Method for establishing a business model, method for processing a business

Abstract

This application discloses a method for establishing a business model and a business processing method, belonging to the field of machine learning technology. The establishment method includes: determining formulas in natural language form in response to formula setting operations, each formula including a basic indicator, a calculator, and indicator options; using the calculation code of the calculator of each formula, connecting the indicator code of the basic indicator and the option code of the indicator option to obtain the formula code; determining conditions in natural language form in response to condition setting operations, each condition including at least two formulas and a logical operator; using the logical code of the logical operator of each condition, connecting the formula codes of the formulas in the condition to obtain the condition code; and determining business rules in natural language form in response to business setting operations, the business rules including the judgment results and judgment order of each condition; establishing the correspondence between the condition code and the judgment result of each condition; setting the judgment order of each condition code according to the judgment order to obtain the business model.

Description

Technical Field

[0001] This application relates to the field of machine learning technology, and in particular to methods for establishing business models and business processing methods. Background Technology

[0002] Currently, business model development in some fields, such as finance, is done entirely through code. Similarly, any adjustments to the business model require code modifications. However, developing business models purely through code involves a large amount of code, a long development cycle, high costs, and is also more prone to introducing defects and bugs.

[0003] Therefore, how to simplify the development model of business models is a technical problem that urgently needs to be solved. Summary of the Invention

[0004] This application provides a method for establishing a business model and a business processing method to simplify the development mode of the business model.

[0005] Firstly, embodiments of this application provide a method for establishing a business model, comprising:

[0006] In response to the formula setting operation, determine at least two formulas in natural language form, each formula including basic indicators, operators, and indicator options;

[0007] By using the calculation code of the operator of each formula, the indicator code of the basic indicator of the formula and the option code of the indicator option are connected to obtain the formula code of the formula.

[0008] In response to a condition setting operation, determine at least two conditions in natural language form, each condition including at least two formulas and one logical operator;

[0009] By using the logical code of the logical operator of each condition, the formula code of the formula in the condition is connected to obtain the condition code of the condition;

[0010] In response to a business settings operation, business rules in natural language form are determined, the business rules including the judgment results and judgment order of each condition;

[0011] Establish the correspondence between the condition code and the judgment result for each condition, and set the judgment order of each condition code according to the judgment order to obtain the business model.

[0012] In some embodiments, the formula for each natural language form is determined according to the following steps:

[0013] In response to the basic indicator setting operation, determine the basic indicators included in the formula;

[0014] If the basic indicator is a non-optional indicator, then the indicator value input control will be displayed;

[0015] In response to the trigger operation of the indicator value input control, the currently input indicator value is determined as the indicator option included in the formula;

[0016] If the basic indicator is an optional indicator, then display the indicator option set of the basic indicator;

[0017] In response to the selection operation of the indicator option set, the selected indicator option is determined as the indicator option included in the formula;

[0018] In response to the operator setting operation, the operators included in the formula are determined.

[0019] In some embodiments, after obtaining the business model, the method further includes:

[0020] The business model is used to process the business data to obtain the business output results.

[0021] In some embodiments, after obtaining the business model, the method further includes:

[0022] Obtain the business output results and actual business results of the business model for multiple business data;

[0023] Based on the business output results and the actual business results, the accuracy of the business model is determined;

[0024] If the accuracy rate is lower than the preset value, the business model is optimized by using machine learning, with multiple business data as input and the actual business results of the multiple business data as output.

[0025] Secondly, embodiments of this application provide a business processing method, including:

[0026] Obtain the correspondence between each condition code and the judgment result in the business model, as well as the judgment order of each condition code;

[0027] Based on the judgment order, select the target condition code that has not been judged and has the earliest judgment order;

[0028] The logic code in the target condition code is segmented to obtain at least two formula codes contained in the target condition code;

[0029] Using the corresponding indicator options in the current business data, replace the indicator code in each formula code, and then calculate the replaced formula code;

[0030] Based on the logical code in the target condition code, perform logical operations on the calculation results of the at least two formula codes to obtain the condition result;

[0031] If the condition result is not true, then the step of selecting the target condition code that has not been judged and has the earliest judgment order is executed based on the judgment order;

[0032] If the condition result is true, then the judgment result corresponding to the target condition code is determined as the business output result of the business model on the business data.

[0033] Thirdly, embodiments of this application provide a business processing method, including:

[0034] Obtain at least two business models, wherein each business model is established using any of the methods described above;

[0035] Based on the business logic relationships between the various business models, business data is input into at least two of the business models to obtain business processing results.

[0036] Fourthly, embodiments of this application provide a business model establishment apparatus, comprising:

[0037] The formula setting module is used to determine at least two formulas in natural language form in response to the formula setting operation. Each formula includes a basic indicator, a calculator, and indicator options.

[0038] The formula generation module is used to connect the indicator code of the basic indicator and the option code of the indicator option of the formula by using the calculation code of the operator of each formula to obtain the formula code of the formula.

[0039] The condition setting module is used to determine at least two conditions in natural language form in response to a condition setting operation, each condition including at least two formulas and one logical operator;

[0040] The condition generation module is used to connect the formula codes of the formulas in the conditions using the logical codes of the logical operators of each condition, so as to obtain the condition code of the conditions.

