenario is calculated.

[0113] The computing module 103 is further configured to:

[0114] Calculate an initial indicator threshold of the target indicator in the target scenario according to the mean and probability of the data belonging to the first category, the mean and probability of the data belonging to the second category, and the standard deviation of the data of the target indicator in the relevant data set of the target scenario;

[0115] According to the threshold conversion rule, the initial indicator threshold of the target indicator in the target scenario is converted into the indicator threshold of the target indicator in the target scenario, wherein the initial indicator threshold is within a first range and the indicator threshold is within a second range.

[0116] The screening module 104 is further used to:

[0117] According to the indicator threshold of the target indicator in the target scenario, the indicator thresholds of all the indicators corresponding to the target scenario are obtained;

[0118] Based on the indicator threshold reference value, among the indicator thresholds of all the indicators corresponding to the target scenario, filter out the indicator threshold in the target scenario that is greater than the indicator threshold reference value;

[0119] The index to be filtered out from the index set is determined according to the filtered index threshold.

[0120] The screening module 104 is further used to:

[0121] According to the indicator threshold of the target indicator in the target scenario, multiple indicator thresholds of the target indicator in all scenarios are obtained;

[0122] Determine the maximum value among the multiple indicator thresholds, that is, the optimal threshold of the target indicator;

[0123] According to the optimal threshold of the target indicator, the optimal threshold of all indicators is obtained;

[0124] Based on the indicator threshold reference value, the optimal thresholds of all indicators are screened, and according to the screening result, the indicators screened from the indicator set are determined.

[0125] The screening module 104 is further used to:

[0126] Sorting the optimal thresholds of all indicators, and selecting the optimal thresholds that are greater than the indicator threshold reference values;

[0127] The index selected from the index set is determined according to the selected optimal threshold.

[0128] The screening module 104 is further used to:

[0129] Obtain project progress indicators;

[0130] According to the project progress indicator, the indicator threshold reference value is determined.

[0131] The present invention provides an indicator screening device based on a binary classification model. The present application is based on a binary classification model to calculate the indicator threshold of the target indicator in the target scene, and screens the indicators in the indicator set based on the indicator threshold reference value. The threshold automatic configuration of each indicator in the evaluation process is realized, which saves time and effort and improves accuracy. In addition, the indicators are screened by the indicator threshold reference value, and the indicators with less contribution to the evaluation are screened out, which reduces the evaluation cost and improves the evaluation efficiency.

[0132] For the specific definition of the index screening device based on the binary classification model, please refer to the definition of the index screening method based on the binary classification model above, which will not be repeated here. Each module in the above-mentioned index screening device based on the binary classification model can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0133] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 5As shown. The computer device includes a processor, a memory, a network interface and a database connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile and / or volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external device end through a network connection. When the computer program is executed by the processor, it realizes the functions or steps of the service side of an indicator screening method based on a binary classification model.

[0134] In one embodiment, a computer device is provided. The computer device may be a device end, and its internal structure diagram may be as follows: Figure 6 As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external server via a network connection. When the computer program is executed by the processor, the functions or steps of the device side of an indicator screening method based on a binary classification model are implemented.

[0135] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program:

[0136] Acquire an indicator set and a scenario set, wherein the indicator set includes a plurality of indicators, and the scenario set includes a plurality of scenarios;

[0137] According to the indicator and the scenario, searching for a relevant data set of the target indicator in the target scenario in a preset database;

[0138] Based on the binary classification model, according to the relevant data set of the target indicator in the target scenario, the indicator threshold of the target indicator in the target scenario is calculated;

[0139] Based on the indicator threshold reference value, the indicators in the indicator set are screened according to the indicator threshold of the target indicator in the target scenario.

[0140] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0141] Acquire an indicator set and a scenario set, wherein the indicator set includes a plurality of indicators, and the scenario set includes a plurality of scenarios;

[0142] According to the indicator and the scenario, searching for a relevant data set of the target indicator in the target scenario in a preset database;

[0143] Based on the binary classification model, according to the relevant data set of the target indicator in the target scenario, the indicator threshold of the target indicator in the target scenario is calculated;

[0144] Based on the indicator threshold reference value, the indicators in the indicator set are screened according to the indicator threshold of the target indicator in the target scenario.

[0145] It should be noted that the above functions or steps that can be implemented by the computer-readable storage medium or computer device can refer to the relevant descriptions on the server side and the device side in the aforementioned method embodiment. To avoid repetition, they will not be described one by one here.

