Business project processing method, device, electronic device and storage medium

Abstract

The embodiments of this specification relate to the field of big data technology and can be used in the field of financial technology or other fields. Specifically, a business project processing method, device, electronic device and storage medium are disclosed, and the method includes: receiving a target requirement item of a business project; the target requirement item is used to characterize a sub-development link in the development process of the business project; extracting business key information of the target requirement item, and determining the business type to which the target requirement item belongs based on the business key information as the target business type; obtaining a product application association rule corresponding to the target business type, and the product application association rule is used to characterize the potential association relationship between each product application involved in the target business type; determining the product application associated with the target requirement item based on the product application association rule, and using the determined product application to realize the processing of the target requirement item, thereby greatly improving the efficiency of business project development.

Description

Technical Field

[0001] This specification relates to the field of big data technology and can be used in the field of financial technology or other fields. In particular, it relates to a business project processing method, device, electronic device and storage medium. Background Art

[0002] In the Internet era, in order to quickly adapt to business needs, the project development process has gradually transformed from traditional methods to agile development to meet the market requirements for rapid product launch. Usually each project consists of multiple requirements, and each requirement is jointly developed and implemented by one or more product applications.

[0003] At present, during the project development process, after the demander puts forward a demand, a task order can be issued through the system management platform. Architects and other experienced employees can split the demand items from top to bottom based on the architecture design and work experience for the project demand task order, so as to allocate the functional implementation of the demand items to one or more product applications. However, this allocation method is too dependent on human experience, and it is also prone to human errors when the workload is too large. And with the continuous acceleration of technological development, the number of project requirements is also increasing, and the application allocation of demand items has become a matter that seriously consumes labor costs. Summary of the invention

[0004] The purpose of the embodiments of this specification is to provide a business project processing method, device, electronic device and storage medium, which can greatly improve the efficiency of business system development.

[0005] This specification provides a business item processing method, device, electronic device and storage medium which are implemented in the following ways:

[0006] A business project processing method, applied to a server, the method comprising: receiving a target requirement item of a business project; wherein the target requirement item is used to characterize a sub-development link in the development process of the business project; extracting business key information of the target requirement item, and determining the business type to which the target requirement item belongs based on the business key information as the target business type; obtaining a product application association rule corresponding to the target business type, the product application association rule being used to characterize the potential association relationship between each product application involved in the target business type; and determining the product application associated with the target requirement item based on the product application association rule, and realizing the processing of the target requirement item by using the determined product application.

[0007] In some other embodiments provided by the methods described in this specification, determining the business type to which the target requirement item belongs based on the business key information includes: using a pre-built business classification model to process the business key information to obtain the business type to which the target requirement item belongs.

[0008] In some other embodiments provided by the methods described in this specification, the business classification model is constructed in the following manner: extracting requirements, business key information of the requirements and the business types to which the requirements belong from the project data of the developed business projects; for any requirement item, constructing an input vector of the corresponding requirement item using the business key information of the requirement item, and using the business type to which the requirement item belongs as a label for the corresponding requirement item; using the input vector and label of the requirement item as samples to obtain a sample set; and constructing a business classification model using the sample set.

[0009] In some other embodiments provided by the methods described in this specification, the sample set is processed using a naive Bayes classification algorithm to obtain a business classification model.

[0010] In some other embodiments provided by the method described in this specification, the method also includes: extracting demand items, business types to which the demand items belong, and product applications used to implement the corresponding demand items from project data of developed business projects as a data source; extracting product applications involved in any business type from the data source to obtain a product application set corresponding to the corresponding business type; for any business type, extracting potential associations between product applications in the product application set corresponding to the business type to obtain product application association rules for the corresponding business type.

[0011] In some other embodiments provided by the methods described in this specification, an Apriori algorithm is used to extract potential associations between product applications in a product application set corresponding to the business type.