[0041] The rule setting module is used to determine business rules in natural language form in response to business setting operations. The business rules include the judgment results and judgment order of each condition.

[0042] The model generation module is used to establish the correspondence between the condition code and the judgment result of each condition, and to set the judgment order of each condition code according to the judgment order to obtain the business model.

[0043] In some embodiments, the formula setting module is specifically used to determine the formula for each natural language form according to the following steps:

[0044] In response to the basic indicator setting operation, determine the basic indicators included in the formula;

[0045] If the basic indicator is a non-optional indicator, then the indicator value input control will be displayed;

[0046] In response to the trigger operation of the indicator value input control, the currently input indicator value is determined as the indicator option included in the formula;

[0047] If the basic indicator is an optional indicator, then display the indicator option set of the basic indicator;

[0048] In response to the selection operation of the indicator option set, the selected indicator option is determined as the indicator option included in the formula;

[0049] In response to the operator setting operation, the operators included in the formula are determined.

[0050] In some embodiments, it also includes:

[0051] The business processing module is used to process business data using the business model after obtaining the business model, and obtain business output results.

[0052] In some embodiments, a model update module is also included, for:

[0053] After obtaining the business model, acquire the business output results and actual business results of the business model for multiple business data.

[0054] Based on the business output results and the actual business results, the accuracy of the business model is determined;

[0055] If the accuracy rate is lower than the preset value, the business model is optimized by using machine learning, with multiple business data as input and the actual business results of the multiple business data as output.

[0056] Fifthly, embodiments of this application provide a business processing apparatus, including:

[0057] The acquisition module is used to obtain the correspondence between each condition code and the judgment result in the business model, as well as the judgment order of each condition code;

[0058] The selection module is used to select the target condition code that has not been judged and has the earliest judgment order, based on the judgment order.

[0059] The segmentation module is used to segment the logic code in the target condition code to obtain at least two formula codes contained in the target condition code;

[0060] The formula calculation module is used to replace the indicator code in each formula code with the corresponding indicator option in the current business data, and then calculate the replacement formula code.

[0061] The condition judgment module is used to perform logical operations on the calculation results of the at least two formula codes based on the logical code in the target condition code to obtain the condition result;

[0062] The business processing module is used to perform the step of selecting the target condition code that has not been judged and has the earliest judgment order based on the judgment order if the condition result is not true; if the condition result is true, the judgment result corresponding to the target condition code is determined as the business output result of the business model on the business data.

[0063] Sixthly, embodiments of this application provide a business processing apparatus, including:

[0064] The acquisition module is used to acquire at least two business models, wherein each business model is established using any of the methods described above;

[0065] The processing module is used to input business data into the at least two business models according to the business logic relationship between the various business models, and obtain the business processing results.

[0066] In a seventh aspect, embodiments of this application provide an electronic device, comprising: at least one processor, and a memory communicatively connected to the at least one processor, wherein:

[0067] The memory stores instructions that can be executed by at least one processor to enable the at least one processor to perform any of the above-described business model establishment methods or any of the business processing methods.

[0068] Eighthly, embodiments of this application provide a storage medium in which, when the instructions in the storage medium are executed by the processor of an electronic device, the electronic device is able to execute any of the above-described methods for establishing a business model or any of the above-described business processing methods.

[0069] Ninthly, embodiments of this application provide a computer program product that, when invoked and executed by an electronic device, causes the electronic device to execute any of the above-described business model establishment methods or any of the business processing methods.

[0070] In this embodiment, in response to a formula setting operation, at least two formulas in natural language form are determined. Each formula includes a basic indicator, a calculator, and indicator options. The calculation code of the calculator in each formula is used to connect the indicator code of the basic indicator and the option code of the indicator option to obtain the formula code of the formula. In response to a condition setting operation, at least two conditions in natural language form are determined. Each condition includes at least two formulas and a logical operator. The logical code of the logical operator in each condition is used to connect the formula codes of the formulas in the condition to obtain the condition code of the condition. In response to a business setting operation, business rules in natural language form are determined. The business rules include the judgment results and judgment order of each condition. A correspondence between the condition code and the judgment result of each condition is established, and the judgment order of each condition code is set according to the judgment order to obtain the business model. Thus, by configuring basic elements such as basic indicators, calculators, indicator options, formulas, and conditions to establish a business model, a flexible and configurable low-code business development model is provided. Attached Figure Description

[0071] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments of this application and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0072] Figure 1 A flowchart illustrating a method for establishing a business model as provided in an embodiment of this application;

[0073] Figure 2 A flowchart of a business processing method provided in an embodiment of this application;

[0074] Figure 3 A flowchart illustrating yet another business processing method provided in this application embodiment;

[0075] Figure 4 This is a schematic diagram of the structure of an impairment model provided in an embodiment of this application;

[0076] Figure 5 A schematic diagram of a business model creation apparatus provided in an embodiment of this application;

[0077] Figure 6 This is a schematic diagram of the structure of a service processing device provided in an embodiment of this application;

[0078] Figure 7 A schematic diagram of the structure of another service processing device provided in the embodiments of this application;

[0079] Figure 8 This is a schematic diagram of the hardware structure of an electronic device for implementing a business model establishment method or any business processing method, provided in an embodiment of this application. Detailed Implementation

[0080] To simplify the development of business models, embodiments of this application provide methods for establishing business models and methods for processing business data.

