Business analysis method and related device based on natural language processing model

Abstract

The present application relates to the field of artificial intelligence technology, and provides a business analysis method and related devices based on a natural language processing model, wherein the method includes: obtaining basic information and business transaction data of a target enterprise; analyzing the basic information based on a natural language processing model to obtain target business rules of the target enterprise; constructing a portrait model of the target enterprise based on the business transaction data and the basic information; analyzing the portrait model based on the target business rules to obtain the numerical values ​​of the business indicators of the target enterprise. The use of this application can improve the efficiency and accuracy of business analysis, which is conducive to improving the targeting and precision of enterprise management.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and mainly to a business analysis method and related devices based on a natural language processing model. Background Art

[0002] With the development of computer technology and network technology, investment and financial management, insurance purchase, travel, daily consumption, online shopping, mobile payment and other businesses have penetrated into people's lives. Analyzing the business of enterprises, for example, analyzing the key performance indicators (KPI), daily flow, loan risk value, turnover, illegal operations and other information in the bank's business, is conducive to improving the management of enterprises. At present, data analysis of enterprise business is still in the initial stage, and manual judgment according to preset rules has problems of low efficiency and accuracy. Summary of the invention

[0003] The embodiments of the present application provide a business analysis method and related devices based on a natural language processing model, which can improve the efficiency and accuracy of business analysis and help improve the targeting and precision of enterprise management.

[0004] In a first aspect, an embodiment of the present application provides a business analysis method based on a natural language processing model, wherein:

[0005] Obtain basic information and business transaction data of the target enterprise;

[0006] Analyze the basic information based on a natural language processing model to obtain target business rules of the target enterprise;

[0007] Building a portrait model of the target enterprise based on the business transaction data and the basic information;

[0008] The portrait model is analyzed based on the target business rules to obtain the numerical values ​​of the business indicators of the target enterprise.

[0009] In a second aspect, an embodiment of the present application provides a business analysis device based on a natural language processing model, wherein:

[0010] A first acquisition unit, used to acquire basic information and business transaction data of a target enterprise;

[0011] A first analysis unit, configured to analyze the basic information based on a natural language processing model to obtain a target business rule of the target enterprise;

[0012] A construction unit, configured to construct a portrait model of the target enterprise based on the business transaction data and the basic information;

[0013] The second analysis unit is used to analyze the portrait model based on the target business rules to obtain the numerical value of the business indicator of the target enterprise.

[0014] In a third aspect, an embodiment of the present application provides a computer device, comprising a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the program includes instructions for some or all of the steps described in the first aspect.

[0015] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the computer program enables a computer to execute to implement some or all of the steps described in the first aspect.

[0016] Implementing the embodiments of the present application will have the following beneficial effects:

[0017] After adopting the above-mentioned business analysis method based on natural language processing model and related devices, the basic information and business transaction data of the target enterprise are first obtained. Then, the basic information of the target enterprise is analyzed based on the natural language processing model to obtain the target business rules of the target enterprise, and a portrait model of the target enterprise is constructed based on the business transaction data and basic information of the target enterprise. Then, the portrait model is analyzed based on the target business rules to obtain the numerical values ​​of the business indicators of the target enterprise. In this way, the efficiency and accuracy of business analysis can be improved, which is conducive to improving the targeting and accuracy of enterprise management. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] in:

[0020] Figure 1 A flowchart of a business analysis method based on a natural language processing model provided in an embodiment of the present application;

[0021] Figure 2 A schematic diagram of an email reminder provided in an embodiment of the present application;

[0022] Figure 3 A schematic diagram of the structure of a business analysis device based on a natural language processing model provided in an embodiment of the present application;

[0023] Figure 4 A schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. According to the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0025] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0026] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0027] The network architecture used in the embodiment of the present application includes a server and an electronic device. The embodiment of the present application does not limit the number of electronic devices and servers, and the server can provide services for multiple electronic devices at the same time. The server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms. The server may be implemented by a server cluster consisting of multiple servers.

[0028] The electronic device may be a personal computer (PC), a laptop or a smart phone, or an all-in-one machine, a handheld computer, a tablet computer (pad), a smart TV player terminal, a vehicle-mounted terminal or a portable device. The operating system of the electronic device on the PC side, such as an all-in-one machine, may include but is not limited to Linux system, Unix system, Windows series system (such as Windows XP, Windows 7, etc.), Mac OS X system (Apple computer operating system) and other operating systems. The operating system of the electronic device on the mobile side, such as a smart phone, may include but is not limited to Android system, IOS (Apple mobile phone operating system), Window system and other operating systems.

[0029] The electronic device can install and run the application, and the server can be a server corresponding to the application installed in the electronic device, providing application services for the application. The application can be a separately integrated application software, or a small program embedded in other applications, or a system on a web page, etc., which is not limited here.

[0030] In the embodiment of the present application, the application program may be an application program with a business analysis function, or an information management platform of a target enterprise, etc. The target enterprise involved in the present application may include banks, hospitals, finance, the Internet, and other enterprises with transaction businesses. The target enterprise may be a separate enterprise, or may be a department in an enterprise, such as an administrative department, a material department, a network department, etc.

[0031] The embodiment of the present application proposes a business analysis method based on a natural language processing model, which can be executed by a business analysis device based on a natural language processing model. The device can be implemented by software and / or hardware, and can generally be integrated in an electronic device or a server, which can improve the efficiency and accuracy of business analysis and is conducive to improving the targeting and accuracy of enterprise management.

[0032] It should be noted that the device that performs business analysis on the target enterprise should have the authority to analyze data, otherwise it cannot execute the business analysis method based on the natural language processing model proposed in this application.