[0012] In some other embodiments provided by the method described in this specification, the use of the Apriori algorithm to extract the potential association relationship between each product application in the product application set corresponding to the business type includes: extracting frequent item sets of the product application set under a k-item set; wherein the k-item set refers to a set containing k product applications in the product application set; the initial value of k is 1, k is a positive integer less than or equal to n-1, and n is the total number of product applications in the product application set; based on the frequent item sets under the k-item set, constructing a k+1 item set of the product application set, and extracting frequent item sets of the k+1 item set; executing the above iterative steps until the value of k is equal to n-1, and outputting the frequent item sets of the product application set under each item number; filtering out frequent item sets whose confidence is greater than a confidence parameter from the frequent item sets under the each item number; and determining the potential association relationship between each product application in the product application set based on the filtered frequent item sets.

[0013] On the other hand, an embodiment of the present specification also provides a business project processing device, which includes: a receiving module, used to receive a target requirement item of a business project; wherein the target requirement item is used to characterize a sub-development link in the development process of the business project; an extraction module, used to extract business-critical information of the target requirement item, so as to determine the business type to which the target requirement item belongs based on the business-critical information as the target business type; an association rule acquisition module, used to obtain a product application association rule corresponding to the target business type, wherein the product application association rule is used to characterize the potential association relationship between the product applications involved in the target business type; an association application determination module, used to determine the product application associated with the target requirement item based on the product application association rule, so as to realize the processing of the target requirement item using the determined product application.

[0014] In some other embodiments provided by the device described in this specification, the device also includes: a data source extraction module, which is used to extract requirement items, business types to which the requirement items belong, and product applications used to implement the corresponding requirement items from project data of developed business projects as a data source; an application set extraction module, which is used to extract product applications involved in any business type from the data source to obtain a product application set corresponding to the corresponding business type; an association rule extraction module, which is used to extract, for any business type, potential association relationships between product applications in the product application set corresponding to the business type to obtain product application association rules for the corresponding business type.

[0015] On the other hand, an embodiment of the present specification also provides an electronic device, which includes at least one processor and a memory for storing processor executable instructions, and when the instructions are executed by the processor, the steps of the method described in any one or more of the above embodiments are implemented.

[0016] On the other hand, an embodiment of the present specification further provides a computer-readable storage medium having computer instructions stored thereon, and the instructions, when executed, implement the steps of the method described in any one or more of the above embodiments.

[0017] The business project processing method, device, electronic device and storage medium provided in one or more embodiments of the present specification pre-extract product applications that may be involved in a specified business type, and extract the potential association relationship between the product applications involved in the specified business type. During the actual project development process, the server can analyze the target project requirements to determine the target business type involved in the target project requirements, and then determine the product applications associated with the target project requirements based on the potential association relationship between the product applications under the target business type, thereby greatly improving the efficiency and accuracy of determining the product applications associated with the project requirements, reducing the cost of manpower screening, and greatly improving the efficiency of business project development. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of this specification or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art description. Obviously, the drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. In the drawings:

[0019] Figure 1 A schematic diagram of the module structure of a business item processing device in an embodiment provided in this specification;

[0020] Figure 2 A schematic diagram of the module structure of a business item processing device in an embodiment provided in this specification;

[0021] Figure 3 A schematic diagram of the module structure of a business project processing system in an embodiment provided in this specification;

[0022] Figure 4 A schematic diagram of the module structure of a data preprocessing device in an embodiment provided in this specification;

[0023] Figure 5 A schematic diagram of the module structure of an association mining device in an embodiment provided in this specification;

[0024] Figure 6 A schematic diagram of the module structure of a division of labor generation device in an embodiment provided in this specification. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in one or more embodiments of this specification will be clearly and completely described below in conjunction with the drawings in one or more embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of the specification, not all of the embodiments. Based on one or more embodiments of the specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the embodiments of this specification.

[0026] Figure 1 This is a flowchart of an embodiment of the business project processing method provided in this specification. Figure 1 As shown, the embodiment of this specification also provides a business item processing method, which can be applied to a server. Accordingly, the method can include the following steps.

[0027] S102: Receive target requirement items of a business project; wherein the target requirement items are used to represent sub-development links in the development process of the business project.

[0028] The business project may refer to the process of business system development, maintenance and improvement. Enterprises can set the process of business system development, maintenance and improvement as a series of system development projects according to their own needs to facilitate resource allocation and management. The processing content included in any business project can be set according to needs.