[0081] The preferred embodiments of this application are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit this application. Unless otherwise specified, the embodiments and features described herein can be combined with each other. Furthermore, the acquisition, storage, use, and processing of data in the embodiments of this application comply with the relevant provisions of national laws and regulations.

[0082] Figure 1 A flowchart of a method for establishing a business model provided in this application embodiment includes the following steps.

[0083] In step 101, in response to the formula setting operation, at least two formulas in natural language form are determined, each formula including a basic indicator, a calculator, and indicator options.

[0084] One type of formula is one written in natural language, such as an external debt rating greater than AA. This allows developers to write formulas in natural language, making formula development easier.

[0085] Furthermore, a formula includes a basic indicator, a calculator, and indicator options. Taking the external debt rating as greater than AA as an example, the basic indicator refers to the external debt rating, the calculator means greater than, and the indicator options mean AA.

[0086] In some embodiments, the formula for each natural language form may be determined according to the following steps:

[0087] In response to the basic indicator setting operation, determine the basic indicators included in the formula;

[0088] If the basic indicator is a non-optional indicator, then display the indicator value input control;

[0089] In response to a trigger operation on the indicator value input control, the currently entered indicator value is determined as an indicator option included in the formula;

[0090] If the base indicator is an option indicator, then display the set of indicator options for the base indicator;

[0091] In response to the selection operation on the indicator option set, the selected indicator option is determined as the indicator option included in the formula;

[0092] In response to the operator setting operation, determine the operators included in the formula.

[0093] In this way, by configuring each formula individually through page settings, the basic indicators, operators, and indicator options included in each formula can be set one by one, which helps to further reduce the difficulty of formula development.

[0094] In step 102, the calculation code of the operator of each formula is used to connect the indicator code of the basic indicator of the formula and the option code of the indicator option to obtain the formula code of the formula.

[0095] The calculation codes for the operators of each formula, the indicator codes for the basic indicators, and the option codes for the indicator options are all pre-configured.

[0096] Taking the formula described in natural language as "external debt rating greater than AA" as an example, the formula code is: outRating>11. Here, outRating is the indicator code of the basic indicator "external debt rating", > is the calculation code of the operator "greater than", and 11 is the option code of the indicator "AA".

[0097] In this way, when developers develop formulas, they only need to select the basic indicators, operators, and indicator options included in the formula, without having to worry about the underlying code of the basic indicators, operators, and indicator options, to obtain the formula code. The formula development is simple and less prone to introducing bugs.

[0098] In step 103, in response to the condition setting operation, at least two conditions in natural language form are determined, each condition including at least two formulas and one logical character.

[0099] Among them, a condition in natural language form refers to a condition described in natural language, such as an external debt rating greater than AA and an asset classification of normal. The external debt rating greater than AA is one formula, and the asset classification of normal is another formula, and both are logical operators.

[0100] In this way, developers can write conditions in natural language, making condition development easier.

[0101] In step 104, the logical code of the logical symbol of each condition is used to connect the formula code of the formula in that condition to obtain the condition code.

[0102] To simplify the recording format of a condition code, the condition code can be expressed using the formula IDs of the formulas in the condition. Assuming the condition in natural language is: external debt rating is greater than AA and asset classification is normal, the condition code can be represented as: 11and 22, where 11 represents the formula ID of the formula for external debt rating greater than AA, 22 represents the formula ID of the formula for asset classification is normal, and and means "and".

[0103] In step 105, in response to the business setting operation, business rules in natural language form are determined. The business rules include the judgment results and judgment order of each condition.

[0104] Among them, business rules in natural language form refer to business rules described in natural language. This way, developers can write business rules in natural language, making the development of business rules less difficult.

[0105] In step 106, the correspondence between the condition code and the judgment result of each condition is established, and the judgment order of each condition code is set according to the judgment order to obtain the business model.

[0106] That is, the business model describes the correspondence between the condition code and the judgment result for each condition, as well as the judgment order of each condition code.

[0107] In step 107, the business data is processed using the business model to obtain the business output results.

[0108] In step 108, the business model's business output results and actual business results for multiple business data are obtained.

[0109] In step 109, the accuracy of the business model is determined based on the business output results and the actual business results.

[0110] Taking the business output result and the actual business result of a business data as an example, if the difference between the business output result and the actual business result is less than the preset difference, it is determined that the business model's processing result for this business data is accurate; if the difference between the business output result and the actual business result is not less than the preset difference, it is determined that the business model's processing result for this business data is inaccurate.

[0111] If N out of M false business data points have accurate processing results, then the accuracy rate = N / M * 100%, where M and N are both integers, and M ≥ N.

[0112] In step 110, if the accuracy is lower than the preset value, the business model is optimized by using machine learning, with multiple business data as input and the actual business results of the multiple business data as output.