[0033] Please refer to Figure 1 , Figure 1 This is a flow chart of a business analysis method based on a natural language processing model provided by the present application. Taking the application of this method in a server as an example, it includes the following steps S101 to S104, wherein:

[0034] S101: Obtain basic information and business transaction data of the target enterprise.

[0035] This application does not limit the target enterprise. Taking banks as an example, it can include central banks, policy banks, commercial banks, investment banks, the World Bank, etc. The enterprise level of the target enterprise can be a branch, head office, office, and business hall, etc., or can be divided into a first-level unit, a second-level unit, and a third-level unit, etc. If the target enterprise is a bank, the enterprise level can be a head office, a branch, a sub-branch, a sub-office, and a savings office, etc. The number of target enterprises can be one or more, which is not limited here.

[0036] In a possible example, before step S101, the method further includes: receiving a business analysis instruction from the target enterprise when a preset time period is reached.

[0037] This application does not limit the preset duration, which can be 1 month, 1 quarter or half a year, etc. The business analysis instruction can be automatically generated by the server, or can be sent to the server by the target enterprise's superior bank or a staff member with management authority over the target enterprise. In this way, the business transaction data of the target enterprise involved in the business analysis instruction can be counted, thereby analyzing the values ​​of the business indicators corresponding to the business transaction data. Then managing the enterprise based on this data is conducive to improving the targeting and accuracy of enterprise management.

[0038] In the embodiment of the present application, the basic information of the target enterprise may include basic enterprise information of the target enterprise, such as name, enterprise level and location information, etc. The location information may include address information of the target enterprise and surrounding area attributes, etc. For example, the location information may include 200 meters from a hospital, 100 meters from a shopping mall, 300 meters from a school, etc.

[0039] The basic information of the target enterprise may also include the basic information of the employees. The basic occupational information may include the number of employees in the target enterprise and each employee's name, age, contact number, home address, education, work experience, and position allocation in the target enterprise (for example, lobby manager, salesperson, teller, security guard, etc. in a bank) and business records, etc., without limitation here.

[0040] Among them, the business record may include the operation record of the staff in handling each business. If the business can receive customer comments, the business record may also include customer rating information on the business. It can be understood that the business record can be used to obtain the business capabilities of the staff and the quality of the business rating, and can also be used to determine whether the staff has violated the regulations, etc., which is conducive to improving the comprehensiveness of the analysis of banking business.

[0041] The basic information of the target enterprise may also include basic business information. The basic business information may include the number of businesses involved by the target enterprise and the name, type, income information and income risk of each business. This application does not limit the type of business. If the target enterprise is a bank, the type of business may include current business, fixed-term business, transfer business, financial management business, insurance business, ecological business or loan business.

[0042] Among them, demand business refers to the business of funds that customers can flexibly access. The funds in the fixed-term business can be withdrawn when the fixed-term period arrives, or can be modified to demand business before the fixed-term period arrives. Transfer business usually includes transfer business, that is, business of transferring money to others. Transfer business can be transferred through the customer's bank card or cash, etc. Financial management business may include fund business, stock business, gold business, etc., and may also include insurance business of financial management nature, etc. Insurance business may include insurance business in which customers use bank cards or passbooks opened in the target enterprise for payment. The insured of the insurance business may be the customer himself or other people such as parents, spouse, children, etc., and the insurance business is provided by the insurance company. Insurance business may also include medical insurance provided by the government, etc. Ecological business may include peripheral businesses introduced into the target enterprise, such as living payment, phone bill recharge, commemorative coin reservation, activity fitness, pension, housing provident fund, popular merchants or preferential activities of third-party applications, etc., which can be applied to many aspects of customer life. Loan business refers to the business of lending to individual customers or corporate customers.

[0043] The income information of a business refers to the income or income range that a customer can obtain by purchasing the business. For example, the interest rate of a current account business is 0.3%, the interest rate of a one-year fixed-term business is 1.75%, and the interest rate of a wealth management business is 4.6%. The income risk of a business refers to the risk level that a customer needs to bear when purchasing the business. It can be determined based on the business type. For example, different wealth management businesses have different income risks. The income risk can be described in the form of high, medium, or low, and is not limited here.

[0044] In an embodiment of the present application, the business transaction data of the target enterprise may include transaction orders and information of each transaction order conducted through the target enterprise. The transaction order may include basic customer information of the transaction customer and profit information generated by the transaction order, etc. Among them, the basic customer information may include the customer's name, age, contact number, home address, education, work experience, contact person, asset information, etc., and may also include order information of the customer using the application corresponding to the target enterprise to conduct transactions, etc. The profit information generated by the transaction order can be obtained through the difference between the income generated by the business and the cost used to pay for the business. The cost of the business may include the expenses and labor generated by launching the business, etc.

[0045] If the business is a loan business, the business transaction data may also include overdue risk, which is used to describe the risk probability of the customer's overdue repayment. The overdue risk can be determined based on the asset information in the customer's basic information, or can also be determined based on the contact person's asset information and / or the asset status determined by the customer's other order information, etc., which is not limited here.

[0046] S102: Analyze the basic information based on a natural language processing model to obtain target business rules of the target enterprise.

[0047] In the embodiment of the present application, the target business rules of the target enterprise are used to obtain the value of the business indicator of the target enterprise, and may include an operation expression for calculating the value of the business indicator and a preset condition of the business indicator to determine whether the value of the business indicator meets the preset condition. The business indicator may include the key performance indicator (KPI) of the target enterprise, the number of customers, the daily traffic of the application or store corresponding to the target enterprise, the risk value of the target enterprise, the turnover of the target enterprise, illegal operations, etc., which are not limited here.

[0048] This application does not limit the preset conditions, which may be whether the KPI of the target enterprise is in the bottom three. Or it may be that the daily flow of customers is less than a threshold value A, or the turnover of the target enterprise is less than a threshold value B, or the risk value of the target enterprise is greater than a threshold value C, or there are illegal operations by employees, etc.