[0029] Business projects can be decomposed and processed in advance according to needs. For example, the processing of business projects can be divided according to the functions and data processing logic that the business projects need to achieve, and a series of project units can be obtained. The project unit can be described as a requirement item. Accordingly, a requirement item can refer to any sub-development link in the business project development process.

[0030] The functions and data processing logic required to be implemented by the requirement items can be configured as needed. For example, during the development of a business project, each demander can create a new requirement item on the system management platform for the business project development, and can also configure the requirement description information of the requirement item. The requirement description information may include the targeted business information, the functions required to be implemented, the standards required to be achieved, etc. After filling in, the demander can publish the task allocation instructions corresponding to the requirement items through the system management platform. So that the server determines the product application for implementing the requirement items based on the instructions. The requirement items to be assigned tasks can be used as target requirement items.

[0031] S104: Extracting business-critical information of the target demand item, and determining the business type to which the target demand item belongs based on the business-critical information as the target business type.

[0032] The server can obtain the requirement description information of the target requirement item from the task assignment instruction of the system management platform, and extract business key information from the requirement description information. The requirement description information may contain multiple types of information, such as targeted business information, functions to be implemented, standards to be achieved, etc. There is a lot of noise information, and it is difficult to accurately determine the business type to which the target requirement item belongs by directly using the requirement description information. In some embodiments, the requirement description information can be processed in advance to extract keywords that can characterize the business type as business key information, and then determine the business type to which the target requirement item belongs based on the business key information, which can greatly improve the accuracy of business type determination.

[0033] For example, the CRF algorithm can be used to segment the demand description information, and a value set {B, E, M, S} is set to calculate the labeling probability between words, where the value set {B, E, M, S} is used to represent the word position information of the word, B is the word start position, M is the word middle position, E is the word end information, and S is a single word. Set the vector F(y, x) and the weight vector w, observe the sequence x, and set the recursive function Calculate and output the set y as the optimal path output, where And use the FudanNLP toolkit to annotate parts of speech, annotate nouns, verbs and other parts of speech, filter out special symbols, adjectives, auxiliary words and other useless words, so as to facilitate the dimensionality reduction of the word vector model. Using the above method, the initial keywords in the demand description information can be extracted. After that, professional vocabulary can be further identified in combination with banking vocabulary, and keywords used to characterize business information can be filtered out from the initial keywords to form business key information, so as to determine the business type to which the target demand item belongs based on the business key information as the target business type.

[0034] In some embodiments, the business key information can be processed using a pre-built business classification model to obtain the business type to which the target demand item belongs. By pre-building a classification model to determine the corresponding business type of the target demand item, the accuracy and efficiency of business type determination can be greatly improved.

[0035] For example, the project data of a developed project can be obtained, and the project data can include requirement item information, requirement description information involved in the requirement item, the business type to which the requirement item belongs, the product application associated with the requirement item, and so on. The project data of the developed project contains a series of information configured by business personnel during the historical project development process. Building a classification model based on this information can further improve the accuracy and stability of the classification model. The above-mentioned business key information extraction method can be used to process the requirement description information of each requirement item to obtain the business key information corresponding to the corresponding requirement item. The business key information of the requirement item can be used as input information, and the business type to which the requirement item belongs can be used as a label to construct a sample. Afterwards, the sample can be used to construct a business classification model.

[0036] For example, the sample can be trained using a naive Bayesian classification algorithm to construct the business classification model. For example, the input vector can be constructed using the business keywords corresponding to the demand items, that is, the keyword vector is used to represent the key business information. Accordingly, the key business information corresponding to the demand item can be expressed as t={t1, t2, ..., t n}, the business type is represented by c i .

[0037] For any input vector t, we can calculate whether the current vector t is classified as category ci The conditional probability p(c i |t), where the maximum probability can be used to determine the category to which it belongs as c i . Relying on Bayes' criterion, we can obtain Expanding the vector t into independent features, then p(t|c i ) = p(t1|c i )p(t2|c i )p(t3|c i )...p(t n |c i ), that is, the product of the probabilities of each term appearing in the category c i . Additionally, in the actual calculation process, since the product of probabilities is the multiplication of many very small numbers, it is prone to calculation overflow. Therefore, the ln logarithm method is used for optimization during the product calculation, and finally the value of p(c i |t) is obtained. If p(c1|t) > p(c2|t), then it is considered that the category corresponding to the t vector belongs to c1. If p(c1|t) < p(c2|t), then it is considered that the category corresponding to the t vector belongs to c2.