[0113] This includes optimizing the business model, such as optimizing the basic metrics and metric options within the business model.

[0114] In this way, by configuring basic elements such as basic indicators, operators, indicator options, formulas, and conditions to build a business model, a flexible and low-code business development model is provided.

[0115] Based on the above-described business model establishment process, this application embodiment also provides a business processing method. Figure 2 A flowchart of a business process provided in this application embodiment includes the following steps.

[0116] In step 201, the correspondence between each condition code and the judgment result in the business model, as well as the judgment order of each condition code, are obtained.

[0117] In step 202, based on the judgment order, the condition code that has not been judged and has the earliest judgment order is selected as the target condition code.

[0118] In step 203, the logic code in the target condition code is segmented to obtain at least two formula codes contained in the target condition code.

[0119] That is, the target condition code is divided into segments based on the logic code to obtain at least two formula codes contained in the target condition code.

[0120] In step 204, the indicator code in each formula code is replaced using the corresponding indicator option in the current business data, and the replaced formula code is calculated.

[0121] In step 205, based on the logic code in the target condition code, logical operations are performed on the calculation results of these at least two formula codes to obtain the condition result.

[0122] In step 206, it is determined whether the condition result is true. If it is true, proceed to step 207; otherwise, proceed to step 202.

[0123] In step 207, the judgment result corresponding to the target condition code is determined as the business output result of the business model on the business data.

[0124] In addition, in some complex business scenarios, at least two business models can be connected and used together.

[0125] Specifically, at least two business models are obtained. Then, according to the business logic relationships between the business models, business data is input into these at least two business models to obtain the business processing results. The method for establishing each business model can be found in [link to relevant documentation]. Figure 1 For instructions on how to use each model, please refer to [link / reference]. Figure 2 .

[0126] The following section uses the establishment of a business model in the financial field as an example to introduce the solution of this application embodiment.

[0127] This solution can automatically generate and optimize business models in the financial field through front-end configuration, significantly reducing code development and deployment cycles, and improving the iteration efficiency and accuracy of business models.

[0128] The main steps are as follows:

[0129] 1) Pre-configured basic model elements;

[0130] 2) Users enter formula information through the interface;

[0131] 3) Convert the formula information entered by the user and then store it in the database;

[0132] 4) Users construct a single condition from multiple formulas using logical operators;

[0133] 5) Users construct a business model by combining multiple conditions and the corresponding judgment results;

[0134] 6) Optimize business models through machine learning.

[0135] The steps described above will be explained in detail below.

[0136] The first step is to pre-configure the database, which includes basic indicators, indicator codes for basic indicators, operators, calculation codes for operators, logical operators, logical codes for logical operators, indicator options, and option codes for indicator options.

[0137] Generally, a database may contain one basic indicator table and one indicator option table. The basic indicator table contains three fields: indicator code, indicator name, and indicator type. The indicator option table contains fields such as indicator code, option code, and option name. In addition, for indicators of option type in the basic indicator table, the indicator option table can also store one-to-many indicator options. For indicators of non-option type, the indicator value can be entered by the user.

[0138] In addition, the database can store a rich expression engine, including operators and logical operators. Operators include basic addition, subtraction, multiplication, and division, as well as complex square roots, powers, absolute values, maximum values, minimum values, average values, standard deviations, quantiles, and rankings; logical operators include greater than, less than, equal to, greater than or equal to, less than or equal to, and not equal to.

[0139] The second step is to determine the basic indicators, operators, and logical operators according to the user's instructions, and to determine the indicator code of the basic indicators, the calculation code of the operators, and the logical code of the logical operators.

[0140] Specifically, for each basic indicator, if the basic indicator is an optional indicator, the indicator option of the basic indicator can be determined from multiple optional indicator options based on the user's selection, and the option code of this indicator option can be determined; if the basic indicator is a non-optional indicator, the indicator value of the basic indicator can be determined based on the user's input.

[0141] The third step is to construct the formula code for each formula based on the basic indicators, operators, indicator values ​​or indicator options, indicator codes, calculation codes, and option codes. The formula codes for each formula are then stored in a database table.

[0142] Specifically, for each formula, if the basic indicator contained in the formula is an option indicator, then the formula code of the formula is constructed based on the basic indicator, operator, indicator option, indicator code of the basic indicator, calculation code of the operator, and option code of the indicator option contained in the formula. If the basic indicator contained in the formula is a non-option indicator, then the formula code of the formula is constructed based on the basic indicator, operator, indicator value contained in the formula, indicator code of the basic indicator, calculation code of the operator, and indicator value.

[0143] For example, the formula: OutRating>11, after being transcoded and stored in the database, is: outRating>11, where outRating is the indicator code of the basic indicator of OutRating, 11 is the option code of the indicator option of AA, and > is the calculation code of the greater than operator.

[0144] The fourth step is to connect the at least two formulas contained in each condition using logical operators to obtain the condition code. The condition codes for each condition are then stored in a database table.

[0145] For example, the condition that the external debt rating is greater than AA and the asset classification is normal includes two formulas: the external debt rating is greater than AA and the asset classification is normal. These two formulas are connected into a single condition by the AND logical operator.