[0049] It is understandable that the preset conditions corresponding to different enterprise levels should be different, the benefits created by target enterprises in different positions are different, and different businesses have different corresponding benefits. Based on this, obtaining the target business rules of the target enterprise based on the basic information of the target enterprise can improve the accuracy of business analysis.

[0050] In an embodiment of the present application, a natural language processing model can be used to analyze the target business rules of a target enterprise. The natural language processing model can be based on a natural language processing algorithm, and can use the Jieba word segmentation tool, or use the word2vec word vector model to obtain the target vocabulary in the basic information of the target enterprise, as well as the part of speech of the target vocabulary (for example, nouns and verbs, as well as names, place names, institution names, etc., or adverbs, noun verbs, etc.) and meaning, so as to determine the meaning of the target vocabulary in the basic information.

[0051] The target vocabulary can be any vocabulary in the basic information, or can be the vocabulary except the stop words. Stop words are words or terms that are automatically filtered out before or after processing natural language data (or text) in information retrieval to save storage space and improve search efficiency. In the embodiments of the present application, a stop word list can be pre-stored, and the stop word list can include multiple stop words. Further, the stop words can be divided into strict stop words and loose stop words. The importance of strict stop words is relatively lower than that of loose stop words. For example, interrogative mood words such as "ma" and "ne" can be strict stop words, and words indicating a sequential relationship such as "then" and "and" can be loose stop words.

[0052] The present application does not limit the method for analyzing the target business rules. The basic information of the target enterprise may include enterprise basic information, employee basic information, and business basic information. In a possible example, step S102 may include the following steps A1 to A4, where:

[0053] A1: Analyze the business basic information based on a natural language processing model to obtain the types of business data involved in the target enterprise.

[0054] As described above, the business basic information may include the quantity of the business involved in the target enterprise, and the name, type, revenue information, and revenue risk of each business, etc., which will not be elaborated here. In the embodiments of the present application, the business data type is the type of data used or required to be used in the business involved in the target enterprise. The name, type, revenue information, and revenue risk of the business, etc., can be extracted from the business basic information based on a natural language processing model, and then the possible data types involved can be obtained based on the above information to obtain the business data type. In this way, the omission of the business data type can be avoided, which is beneficial to improving the comprehensiveness of data analysis.

[0055] A2: Determine the business indicators of the target enterprise and the arithmetic expressions of the business data corresponding to the business indicators based on the business data type.

[0056] As mentioned above, the business indicators may include the target enterprise's KPI, daily traffic, risk value, turnover, illegal operations and other information, which will not be repeated here. In an embodiment of the present application, the operation expression of the business data corresponding to the business indicator is used to calculate the numerical value corresponding to the business indicator based on the business data corresponding to the business indicator. The mapping relationship between the business indicator and the business data can be stored in advance, so that the business indicator and the corresponding business data type can be selected based on whether the data type of the business data in the mapping relationship is the business data type of the target enterprise, and whether the data type has a corresponding relationship with the business data type, and the operation expression of the business data corresponding to the business indicator is determined. In this way, the business indicators that can be evaluated by the target enterprise can be determined based on the business data type of the target enterprise, as well as the operation expression required to evaluate the business indicator, which can improve the comprehensiveness of business analysis.

[0057] A3: Analyze the basic information of the enterprise and the basic information of the employees based on the natural language processing model to obtain preset conditions corresponding to the business indicators.

[0058] As mentioned above, the basic information of the enterprise may include the name, enterprise level and location information, etc. As mentioned above, the basic information of the employees may include the number of employees in the target enterprise and each employee's name, age, contact number, home address, education, work experience, and position allocation in the target enterprise (for example, lobby manager, salesperson, teller, security guard, etc.) and business records, etc. The preset conditions corresponding to the business indicators are used to determine whether the value of the business indicator meets the standard. As mentioned above, the preset conditions may be whether the KPI of the target enterprise is in the bottom 3. Or it may be that the daily flow of customers is less than a threshold value A, or the turnover of the target enterprise is less than a threshold value B, or the risk value of the target enterprise is greater than a threshold value C, or there may be illegal operations by employees, etc., which will not be repeated here.

[0059] The present application does not limit the method for determining the preset condition. In a possible example, step A3 may include the following steps A31 to A35, wherein:

[0060] A31: Obtain the enterprise level and / or location information of the target enterprise from the basic information of the enterprise based on the natural language processing model.

[0061] A32: Obtain the number of employees of the target enterprise and / or capability information of each employee from the basic information of the employees based on the natural language processing model.

[0062] The present application does not limit the execution order of step A31 and step A32. Step A31 may be executed first, and then step A32. Alternatively, step A32 may be executed first, and then step A31. Alternatively, step A31 and step A32 may be executed simultaneously.

[0063] In the embodiment of the present application, if the basic information of the enterprise includes the enterprise level and / or location information of the target enterprise, the text corresponding to the level and location information and other similar words can be directly extracted from the basic information of the enterprise based on the natural language processing model to obtain the enterprise level and / or location information of the target enterprise. If the basic information of the enterprise does not include the enterprise level and / or location information of the target enterprise, the enterprise level and / or location information of the target enterprise can be found from the Internet or pre-stored information based on the name or logo of the target enterprise in the basic information of the enterprise.

[0064] If the basic information of employees includes the number of employees and the ability information of each employee, then the text corresponding to the number of employees and the ability information of each employee can be directly extracted from the basic information of employees based on the natural language processing model to obtain the number of employees and the ability information of each employee. If the basic information of employees does not include the number of employees and the ability information of each employee, the data of the employees can be determined based on the number of their work numbers, and the ability information of the employees can be determined based on their business records. Optionally, the processing rate and processing quality of the employees can be determined based on the operation records in the business records and the customer's rating information, and then the ability information of the employees can be determined based on the processing rate and processing quality.