[0038] The above algorithm can be used to process the input vector of the sample, and the labels can be used to adjust the parameters in the algorithm to obtain the trained business classification model. Some samples can also be used as test data to iteratively train and calculate the average error rate until the error rate reaches an acceptable range, as the final business classification model.

[0039] Correspondingly, in some embodiments, the business classification model can be constructed in the following manner: extracting the requirement items, the business key information of the requirement items, and the business types to which the requirement items belong from the project data of the developed business projects; for any requirement item, the input vector of the corresponding requirement item can be constructed using the business key information of the requirement item, and the business type to which the requirement item belongs is used as the label of the corresponding requirement item; the input vector and label of the requirement item are used as samples to obtain a sample set; the sample set is used to construct a business classification model. Preferably, the naive Bayes classification algorithm can be used to process the sample set to obtain a business classification model.

[0040] The system management platform can display the business types of the target requirement items determined by the server, and business personnel can adjust the business types of the target requirement items, such as adding, modifying, deleting, etc. The classification model is constructed based on historical data and may have a certain lag in response to actual business scenario changes. By supporting manual adjustment by business personnel, the business types to which the target requirement items belong can be made more accurate, thereby improving the accuracy of subsequent business application associations.

[0041] S106: Acquire a product application association rule corresponding to the target business type, where the product application association rule is used to characterize a potential association relationship between product applications involved in the target business type.

[0042] The server can extract the requirements, the business types to which the requirements belong, and the product applications used to implement the corresponding requirements from the project data of the developed business projects in advance as the data source. The product application can refer to a set of programs that implement a certain application function. The product application can be an application APP that can be integrated in a business terminal or a user terminal, or it can refer to functional software that implements a certain function in a business system. Of course, it can also be a set of programs in other forms for implementing a specific function.

[0043] The product applications involved in any business type can be extracted from the data source to obtain the product application set corresponding to the business type, so as to extract the potential association relationship between the product applications in the product application set corresponding to the business type and obtain the product application association rules of the corresponding business type. Of course, the system management platform can also display the product applications involved in each business type to business personnel, and support business personnel to adjust the product applications involved in each business type, such as adding, modifying, and deleting product applications in the product application set of each business type. Table 1 is an example of product applications involved in business types.

[0044] Table 1

[0045] Business Type Application A {Fa,Fc,Fd} B {Fb,Fc,Fe} C {Fa,Fb,Fc,Fe} D {Fb,Fe}

[0046] Corresponding to any business type, the server may also use the Apriori algorithm to extract potential association relationships between product applications in the product application set corresponding to the business type in advance as product application association rules corresponding to the corresponding business type.

[0047] For any product application set, a product application can be taken as an item to construct the item set of the current product application set. If the item set contains k product applications, the item set can be described as a k-item set.

[0048] The support parameter N and the confidence parameter M can be pre-set, and the pre-configured support parameter N and confidence parameter M can be used to extract the potential correlation between the product applications in the product application set. The probability of each item in the item set occurring simultaneously is called the support of the item set. The probability that item B or the B sub-item set also occurs when item A or the A sub-item set occurs in the item set is called the confidence of the item set. If the support of the item set is greater than N, the item set can be considered to be a frequent item set. After the frequent item set is extracted, if the confidence of a frequent item set is greater than M, it can be considered that there is a strong correlation between the product applications in the frequent item set, and the potential correlation between the product applications in the product application set can be determined based on the frequent item set.