[0146] There is a condition table in the database, containing condition IDs and condition content. For example, if the external debt rating is greater than AA and the asset classification is normal, the condition content field in the condition table would be "11and 22". 11 is the formula ID for the formula "external debt rating greater than AA", 22 is the formula ID for the formula "asset classification is normal", and "and" represents "and".

[0147] The fifth step is to configure the judgment result for each condition and the judgment order of each condition to obtain the business model.

[0148] Taking the asset impairment assessment model as an example, its business rules are shown in Table 1:

[0149] Table 1

[0150]

[0151]

[0152] In Table 1, when the content of a condition is empty, it means that the condition is satisfied by default if other conditions are not met.

[0153] Step 6: Optimize the business model.

[0154] Collect the input, judgment results, and actual results of the business model, generate a training set, and calculate the first accuracy of the business model based on the judgment results and actual results. Optimize the indicator values ​​and option values ​​of the business model using machine learning and the training set. Run the business model and calculate the second accuracy. When the difference between the second accuracy and the first accuracy is greater than a specified value, the business model can be replaced according to the instruction.

[0155] In this embodiment, users can develop and modify business models simply by configuring them on a webpage, eliminating the need for coding and minimizing code development effort. Furthermore, the configuration takes effect immediately after completion, avoiding the cumbersome steps of traditional development, testing, and deployment, resulting in rapid model adoption. Since no new code needs to be developed, the introduction of new bugs is also avoided. Additionally, continuous model optimization through machine learning can improve the model's accuracy and confidence.

[0156] The following section describes the process of using the business model established in the above manner.

[0157] The database stores a business model table, which contains fields such as model ID, condition ID, judgment result value, and judgment order.

[0158] See Figure 3 When a business model is applied to a field in the business data, the process first retrieves the condition IDs, corresponding judgment results, and judgment order of the business model from the business model table using the model ID. Then, it joins the condition table using the condition IDs to find all conditions. Each condition is parsed according to the judgment order. Specifically, the parsing steps involve splitting the condition content using characters such as "(", ")", "and", and "or" to obtain the formula IDs contained in the condition. These formula IDs are then joined to the formula table to obtain the specific formula content. Parsing the formula yields the formula result: "true" or "false". The formula result is then substituted into the condition, replacing the formula ID, resulting in expressions like "true and false" or "true or false". Logical operations are then performed to obtain the condition result: true or false. When the condition result is true, the condition is hit; when the result is false, the next condition is judged. Finally, the business model returns the judgment result of the hit condition.

[0159] In the above process, the formula parsing process is as follows: the formula content is searched, and when the indicator code is found, it is replaced with the field value corresponding to the field to obtain a replaced formula such as "1+2>2", and calculation and logical operation are performed to obtain a formula result such as true or false.

[0160] The following example illustrates the process of using multiple business models to handle complex business processes.

[0161] See Figure 4 For example, the impairment model for determining the impairment ratio when assessing asset impairment includes four sub-models: the impairment stage sub-model (corresponding to the business model in Table 1 above), the default probability sub-model, the default loss rate sub-model, and the impairment ratio sub-model. Each sub-model is established using the model establishment method described above.

[0162] The impairment stage sub-model is used to divide impairment stages, such as stage one, stage two, and stage three. The input of the impairment stage sub-model is the internal rating of the debt and default information such as the number of days of principal default and the number of days of interest default. The output is the impairment stage.

[0163] The default probability sub-model is used to estimate the default probability of an asset. The inputs to the default probability sub-model are the impairment stage, rating agency, debt rating, issuer rating, and forward-looking coefficient, and the output is the default probability.

[0164] The loss due to default sub-model is used to estimate the proportion of principal loss of an asset in the event of default. The inputs of the loss due to default sub-model are asset type, collateral type, type of collateral, and currency, and the output is the loss due to default.

[0165] The impairment ratio sub-model is used to calculate the impairment ratio of an asset. The inputs to the impairment ratio sub-model are the impairment stage, the probability of default, and the loss due to default, and the output is the impairment ratio.

[0166] When the method provided in the embodiments of this application is implemented in software, hardware, or a combination of software and hardware, the electronic device may include multiple functional modules, and each functional module may include software, hardware, or a combination thereof.

[0167] Based on the same technical concept, this application also provides a business model establishment device. The principle of the business model establishment device in solving the problem is similar to that of the above-mentioned business model establishment method. Therefore, the implementation of the business model establishment device can refer to the implementation of the business model establishment method, and the repeated parts will not be described again. Figure 5 A schematic diagram of a business model establishment apparatus provided in this application embodiment includes:

[0168] Formula setting module 501 is used to determine at least two formulas in natural language form in response to a formula setting operation, each formula including a basic indicator, a calculator, and indicator options;

[0169] Formula generation module 502 is used to connect the indicator code of the basic indicator and the option code of the indicator option of the formula by using the calculation code of the operator of each formula to obtain the formula code of the formula.

[0170] Condition setting module 503 is used to determine at least two conditions in natural language form in response to a condition setting operation, each condition including at least two formulas and a logical operator;

[0171] The condition generation module 504 is used to connect the formula codes of the formulas in the conditions using the logical codes of the logical operators of each condition, so as to obtain the condition codes of the conditions.