[0065] A33: Obtaining the evaluation grade of the target enterprise based on the enterprise grade and / or the location information.

[0066] A34: Obtain evaluation values ​​of the employees based on the number of the employees and / or the ability information.

[0067] The present application does not limit the execution order of step A33 and step A34. Step A33 may be executed first, and then step A34. Alternatively, step A34 may be executed first, and then step A33. Alternatively, step A33 and step A34 may be executed simultaneously.

[0068] In the embodiment of the present application, the evaluation level is used to describe the requirements of the target enterprise. That is to say, the higher the evaluation level, the higher the preset condition. It can be understood that the higher the enterprise level or the more prosperous the location information of the target enterprise (for example, large daily traffic, large permanent population, etc.), the higher the corresponding evaluation level. The evaluation level can be a weighted average value between the sub-evaluation level corresponding to the enterprise level and the sub-evaluation level corresponding to the location information, or a minimum value, etc. In step A33, the evaluation level of the target enterprise is obtained based on the enterprise level and / or location information, which is conducive to improving the accuracy of data analysis.

[0069] In the embodiment of the present application, the evaluation value is used to describe the business capabilities that the target enterprise can handle, wherein the larger the evaluation value, the higher the preset condition. It can be understood that the more employees there are or the stronger the ability of the employees, the larger the amount of business that can be carried out, and a larger evaluation value can be corresponding to select a higher preset condition. The evaluation value can be a weighted average value between the sub-evaluation corresponding to the number of employees and the sub-evaluation value corresponding to the ability information, or a minimum value, etc. In step A34, the evaluation value of the employee is obtained based on the number of employees and / or the ability information, which is conducive to improving the accuracy of data analysis.

[0070] A35: Obtaining a preset condition corresponding to the business indicator based on the evaluation level and the evaluation value.

[0071] In the embodiment of the present application, the range corresponding to the preset condition can be determined based on the evaluation level, and then the preset condition can be obtained from the range corresponding to the preset condition based on the evaluation value. Alternatively, a weighted average value between the value corresponding to the evaluation level and the evaluation value can be obtained first, and then the preset condition can be selected from the preset condition library based on the weighted average value, etc., which is not limited here.

[0072] It can be understood that in steps A31 to A35, the enterprise level and / or location information of the target enterprise is first obtained from the basic information of the enterprise based on the natural language processing model, and the number of employees of the target enterprise and / or the ability information of each employee are obtained from the basic information of the employees. Then, the evaluation level of the target enterprise is obtained based on the enterprise level and / or location information, and the evaluation value of the employee is obtained based on the number of employees and / or the ability information of each employee. Finally, the preset conditions are obtained based on the evaluation level and the evaluation value. In other words, obtaining the preset conditions from the perspective of the basic information of the enterprise and the basic information of the employees can improve the accuracy of setting the preset conditions, which is conducive to improving the effect of data analysis.

[0073] A4: Generate target business rules for the target enterprise based on the preset conditions and the operation expression.

[0074] It can be understood that in steps A1 to A4, the basic business information is first analyzed based on the natural language processing model to obtain the business data type involved in the target enterprise, and the basic enterprise information and employee basic information are analyzed based on the natural language processing model to obtain the preset conditions corresponding to the business indicators. Then, the business indicators of the target enterprise and the operation expressions of the business data corresponding to the business indicators are determined based on the business data types. Finally, the target business rules are generated based on the preset conditions and the operation expressions. This is conducive to improving the accuracy of data analysis.

[0075] It should be noted that the present application does not limit the execution order of step A1 and step A3. Step A1 may be executed first, and then step A3. Alternatively, step A3 may be executed first, and then step A1. Alternatively, step A1 and step A3 may be executed simultaneously.

[0076] S103: Constructing a portrait model of the target enterprise based on the business transaction data and the basic information.

[0077] In an embodiment of the present application, a portrait model of a target enterprise is used to describe the basic information and business transaction data of the target enterprise. The portrait model may include a sub-model of each preset dimension in a plurality of preset dimensions. The preset dimensions are used to measure information on one aspect of the target enterprise, and may include dimensions such as scale, revenue, efficiency, customer base, and risk. Among them, scale is used to measure the size of the target enterprise, which can be determined based on the number of customers received and the amount of business handled by the target enterprise. Revenue is used to measure the profitability of the target enterprise, which can be obtained according to the difference between the revenue and expenditure of different business products. Efficiency is used to measure the speed at which the target enterprise handles business, which can be determined from the length of time customers queue in the business hall and the processing time of each business.

[0078] Customer groups are used to measure the types of customers involved in the target enterprise. Customer groups can be classified by age, for example, the elderly and young people; or those born in the 1960s and above, those born in the 1970s, 1980s, 1990s, and those born in the 2000s and below; or 0-17 years old, 18-25 years old, 26-35 years old, 36-45 years old, 45-55 years old, 56 years old and above, etc. Customer groups can also be classified by place of residence, for example, residents of high-quality residential areas, newly built town demolition households, etc. Customer groups can also be classified by occupation, for example, agricultural professionals, professionals, retired users, etc. Professionals refer to professionals with specific professional skills, generally including professors, doctors, judges, lawyers, writers, artists, etc. This group of people generally have a certain degree of authority in the industry they are engaged in, have high incomes, and are one of the key marketing target customer groups of outlets. Customer groups can be classified according to customer levels, for example, potential customers, VIP customers (very important person, VIP), etc.

[0079] Risk is used to measure the risk factor of lending to customers. If the customer is an individual customer, the risk value corresponding to this risk dimension can be determined by the individual customer's asset information and repayment time. If the customer is a corporate customer, the risk value corresponding to this risk dimension can be determined by the corporate customer's asset information, repayment time and the risk value of the supply chain company.