[0049] Generally, if an item set is an infrequent item set, then all its supersets are also infrequent. Therefore, we can first construct a k-item set with a k value of 1. By traversing each product application in the product application set, we can get n k-item sets, where n is the total number of product applications in the product application set. We can retain the k-item sets with support greater than or equal to the support parameter n as frequent item sets under the k-item set. Then, we can use the frequent item sets under the k-item set as a benchmark to construct a k+1 item set (i.e., construct an item set containing two product applications); and then extract the frequent item sets under the k+1 item set based on the support. After that, we can use the item set containing two product applications as the k-item set, and the frequent item sets under the k-item set as a benchmark to further construct a k+1 item set (i.e., construct an item set containing three product applications); and then extract the frequent item sets under the k+1 item set based on the support. And so on, until the frequent item sets under the item set containing n product applications are extracted. Table 2 is an example table of frequent item sets for product applications, showing the generation results of frequent item sets with support of 0.5 and 0.7 respectively.

[0050] Table 2

[0051]

[0052] After obtaining the frequent item sets, the server can further calculate the confidence of each frequent item set. And output the frequent item sets with confidence greater than M. The product applications in the frequent item sets screened out in the above manner have a strong association relationship, that is, when a product application in the screened frequent item sets appears, the probability of other product applications in the frequent item sets appearing at the same time is relatively high. The potential association relationship between the application products in the product application set can be determined based on the screened frequent item sets as the product application association rules of the corresponding business type.

[0053] Table 3 is an example table of product application association rules for a certain business type, showing the rule generation results with confidence levels of 0.7 and 0.6 respectively. For example, {Fa}->{Fc} means that when {Fa} product application appears, {Fc} is also more likely to appear. That is, if a requirement item is associated with a product application {Fa}, and the product application association rules of the business type involved in the requirement item include {Fa}->{Fc}, then the product application {Fc} can be used as a recommended product application, so that the product applications that may be involved in the requirement item can be quickly and accurately determined.

[0054] Table 3

[0055]

[0056] The system management platform can also display the product application association rules constructed above to business personnel, and support business personnel to adjust the product application association rules.

[0057] Based on the solutions provided by the above embodiments, in some embodiments, the server can extract requirement items, business types to which the requirement items belong, and product applications used to implement the corresponding requirement items from the project data of the developed business projects as a data source; extract the product applications involved in any business type from the data source to obtain a product application set corresponding to the corresponding business type; for any business type, extract the potential association relationship between the product applications in the product application set corresponding to the business type to obtain the product application association rules for the corresponding business type.

[0058] In some other embodiments, the server may use an Apriori algorithm to extract potential associations between product applications in a product application set corresponding to the business type.

[0059] In some other embodiments, the server extracts the frequent item sets of the product application set under the k-item set; wherein the k-item set refers to a set containing k product applications in the product application set; the initial value of k is 1, k is a positive integer less than or equal to n-1, and n is the total number of product applications in the product application set; based on the frequent item sets under the k-item set, the k+1 item set of the product application set is constructed, and the frequent item sets of the k+1 item set are extracted; the above iterative steps are performed until the value of k is equal to n-1, and the frequent item sets of the product application set under each number are output. Then, the frequent item sets with a confidence greater than the confidence parameter can be screened out from the frequent item sets under the various numbers; based on the screened frequent item sets, the potential association relationship between the product applications in the product application set is determined.

[0060] Through the above method, it is possible to more accurately determine product applications that have strong correlations in the same business scenario. Then, when determining the product applications corresponding to the requirement items, it is possible to quickly and accurately determine the product applications that the requirement items may involve based on the correlations, thereby improving the accuracy and efficiency of product application screening.

[0061] S108: Determine the product application associated with the target requirement item based on the product application association rule, so as to implement the processing of the target requirement item by using the determined product application.

[0062] The system management platform can also support business personnel to configure product applications that are most likely to be involved in each target business type corresponding to the target requirement item as designated product applications. The server can retrieve the product application association rules corresponding to each target business type, and then filter out the product applications associated with each designated product application based on the product application association rules as recommended product applications, so as to achieve the target requirement item by using the recommended product applications and designated product applications. Table 4 shows examples of product applications associated with target requirement items. Among them, the product application association rules based on the results of Table 4 are extracted using a support of 0.5 and a confidence of 0.7. The system management platform can also display the results of Table 4, and business personnel can also adjust the results and confirm them on the system management platform.