[0172] The rule setting module 505 is used to determine business rules in natural language form in response to business setting operations. The business rules include the judgment results and judgment order of each condition.

[0173] The model generation module 506 is used to establish the correspondence between the condition code and the judgment result of each condition, and to set the judgment order of each condition code according to the judgment order to obtain the business model.

[0174] In some embodiments, the formula setting module 501 is specifically configured to determine the formula for each natural language form according to the following steps:

[0175] In response to the basic indicator setting operation, determine the basic indicators included in the formula;

[0176] If the basic indicator is a non-optional indicator, then the indicator value input control will be displayed;

[0177] In response to the trigger operation of the indicator value input control, the currently input indicator value is determined as the indicator option included in the formula;

[0178] If the basic indicator is an optional indicator, then display the indicator option set of the basic indicator;

[0179] In response to the selection operation of the indicator option set, the selected indicator option is determined as the indicator option included in the formula;

[0180] In response to the operator setting operation, the operators included in the formula are determined.

[0181] In some embodiments, it also includes:

[0182] The business processing module 507 is used to process business data using the business model after obtaining the business model, and obtain business output results.

[0183] In some embodiments, a model update module 508 is further included, for:

[0184] After obtaining the business model, acquire the business output results and actual business results of the business model for multiple business data.

[0185] Based on the business output results and the actual business results, the accuracy of the business model is determined;

[0186] If the accuracy rate is lower than the preset value, the business model is optimized by using machine learning, with multiple business data as input and the actual business results of the multiple business data as output.

[0187] Based on the same technical concept, this application also provides a business processing device. The principle of the business processing device in solving the problem is similar to that of the above-mentioned business processing method. Therefore, the implementation of the business processing device can refer to the implementation of the business processing method, and the repeated parts will not be described again. Figure 6 A schematic diagram of a business processing apparatus provided in this application embodiment includes:

[0188] The acquisition module 601 is used to acquire the correspondence between each condition code and the judgment result in the business model, as well as the judgment order of each condition code;

[0189] Selection module 602 is used to select the target condition code that has not been judged and has the earliest judgment order based on the judgment order;

[0190] The segmentation module 603 is used to segment the logic code in the target condition code to obtain at least two formula codes contained in the target condition code;

[0191] Formula calculation module 604 is used to replace the indicator code in each formula code with the corresponding indicator option in the current business data, and then calculate the replaced formula code.

[0192] The condition judgment module 605 is used to perform logical operations on the calculation results of the at least two formula codes based on the logical code in the target condition code to obtain the condition result;

[0193] The business processing module 606 is used to perform the step of selecting the target condition code that has not been judged and has the earliest judgment order based on the judgment order if the condition result is not true; if the condition result is true, the judgment result corresponding to the target condition code is determined as the business output result of the business model on the business data.

[0194] Based on the same technical concept, this application also provides a business processing device. The principle of the business processing device in solving the problem is similar to that of the above-mentioned business processing method. Therefore, the implementation of the business processing device can refer to the implementation of the business processing method, and the repeated parts will not be described again. Figure 7 A schematic diagram of a business processing apparatus provided in this application embodiment includes:

[0195] The acquisition module 701 is used to acquire at least two business models, wherein each business model is established using any of the methods described above;

[0196] The processing module 702 is used to input business data into the at least two business models according to the business logic relationship between each business model, and obtain the business processing result.

[0197] The module division in this application embodiment is illustrative and only represents one logical functional division. In actual implementation, other division methods are possible. Furthermore, the functional modules in each embodiment of this application can be integrated into a single processor, exist as separate physical entities, or be integrated into a single module. Coupling between modules can be achieved through interfaces, typically electrical communication interfaces, but mechanical interfaces or other types of interfaces are also possible. Therefore, modules described as separate components may or may not be physically separate; they can be located in one place or distributed across different locations on the same or different devices. The integrated modules described above can be implemented in hardware or as software functional modules.

[0198] Having introduced the business model establishment method, business processing method, and apparatus according to exemplary embodiments of this application, we will now introduce an electronic device according to another exemplary embodiment of this application.

[0199] In some possible implementations, the electronic device of this application may include at least one processor and at least one memory. The memory stores program code that, when executed by the processor, causes the processor to perform the methods described above according to the various exemplary embodiments of this application.

[0200] The following reference Figure 8 To describe an electronic device 130 implemented according to this embodiment of the present application. Figure 8 The electronic device 130 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0201] like Figure 8As shown, the electronic device 130 is presented in the form of a general-purpose electronic device. The components of the electronic device 130 may include, but are not limited to: at least one processor 131, at least one memory 132, and a bus 133 connecting different system components (including memory 132 and processor 131).

[0202] Bus 133 represents one or more of several bus structures, including a memory bus or memory controller, peripheral bus, processor, or local bus using any of the various bus structures.

[0203] The memory 132 may include a readable medium in the form of volatile memory, such as random access memory (RAM) 1321 and / or cache memory 1322, and may further include read-only memory (ROM) 1323.