[0080] The present application does not limit the method for constructing the portrait model of the target enterprise, and takes a sub-model of a preset dimension as an example. In a possible example, step S103 may include the following steps B1 to B3, wherein:

[0081] B1: Obtain sub-data corresponding to the preset dimension from the business transaction data and the basic information.

[0082] In an embodiment of the present application, the sub-data corresponding to the preset dimension refers to the data used to measure the preset dimension. For example, the sub-data corresponding to the scale dimension may include the number of business products supported in the target enterprise's business transaction data and the amount of each business product or the proportion of all (or within a region), etc. The sub-data corresponding to the income dimension may include the income information and expenditure information of each business product in the target enterprise's business transaction data. The sub-data corresponding to the efficiency dimension may include the time information of each user from the start of queuing to the completion of the business in the target enterprise's business transaction data and the response efficiency of each employee in handling the business.

[0083] B2: Based on the sub-data corresponding to the preset dimension, obtain the data node corresponding to the preset dimension, and the association relationship between the data node and the associated node associated with the data node.

[0084] In an embodiment of the present application, a data node is a data type in the sub-data corresponding to a preset dimension. An associated node may also be a data type in the sub-data corresponding to a preset dimension, and has an associated relationship with other data nodes. The associated relationship between a data node and an associated node is determined by the associated relationship between the data node and the data corresponding to the associated node. For example, if the data is an upstream-downstream relationship, the associated relationship is an upstream-downstream relationship. For another example, if there is an operational relationship between the data, the associated relationship is an operational relationship.

[0085] B3: Connecting the data node and the associated node based on the association relationship to obtain a sub-model corresponding to the preset dimension.

[0086] It can be understood that in steps B1 to B3, the sub-data corresponding to the preset dimension is first obtained from the business transaction data and / or basic information. Then, based on the sub-data corresponding to the preset dimension, the data node corresponding to the preset dimension and the association relationship between the data node and the associated node associated with the data node are obtained, so as to construct the sub-model corresponding to the preset dimension based on the connection relationship. Then, if the data node in the sub-model is the same as the data node in other sub-models, or there is an association relationship, they can be connected to obtain the portrait model of the target enterprise. In this way, the accuracy of measuring bank information can be improved.

[0087] It should be noted that the present application does not limit the execution order of step S102 and step S103. Figure 1 As shown, step S102 is performed first, and then step S103 is performed. Alternatively, step S103 may be performed first, and then step S102 is performed. Alternatively, step S102 and step S103 may be performed simultaneously.

[0088] S104: Analyze the portrait model based on the target business rules to obtain the numerical values ​​of the business indicators of the target enterprise.

[0089] In the embodiment of the present application, a rule engine can be used to process different business logics. In this way, the target business rules of the target enterprise are used to perform data analysis on the target enterprise's portrait model, which can improve the efficiency and accuracy of data analysis. If the target business rules are modified, the modified target business rules can be used to perform data analysis on the target enterprise's portrait model, thereby improving the flexibility of data analysis.

[0090] The present application does not limit the method for analyzing the portrait model. In a possible example, step S104 may include the following steps C1 to C3, wherein:

[0091] C1: Searching for the target data node corresponding to the operation expression and the associated data nodes of the target data node from the portrait model.

[0092] C2: Based on the association relationship between the target data node and the associated data node, the data corresponding to the target data node and the data corresponding to the associated data node are calculated to obtain the target business data corresponding to the operation expression.

[0093] C3: Calculate the target business data based on the operation expression to obtain the value of the business indicator of the target enterprise.

[0094] In an embodiment of the present application, a target data node refers to a data node in a portrait model that is related to the data in an operation expression in a target business rule. An associated data node refers to a data node in a submodel or a portrait model that is connected to a target data node. The association relationship between a target data node and an associated data node may include an operation relationship between data corresponding to the target data node and data corresponding to the associated data node, and may also include an association value between data corresponding to the target data node and data corresponding to the associated data node. Based on the association relationship between the target data node and the associated data node, the data corresponding to the target data node and the data corresponding to the associated data node may be calculated to obtain the target business data required to be calculated in the operation expression. After obtaining the target business data, the target business data may be calculated based on the operation expression to obtain the numerical value of the business indicator of the target bank. In this way, analyzing the portrait model based on the target business rule can improve the accuracy of obtaining the numerical value of the business indicator.

[0095] exist Figure 1 In the method shown, the basic information and business transaction data of the target enterprise are first obtained. Then, the basic information of the target enterprise is analyzed based on the natural language processing model to obtain the target business rules of the target enterprise, and a portrait model of the target enterprise is constructed based on the business transaction data and basic information of the target enterprise. Then, the portrait model is analyzed based on the target business rules to obtain the values ​​of the business indicators of the target enterprise. In this way, the efficiency and accuracy of business analysis can be improved, which is conducive to improving the targeting and accuracy of enterprise management.

[0096] In a possible example, after step S104, the following step is further included: if the business indicator does not meet the preset condition, a prompt message corresponding to the business indicator is sent to a contact person corresponding to the target enterprise.

[0097] In the embodiment of the present application, the contact person corresponding to the target enterprise may be a manager or a contact person of the target enterprise. The prompt information corresponding to the business indicator is used to prompt that the value corresponding to the business indicator does not meet the preset condition, and can also be used to prompt the contact person to view the data analysis process of the value of the business indicator that does not meet the preset condition. The prompt information can be sent by text message or email, etc., which is not limited here.