[0063] After determining the business applications associated with the requirement items, the implementation of the requirement items can be distributed to the business applications to complete the functions or processing logic requirements of the requirement items based on the business applications, thereby improving the efficiency of business project development.

[0064] Table 4

[0065]

[0066] The solution provided by the above embodiment pre-extracts product applications that may be involved in a specified business type, and extracts potential associations between the product applications involved in the specified business type. During the actual project development process, the server can analyze the target project requirements to determine the target business type involved in the target project requirements, and then determine the product applications associated with the target project requirements based on the potential associations between the product applications under the target business type, thereby greatly improving the efficiency and accuracy of determining the product applications associated with the project requirements, reducing human screening costs, and greatly improving the efficiency of business project development.

[0067] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. For details, please refer to the description of the above-mentioned related processing related embodiments, and no further description is given here.

[0068] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0069] Based on the method provided in the above embodiment, this specification also provides a business item processing device, such as Figure 2 As shown, the device may include:

[0070] The receiving module 202 may be used to receive target requirement items of a business project, wherein the target requirement items are used to represent sub-development links in the development process of the business project.

[0071] The extraction module 204 may be used to extract the business-critical information of the target requirement item, so as to determine the business type to which the target requirement item belongs based on the business-critical information as the target business type.

[0072] The association rule acquisition module 206 may be used to acquire the product application association rule corresponding to the target business type, wherein the product application association rule is used to characterize the potential association relationship between the product applications involved in the target business type.

[0073] The associated application determination module 208 may be configured to determine the product application associated with the target requirement item based on the product application association rule, so as to implement the processing of the target requirement item by using the determined product application.

[0074] In some other embodiments, the device further comprises:

[0075] The data source extraction module is used to extract the requirement items, the business types to which the requirement items belong, and the product applications used to implement the corresponding requirement items from the project data of the developed business projects as the data source.

[0076] An application set extraction module, used to extract product applications involved in any business type from the data source, and obtain a product application set corresponding to the corresponding business type;

[0077] The association rule extraction module is used to extract the potential association relationship between each product application in the product application set corresponding to any business type, and obtain the product application association rule of the corresponding business type.

[0078] It should be noted that the above-mentioned device may also include other implementations according to the description of the above-mentioned embodiment. The specific implementation methods may refer to the description of the relevant method embodiments, which will not be described one by one here.

[0079] This specification also provides a scenario example of a business project processing system. Figure 3 is the structural diagram of the system. Figure 3 As shown, the system may include a data preprocessing device, a correlation mining device and a division of labor generating device. The data preprocessing device is connected to the correlation mining device, and the correlation mining device is connected to the division of labor generating device.

[0080] Data preprocessing device: cleans and processes the original task order data set, including task orders in multiple iterations of multiple projects, cleans the data and constructs attributes, including project name, business type, business scenario, demand description, and related applications. After reconstruction, it is provided to the association mining device.

[0081] Association mining device: Use Bayesian algorithm to build a business type classification model based on demand description, and use Apriori algorithm to mine the association set between business type and product application, input data source for model construction, set support personalized parameters to control the proportion of product application item set, build algorithm model to output frequent item set, and filter frequent items by setting support and confidence parameters. Use this device to provide association rules of classification model and product application, and provide them to the division of labor generation device.

[0082] Division of labor generation device: supports entering product requirements and judging the business type of the requirements through the classification model. Then, according to the association rules between business type and product application, as well as the association rules of personalized settings, the system is jointly entered to recommend application division of labor for requirements of different business types, and supports manual modification and saving, and finally outputs the requirement task list containing product application division of labor.

[0083] Figure 4 is a diagram of a data preprocessing device, wherein the data preprocessing device 1 comprises a data acquisition unit 11, a data cleaning unit 12, an attribute construction unit 13, and a data transformation unit 14, wherein:

[0084] Data acquisition unit 11: used to import original task orders in multiple iterations of multiple projects.

[0085] Data cleaning unit 12: Filter out the task orders with normal status during the iteration process, filter out the task orders with invalid status due to incorrect division of labor, and form a cleaned data source to be processed.