[0204] The memory 132 may also include a program / utility 1325 having a set (at least one) of program modules 1324, including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0205] Electronic device 130 can also communicate with one or more external devices 134 (e.g., keyboard, pointing device, etc.), and with one or more devices that enable a user to interact with electronic device 130, and / or with any device that enables electronic device 130 to communicate with one or more other electronic devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 135. Furthermore, electronic device 130 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 136. As shown, network adapter 136 communicates with other modules used in electronic device 130 via bus 133. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 130, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0206] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided, such as a memory 132 including instructions, which can be executed by a processor 131 to complete the above-described method for establishing a business model or any business processing method. Optionally, the storage medium may be a non-transitory computer-readable storage medium, such as a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device.

[0207] In an exemplary embodiment, a computer program product is also provided, which, when invoked and executed by an electronic device, causes the electronic device to perform any of the exemplary methods provided in this application.

[0208] Furthermore, computer program products may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, RAM, ROM, erasable programmable read-only memory (EPROM), flash memory, optical fiber, compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0209] The program product used for establishing a business model or any business processing in the embodiments of this application may be a CD-ROM and include program code, and may run on a computing device. However, the program product of this application is not limited thereto. In this document, the readable storage medium may be any tangible medium that contains or stores a program, which may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0210] A readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying readable program code. This propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0211] The program code contained on the readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, radio frequency (RF), or any suitable combination thereof.

[0212] Program code for performing the operations of this application can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, such as a Local Area Network (LAN) or a Wide Area Network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0213] It should be noted that although several units or sub-units of the device have been mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to embodiments of this application, the features and functions of two or more units described above can be embodied in one unit. Conversely, the features and functions of one unit described above can be further divided and embodied by multiple units.

[0214] Furthermore, although the operations of the method of this application are described in a specific order in the accompanying drawings, this does not require or imply that these operations must be performed in that specific order, or that all the operations shown must be performed to achieve the desired result. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step, and / or one step may be broken down into multiple steps.

[0215] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0216] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0217] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0218] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0219] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0220] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for establishing a business model, characterized in that, include: In response to a formula setting operation, at least two formulas in natural language form are determined, each formula including a basic indicator, an operator, and indicator options, wherein the basic indicator includes non-optional indicators and optional indicators; By using the calculation code of the operator of each formula, the indicator code of the basic indicator of the formula and the option code of the indicator option are connected to obtain the formula code of the formula. In response to a condition setting operation, determine at least two conditions in natural language form, each condition including at least two formulas and one logical operator; By using the logical code of the logical operator of each condition, the formula code of the formula in the condition is connected to obtain the condition code of the condition; In response to a business settings operation, business rules in natural language form are determined, the business rules including the judgment results and judgment order of each condition; Establish the correspondence between the condition code and the judgment result for each condition, and set the judgment order of each condition code according to the judgment order to obtain the business model; when the target business model is applied to the fields in the business data, each condition corresponding to the target business model is parsed according to the judgment order corresponding to the target business model to obtain the formula contained in the condition, and the formula result is obtained by parsing each formula. Logical operations are performed based on the obtained formula results to obtain conditional results. When the conditional results are true, the judgment result of the condition corresponding to the conditional results is output. The target business model is obtained by taking multiple business data as input and the actual business results of the multiple business data as output, and by using machine learning to optimize the indicator values ​​and option values ​​of the target business model.

2. The method as described in claim 1, characterized in that, The formula for each natural language form is determined according to the following steps: In response to the basic indicator setting operation, determine the basic indicators included in the formula; If the basic indicator is a non-optional indicator, then the indicator value input control will be displayed; In response to the trigger operation of the indicator value input control, the currently input indicator value is determined as the indicator option included in the formula; If the basic indicator is an optional indicator, then display the indicator option set of the basic indicator; In response to the selection operation of the indicator option set, the selected indicator option is determined as the indicator option included in the formula; In response to the operator setting operation, the operators included in the formula are determined.

3. The method as described in claim 1 or 2, characterized in that, After obtaining the business model, the following is also included: Obtain the business output results and actual business results of the business model for multiple business data; Based on the business output results and the actual business results, the accuracy of the business model is determined; If the accuracy rate is lower than the preset value, the business model is optimized by using machine learning, with multiple business data as input and the actual business results of the multiple business data as output.

4. A business processing method, characterized in that, include: Obtain the correspondence between each condition code and the judgment result in the business model, as well as the judgment order of each condition code; Based on the judgment order, select the target condition code that has not been judged and has the earliest judgment order; The logic code in the target condition code is segmented to obtain at least two formula codes contained in the target condition code, wherein each formula includes a basic indicator, a calculator, and indicator options, and the basic indicator includes non-option indicators and option indicators; Using the corresponding indicator options in the current business data, replace the indicator code in each formula code, and then calculate the replaced formula code; Based on the logical code in the target condition code, perform logical operations on the calculation results of the at least two formula codes to obtain the condition result; If the condition result is not true, then the step of selecting the target condition code that has not been judged and has the earliest judgment order is executed based on the judgment order; If the condition result is true, the judgment result corresponding to the target condition code is determined as the business output result of the business model on the business data. The business model is obtained by optimizing the indicator values ​​and option values ​​of the business model by taking multiple business data as input and the actual business results of the multiple business data as output, and by using machine learning.