[0098] For example, if the business indicator KPI is greater than or equal to 90 points, the preset condition is met. Otherwise, it is not met. Figure 2In the schematic diagram of the email reminder shown, the target enterprise is Branch A, the sender is the business analysis platform, and the recipient is the contact person of Branch A. The sending time is 2021-08-25 16:33, and the subject is Business Indicator-Reminder Email. Branch A's KPI is 80.91, which does not meet the preset business indicator, so the corresponding KPI reminder information is sent to the contact person corresponding to Branch A to remind: Branch A's KPI at the end of July is 80.91 points, ranking 23rd in the bank. Please go to page B for details.

[0099] In a possible example, after step S104, the following steps D1 and D2 are further included, wherein:

[0100] D1: If the value of the service indicator does not meet the preset condition, obtaining configuration information of the target service based on the service indicator.

[0101] D2: Send the configuration information to a contact person corresponding to the target enterprise.

[0102] In the embodiment of the present application, the target business can be a business already involved in the target enterprise, or a business not involved in the target enterprise. In other words, the target business can be a business adjusted by the target enterprise, or a business newly added by the target enterprise.

[0103] The configuration information of the target business can be used to indicate the number of target businesses to be allocated and the target customer groups. This application does not limit the method of obtaining the configuration information. The portrait model of the target enterprise includes a sub-model of the customer group dimension. In a possible example, step D1 may include the following steps D11 to D14, where:

[0104] D11: Obtain the values ​​of reference business indicators of similar enterprises to the target enterprise.

[0105] In the embodiment of the present application, the similar enterprise may be a bank of the same enterprise level as the target enterprise, or may be a bank of the same enterprise level in the same region (or the same type). The method for obtaining the numerical value of the reference business indicator of the similar enterprise can refer to the description of steps S101 to S104 proposed in the present application, which will not be repeated here.

[0106] D12: If the value of the reference business indicator is greater than the value of the business indicator, the portrait model of the similar enterprise is compared with the portrait model of the target enterprise to obtain the reference data node of the target enterprise.

[0107] In an embodiment of the present application, the reference data node may be a data node that is present in both the portrait model of a similar enterprise and the portrait model of the target enterprise; it may also be a data node that is present in the portrait model of a similar enterprise but not in the portrait model of the target enterprise; or it may be a data node that is not present in the portrait model of a similar enterprise but present in the portrait model of the target enterprise, etc., and no limitation is made here.

[0108] D13: Determine a target service based on the reference data node.

[0109] In an embodiment of the present application, the target business can be based on the business corresponding to the reference data node. If the number of reference data nodes is greater than or equal to 2, the master node among the reference data nodes can be selected. The master node can be the node with the most connections among the reference data nodes, or it can be determined whether there is a large difference in data between the reference data nodes in similar enterprises and the reference data nodes in the target enterprise. If so, the reference data node is used as the master node, etc., which is not limited here.

[0110] D14: Acquire configuration information of the target business based on the sub-model of the customer group dimension.

[0111] In an embodiment of the present application, the data node corresponding to the target business can be found from the sub-model of the customer group dimension, and the number of target business to be allocated and the target customer group can be determined based on the data node to obtain the configuration information of the target business.

[0112] It can be understood that in steps D11 to D14, if the value of the reference business indicator of the similar enterprise is greater than the value of the business indicator of the target enterprise, the portrait model of the similar enterprise is compared with the portrait model of the target enterprise to obtain a reference data node. Then, the adjustable target business is determined based on the reference data node, and then the configuration information of the target business is determined based on the sub-model of the customer group dimension of the target industry. In this way, the accuracy of business adjustment can be improved, which is conducive to improving the value of the business indicator of the target enterprise.

[0113] The method of the embodiment of the present application is described in detail above, and the device of the embodiment of the present application is provided below.

[0114] and Figure 1 The embodiment shown is consistent with that shown in FIG. Figure 3 , Figure 3 is a schematic diagram of the structure of a business analysis device based on a natural language processing model proposed in this application, such as Figure 3 As shown, the business analysis device 300 includes:

[0115] The first acquisition unit 301 is used to acquire basic information and business transaction data of the target enterprise;

[0116] A first analyzing unit 302 is used to analyze the basic information based on a natural language processing model to obtain a target business rule of the target enterprise;

[0117] A construction unit 303 is used to construct a portrait model of the target enterprise based on the business transaction data and the basic information;

[0118] The second analysis unit 304 is used to analyze the portrait model based on the target business rules to obtain the numerical value of the business indicator of the target enterprise.

[0119] In a possible example, the basic information includes enterprise basic information, employee basic information and business basic information, and the first analysis unit 302 is specifically used to analyze the business basic information based on a natural language processing model to obtain the type of business data involved in the target enterprise; determine the business indicators of the target enterprise and the operation expressions of the business data corresponding to the business indicators based on the business data types; analyze the enterprise basic information and the employee basic information based on the natural language processing model to obtain preset conditions corresponding to the business indicators; and generate the target business rules of the target enterprise based on the preset conditions and the operation expressions.

[0120] In a possible example, the first analysis unit 302 is specifically used to obtain the enterprise level and / or location information of the target enterprise from the enterprise basic information based on the natural language processing model; obtain the number of employees of the target enterprise and / or the ability information of each employee from the employee basic information based on the natural language processing model; obtain the evaluation level of the target enterprise based on the enterprise level and / or the location information; obtain the evaluation value of the employee based on the number of employees and / or the ability information; and obtain the preset conditions corresponding to the business indicators based on the evaluation level and the evaluation value.

[0121] In a possible example, the second analysis unit 304 is specifically used to search the target data node corresponding to the operation expression and the associated data node of the target data node from the portrait model; based on the association relationship between the target data node and the associated data node, calculate the data corresponding to the target data node and the data corresponding to the associated data node to obtain the target business data corresponding to the operation expression; calculate the target business data based on the operation expression to obtain the numerical value of the business indicator of the target enterprise.