[0146] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0147] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0148] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. An indicator screening method based on a binary classification model, characterized in that: include: Acquire an indicator set and a scenario set, wherein the indicator set includes a plurality of indicators, and the scenario set includes a plurality of scenarios; According to the indicator and the scenario, searching for a relevant data set of the target indicator in the target scenario in a preset database; Based on the binary classification model, according to the relevant data set of the target indicator in the target scenario, the indicator threshold of the target indicator in the target scenario is calculated; Based on the indicator threshold reference value, the indicators in the indicator set are screened according to the indicator threshold of the target indicator in the target scenario.

2. The method according to claim 1, characterized in that Based on the binary classification model, according to the relevant data set of the target indicator in the target scenario, the indicator threshold of the target indicator in the target scenario is calculated, including: Based on a preset classification rule, the data of the target indicator in the relevant data set of the target scenario are divided into a first category and a second category; Calculate the mean and probability of the data belonging to the first category, the mean and probability of the data belonging to the second category, and the standard deviation of the data of the target indicator in the relevant data set of the target scenario; According to the mean and probability of the data belonging to the first category, the mean and probability of the data belonging to the second category, and the standard deviation of the data of the target indicator in the relevant data set of the target scenario, the indicator threshold of the target indicator in the target scenario is calculated.

3. The method according to claim 2, characterized in that Calculating an indicator threshold of the target indicator in the target scenario according to the mean and probability of the data belonging to the first category, the mean and probability of the data belonging to the second category, and the standard deviation of the data of the target indicator in the relevant data set of the target scenario, including: Calculate an initial indicator threshold of the target indicator in the target scenario according to the mean and probability of the data belonging to the first category, the mean and probability of the data belonging to the second category, and the standard deviation of the data of the target indicator in the relevant data set of the target scenario; According to the threshold conversion rule, the initial indicator threshold of the target indicator in the target scenario is converted into the indicator threshold of the target indicator in the target scenario, wherein the initial indicator threshold is within a first range and the indicator threshold is within a second range.

4. The method according to claim 1, characterized in that: Based on the indicator threshold reference value, and according to the indicator threshold of the target indicator in the target scenario, the indicators in the indicator set are screened, including: According to the indicator threshold of the target indicator in the target scenario, the indicator thresholds of all the indicators corresponding to the target scenario are obtained; Based on the indicator threshold reference value, among the indicator thresholds of all the indicators corresponding to the target scenario, filter out the indicator threshold in the target scenario that is greater than the indicator threshold reference value; The index to be filtered out from the index set is determined according to the filtered index threshold.

5. The method according to claim 1, characterized in that Based on the indicator threshold reference value, and according to the indicator threshold of the target indicator in the target scenario, the indicators in the indicator set are screened, including: According to the indicator threshold of the target indicator in the target scenario, multiple indicator thresholds of the target indicator in all scenarios are obtained; Determine the maximum value among the multiple indicator thresholds, that is, the optimal threshold of the target indicator; According to the optimal threshold of the target indicator, the optimal threshold of all indicators is obtained; Based on the indicator threshold reference value, the optimal thresholds of all indicators are screened, and according to the screening result, the indicators screened from the indicator set are determined.

6. The method according to claim 5, characterized in that Based on the indicator threshold reference value, the optimal thresholds of all indicators are screened, and according to the screening result, the indicators screened from the indicator set are determined, including: Sorting the optimal thresholds of all indicators, and selecting the optimal thresholds that are greater than the indicator threshold reference values; The index selected from the index set is determined according to the selected optimal threshold.

7. The method according to claim 1, characterized in that The method further comprises: Obtain project progress indicators; According to the project progress indicator, the indicator threshold reference value is determined.

8. An indicator screening device based on a binary classification model, characterized in that: include: An acquisition module, used to acquire an indicator set and a scenario set, wherein the indicator set includes a plurality of indicators and the scenario set includes a plurality of scenarios; A search module, used to search for a relevant data set of a target indicator in a target scenario in a preset database according to the indicator and the scenario; A calculation module, used to calculate the indicator threshold of the target indicator in the target scene based on a binary classification model and according to a relevant data set of the target indicator in the target scene; The screening module is used to screen the indicators in the indicator set based on the indicator threshold reference value and the indicator threshold of the target indicator in the target scenario.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the indicator screening method based on the binary classification model as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the indicator screening method based on a binary classification model as described in any one of claims 1 to 7 are implemented.

Images