5. A business processing method, characterized in that, include: Obtain at least two business models, wherein each business model is established using the method described in any one of claims 1 to 3; According to the business logic relationships between the various business models, business data is input into at least two business models to obtain business processing results. When one of the business models is applied to a field in the business data, each condition corresponding to the business model is parsed according to the judgment order corresponding to the business model to obtain the formula contained in the condition. The formula result is obtained by parsing each formula. Logical operation is performed based on the obtained formula result to obtain the condition result. When the condition result is true, the judgment result of the condition corresponding to the condition result is output. Each business model is obtained by taking multiple business data as input and the actual business results of the multiple business data as output, and by using machine learning to optimize the indicator values ​​and option values ​​of each business model.

6. A business model establishment apparatus, characterized in that, include: The formula setting module is used to determine at least two formulas in natural language form in response to the formula setting operation. Each formula includes a basic indicator, an operator, and indicator options. The basic indicator includes non-option indicators and option indicators. The formula generation module is used to connect the indicator code of the basic indicator and the option code of the indicator option of the formula by using the calculation code of the operator of each formula to obtain the formula code of the formula. The condition setting module is used to determine at least two conditions in natural language form in response to a condition setting operation, each condition including at least two formulas and one logical operator; The condition generation module is used to connect the formula codes of the formulas in the conditions using the logical codes of the logical operators of each condition, so as to obtain the condition code of the condition. The rule setting module is used to determine business rules in natural language form in response to business setting operations. The business rules include the judgment results and judgment order of each condition. The model generation module is used to establish the correspondence between the condition code and the judgment result of each condition, and to set the judgment order of each condition code according to the judgment order to obtain the business model; when the target business model is applied to the fields in the business data, each condition corresponding to the target business model is parsed according to the judgment order corresponding to the target business model to obtain the formula contained in the condition, and the formula result is obtained by parsing each formula. Logical operations are performed based on the obtained formula results to obtain conditional results. When the conditional results are true, the judgment result of the condition corresponding to the conditional results is output. The target business model is obtained by taking multiple business data as input and the actual business results of the multiple business data as output, and by using machine learning to optimize the indicator values ​​and option values ​​of the target business model.

7. The apparatus as claimed in claim 6, characterized in that, The formula setting module is specifically used to determine the formula for each natural language form according to the following steps: In response to the basic indicator setting operation, determine the basic indicators included in the formula; If the basic indicator is a non-optional indicator, then the indicator value input control will be displayed; In response to the trigger operation of the indicator value input control, the currently input indicator value is determined as the indicator option included in the formula; If the basic indicator is an optional indicator, then display the indicator option set of the basic indicator; In response to the selection operation of the indicator option set, the selected indicator option is determined as the indicator option included in the formula; In response to the operator setting operation, the operators included in the formula are determined.

8. The apparatus as claimed in claim 6 or 7, characterized in that, It also includes a model update module, used for: After obtaining the business model, acquire the business output results and actual business results of the business model for multiple business data. Based on the business output results and the actual business results, the accuracy of the business model is determined; If the accuracy rate is lower than the preset value, the business model is optimized by using machine learning, with multiple business data as input and the actual business results of the multiple business data as output.

9. A business processing device, characterized in that, include: The acquisition module is used to obtain the correspondence between each condition code and the judgment result in the business model, as well as the judgment order of each condition code; The selection module is used to select the target condition code that has not been judged and has the earliest judgment order, based on the judgment order. The segmentation module is used to segment the logic code in the target condition code to obtain at least two formula codes contained in the target condition code, wherein each formula includes a basic indicator, a calculator and indicator options, and the basic indicator includes non-option indicators and option indicators. The formula calculation module is used to replace the indicator code in each formula code with the corresponding indicator option in the current business data, and then calculate the replacement formula code. The condition judgment module is used to perform logical operations on the calculation results of the at least two formula codes based on the logical code in the target condition code to obtain the condition result; The business processing module is used to: if the condition result is not true, execute the step of selecting the target condition code that has not been judged and has the earliest judgment order based on the judgment order; if the condition result is true, determine the judgment result corresponding to the target condition code as the business output result of the business model for the business data. The business model is obtained by optimizing the indicator values ​​and option values ​​of the business model using machine learning methods, with multiple business data as input and the actual business results of the multiple business data as output.

10. A business processing apparatus, characterized in that, include: An acquisition module is used to acquire at least two business models, wherein each business model is established using the method described in any one of claims 1 to 3; The processing module is used to input business data into the at least two business models according to the business logic relationship between the various business models, and obtain the business processing results.

11. An electronic device, characterized in that, include: At least one processor, and a memory communicatively connected to said at least one processor, wherein: The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method as described in any one of claims 1-5.

12. A storage medium, characterized in that, When the instructions in the storage medium are executed by the processor of the electronic device, the electronic device is able to perform the method as described in any one of claims 1-5.

13. A computer program product, characterized in that, When a computer program product is invoked and executed by an electronic device, the electronic device performs the method as described in any one of claims 1-5.

Images