[0122] In a possible example, the business analysis device 300 further includes:

[0123] A second acquisition unit 305 is configured to acquire configuration information of a target service based on the service indicator if the value of the service indicator does not meet the preset condition;

[0124] The communication unit 306 is configured to send the configuration information to a contact person corresponding to the target enterprise.

[0125] In a possible example, the portrait model of the target enterprise includes a sub-model of the customer group dimension, and the second acquisition unit 305 is specifically used to obtain the value of the reference business indicator of similar enterprises of the target enterprise; if the value of the reference business indicator is greater than the value of the business indicator, the portrait model of the similar enterprise is compared with the portrait model of the target enterprise to obtain the reference data node of the target enterprise; the target business is determined based on the reference data node; and the configuration information of the target business is obtained based on the sub-model of the customer group dimension.

[0126] In a possible example, the portrait model of the target enterprise includes a sub-model of each preset dimension in multiple preset dimensions, and the construction unit 303 is specifically used to obtain the sub-data corresponding to the preset dimension from the business transaction data and the basic information; obtain the data node corresponding to the preset dimension based on the sub-data corresponding to the preset dimension, and the association relationship between the data node and the associated node associated with the data node; connect the data node and the associated node based on the association relationship to obtain the sub-model corresponding to the preset dimension.

[0127] The detailed execution process of each unit in the business analysis device 300 can refer to the execution steps in the aforementioned method embodiment, which will not be repeated here.

[0128] and Figure 1 For details, please refer to Figure 4 , Figure 4 Schematic diagram of the structure of a computer device provided in an embodiment of the present application. Figure 4 As shown, the computer device 400 includes a processor 410, a memory 420, a communication interface 430, and one or more programs 440. The processor 410, the memory 420, and the communication interface 430 are interconnected via a bus 450. Figure 3 The related functions implemented by the communication unit 306 shown can be implemented through the communication interface 430. Figure 3 The related functions implemented by the first acquisition unit 301 , the first analysis unit 302 , the construction unit 303 , the second analysis unit 304 , and the second acquisition unit 305 may be implemented by the processor 410 .

[0129] The one or more programs 440 are stored in the memory 420 and are configured to be executed by the processor 410. The program 440 includes instructions for executing the following steps:

[0130] Obtain basic information and business transaction data of the target enterprise;

[0131] Analyze the basic information based on a natural language processing model to obtain target business rules of the target enterprise;

[0132] Building a portrait model of the target enterprise based on the business transaction data and the basic information;

[0133] The portrait model is analyzed based on the target business rules to obtain the numerical values ​​of the business indicators of the target enterprise.

[0134] In a possible example, the basic information includes basic enterprise information, basic employee information, and basic business information. In analyzing the basic information based on a natural language processing model to obtain the target business rules of the target enterprise, the program 440 is specifically used to execute instructions for the following steps:

[0135] Analyze the basic business information based on a natural language processing model to obtain the type of business data involved in the target enterprise;

[0136] Determine the business indicator of the target enterprise and the operation expression of the business data corresponding to the business indicator based on the business data type;

[0137] Analyze the basic information of the enterprise and the basic information of the employees based on the natural language processing model to obtain preset conditions corresponding to the business indicators;

[0138] A target business rule of the target enterprise is generated based on the preset condition and the operation expression.

[0139] In a possible example, in the aspect of analyzing the basic information of the enterprise and the basic information of the employees based on the natural language processing model to obtain the preset conditions corresponding to the business indicators, the program 440 is specifically used to execute the following steps:

[0140] Acquire the enterprise level and / or location information of the target enterprise from the basic information of the enterprise based on the natural language processing model;

[0141] Acquire the number of employees of the target enterprise and / or capability information of each employee from the basic information of the employees based on the natural language processing model;

[0142] Acquire the evaluation grade of the target enterprise based on the enterprise grade and / or the location information;

[0143] Acquiring evaluation values ​​of the employees based on the number of the employees and / or the ability information;

[0144] A preset condition corresponding to the business indicator is obtained based on the evaluation level and the evaluation value.

[0145] In a possible example, in analyzing the portrait model based on the target business rule to obtain the value of the business indicator of the target enterprise, the program 440 is specifically used to execute the following steps:

[0146] Searching the target data node corresponding to the operation expression and the associated data node of the target data node from the portrait model;

[0147] Based on the association relationship between the target data node and the associated data node, the data corresponding to the target data node and the data corresponding to the associated data node are calculated to obtain the target business data corresponding to the operation expression;

[0148] The target business data is calculated based on the operation expression to obtain the value of the business indicator of the target enterprise.

[0149] In a possible example, after analyzing the portrait model based on the target business rule to obtain the value of the business indicator of the target enterprise, the program 440 is further used to execute instructions for the following steps:

[0150] If the value of the service indicator does not meet the preset condition, obtaining configuration information of the target service based on the service indicator;

[0151] The configuration information is sent to a contact person corresponding to the target enterprise.

[0152] In a possible example, the portrait model of the target enterprise includes a sub-model of the customer group dimension. In the aspect of obtaining the configuration information of the target business based on the business indicator, the program 440 is specifically used to execute the following steps:

[0153] Obtaining values ​​of reference business indicators of similar enterprises to the target enterprise;

[0154] If the value of the reference business indicator is greater than the value of the business indicator, then the portrait model of the similar enterprise is compared with the portrait model of the target enterprise to obtain a reference data node of the target enterprise;

[0155] Determine a target service based on the reference data node;

[0156] The configuration information of the target business is obtained based on the sub-model of the customer group dimension.

[0157] In a possible example, the portrait model of the target enterprise includes a sub-model of each preset dimension in a plurality of preset dimensions. In acquiring the portrait model of the target enterprise based on the business transaction data and the basic information, the program 440 is specifically used to execute the following steps:

[0158] Acquire sub-data corresponding to the preset dimension from the business transaction data and the basic information;

[0159] Acquire a data node corresponding to the preset dimension and an association relationship between the data node and an associated node associated with the data node based on the sub-data corresponding to the preset dimension;

[0160] The data node and the associated node are connected based on the association relationship to obtain a sub-model corresponding to the preset dimension.

[0161] An embodiment of the present application also provides a computer storage medium, wherein the computer storage medium stores a computer program, which enables a computer to execute part or all of the steps of any method recorded in the method embodiment, and the computer includes an electronic device and a server.

[0162] The present application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute to implement some or all steps of any method described in the method embodiment. The computer program product can be a software installation package, and the computer includes an electronic device and a server.

[0163] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modes involved are not necessarily required by the present application.

[0164] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0165] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as at least one unit or component can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0166] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on at least one network unit. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0167] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software program mode.

[0168] If the integrated unit is implemented in the form of a software program model and sold or used as an independent product, it can be stored in a computer-readable memory. According to this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, magnetic disk or optical disk, etc., and other media that can store program codes.

[0169] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A business analysis method based on a natural language processing model, characterized in that: include: Obtain basic information and business transaction data of the target enterprise; Analyze the basic information based on a natural language processing model to obtain target business rules of the target enterprise, wherein the target business rules include an operation expression for calculating a numerical value of a business indicator; Acquire sub-data corresponding to each preset dimension in a plurality of preset dimensions from the business transaction data and the basic information, where the sub-data corresponding to the preset dimension refers to data used to measure the preset dimension; Acquire a data node corresponding to the preset dimension and an association relationship between the data node and an associated node associated with the data node based on the sub-data corresponding to the preset dimension; The data node is a data type in the sub-data corresponding to the preset dimension, the association node is another data type in the sub-data corresponding to the preset dimension, the association relationship between the data node and the association node is determined by the association relationship between the data node and the data corresponding to the association node, and the association relationship includes an upstream and downstream relationship or an operation relationship; Connecting the data node and the associated node based on the association relationship to obtain a sub-model corresponding to the preset dimension, wherein if a data node in the sub-model has an association relationship with a data node in another sub-model, the data nodes with the association relationship are connected to obtain a portrait model of the target enterprise, wherein the portrait model includes a sub-model of each preset dimension in a plurality of preset dimensions; The portrait model is analyzed based on the operation expressions included in the target business rules to obtain the numerical values ​​of the business indicators of the target enterprise.

2. The method according to claim 1, characterized in that The target business rule also includes preset conditions that the value of the business indicator needs to meet; The basic information includes basic enterprise information, basic employee information and basic business information. The basic information is analyzed based on the natural language processing model to obtain the target business rules of the target enterprise, including: Analyze the basic business information based on a natural language processing model to obtain the type of business data involved in the target enterprise; Determine the business indicator of the target enterprise and the operation expression of the business data corresponding to the business indicator based on the business data type; Analyze the basic information of the enterprise and the basic information of the employees based on the natural language processing model to obtain preset conditions corresponding to the business indicators; A target business rule of the target enterprise is generated based on the preset condition and the operation expression.

3. The method according to claim 2, characterized in that The analyzing the basic information of the enterprise and the basic information of the employees based on the natural language processing model to obtain the preset conditions corresponding to the business indicators includes: Acquire the enterprise level and / or location information of the target enterprise from the basic information of the enterprise based on the natural language processing model; Acquire the number of employees of the target enterprise and / or capability information of each employee from the basic information of the employees based on the natural language processing model; Acquire the evaluation grade of the target enterprise based on the enterprise grade and / or the location information; Acquiring evaluation values ​​of the employees based on the number of the employees and / or the ability information; A preset condition corresponding to the business indicator is obtained based on the evaluation level and the evaluation value.

4. The method according to claim 1, characterized in that The analyzing the portrait model based on the operation expression included in the target business rule to obtain the value of the business indicator of the target enterprise includes: Searching the target data node corresponding to the operation expression and the associated data node of the target data node from the portrait model; Based on the association relationship between the target data node and the associated data node, the data corresponding to the target data node and the data corresponding to the associated data node are calculated to obtain the target business data corresponding to the operation expression; The target business data is calculated based on the operation expression to obtain the value of the business indicator of the target enterprise.

5. The method according to claim 2, characterized in that: After analyzing the portrait model based on the target business rules to obtain the value of the business indicator of the target enterprise, the method further includes: If the value of the service indicator does not meet the preset condition, obtaining configuration information of the target service based on the service indicator; The configuration information is sent to a contact person corresponding to the target enterprise.

6. The method according to claim 5, characterized in that The target enterprise portrait model includes a sub-model of the customer group dimension, and the configuration information of the target business is obtained based on the business indicator, including: Obtaining values ​​of reference business indicators of similar enterprises to the target enterprise; If the value of the reference business indicator is greater than the value of the business indicator, then the portrait model of the similar enterprise is compared with the portrait model of the target enterprise to obtain a reference data node of the target enterprise; Determine a target service based on the reference data node; The configuration information of the target business is obtained based on the sub-model of the customer group dimension.

7. A business analysis device based on a natural language processing model, characterized in that: The device comprises a unit for executing the method according to any one of claims 1 to 6, the device comprising: A first acquisition unit, used to acquire basic information and business transaction data of a target enterprise; A first analysis unit, configured to analyze the basic information based on a natural language processing model to obtain a target business rule of the target enterprise; A construction unit, configured to construct a portrait model of the target enterprise based on the business transaction data and the basic information; The second analysis unit is used to analyze the portrait model based on the target business rules to obtain the numerical value of the business indicator of the target enterprise.

8. A computer device, characterized in that: The method comprises a processor, a memory, a communication interface and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the programs include instructions for executing the steps in any one of the methods of claims 1-6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which enables a computer to execute to implement the method according to any one of claims 1 to 6.

Images