[0086] Attribute construction unit 13: used to construct the cleaned data according to attributes such as project name, business type, business scenario, requirement description and related applications.

[0087] Data transformation unit 14: used to output the attribute-constructed data in a regularized manner and transform it into a modeling data source that can be modeled and identified.

[0088] Figure 5 The association mining device 2 includes a data screening unit 21, a data segmentation unit 22, a classification model unit 23, a parameter setting unit 24, a frequent item generation unit 25, and an association rule output unit 26, wherein:

[0089] Data screening unit 21: retain only the demand items, business types and product application attributes of the data source. Table 1 is an example table of association between business types and product applications, showing an example of data association formed after data screening.

[0090] Data word segmentation unit 22: used for performing word segmentation processing on the requirement description information of the requirement item to extract key business information.

[0091] Classification model unit 23: used to construct a business classification model using a naive Bayes classification algorithm.

[0092] Parameter setting unit 24: used to set support parameter N and confidence parameter M.

[0093] The frequent item generating unit 25 is used to calculate the frequent item sets of the product application set.

[0094] The association rule output unit 26 is used to filter out frequent item sets whose confidences meet the requirements from the frequent item sets, and then generate product application association rules based on the filtered frequent item sets.

[0095] Figure 6 3 is a diagram of a division of labor generating device, wherein the division of labor generating device 3 comprises a demand input unit 31, a text typesetting unit 32, a personalized setting unit 33, and a division of labor generating unit 34, wherein:

[0096] Demand entry unit 31: supports entering one or more project requirements, uses a classification model to determine the business type of the newly entered requirements, and supports manually adjusting the business type for each requirement item;

[0097] Text typesetting unit 32: supports typesetting of the generated task list, with two spaces at the beginning and a blank line at the end, for simple beautification;

[0098] Personalization setting unit 33: supports manual entry of rules, supports maintenance of one or more product applications that do not need to be reconfirmed for each existing business type, supports adding new business types, supports manual adjustment of existing discovered associated application sets, and supports text modification and saving after the task order is automatically generated.

[0099] Division of work generation unit 34: supports automatically recommending and generating multiple demand task orders that meet the conditions according to the manually input rules and the associated application discovery rules, and generates a complete demand task order after manual modification or confirmation.

[0100] It should be noted that the above-mentioned device may also include other implementation modes according to the description of the above-mentioned embodiment. The specific implementation modes may refer to the description of the relevant method embodiments, which will not be described one by one here.

[0101] This specification also provides an electronic device, which may include at least one processor and a memory for storing processor-executable instructions, and when the instructions are executed by the processor, the steps of the method described in any one or more of the above embodiments are implemented.

[0102] The memory may include a physical device for storing information, which is usually to digitize the information and then store it in a medium using electrical, magnetic or optical means. The storage medium may include: a device that uses electrical energy to store information, such as various memories, such as RAM, ROM, etc.; a device that uses magnetic energy to store information, such as a hard disk, a floppy disk, a magnetic tape, a magnetic core memory, a magnetic bubble memory, a USB flash drive; a device that uses optical means to store information, such as a CD or a DVD. Of course, there are other types of readable storage media, such as quantum memory, graphene memory, etc.

[0103] Accordingly, the present specification also provides a computer-readable storage medium on which computer instructions are stored, and when the instructions are executed, the steps of the method described in any one or more of the above embodiments are implemented.

[0104] It should be noted that the embodiments of this specification are not limited to the situations that must comply with the standard data model / template or the embodiments of this specification. Certain industry standards or slightly modified implementation plans based on the implementation described in the custom method or the embodiment can also achieve the same, equivalent or similar, or predictable implementation effects after deformation of the above-mentioned embodiments. The embodiments obtained by using these modified or deformed data acquisition, storage, judgment, processing methods, etc. can still fall within the scope of the optional implementation plans of this specification.

[0105] Each embodiment in this specification is described in a progressive manner, and the same and similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. In the description of this specification, the description of the reference terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of this specification. In this specification, the schematic representation of the above terms does not necessarily target the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, in the absence of contradiction, a person skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0106] The above description is only an embodiment of the present specification and is not intended to limit the present specification. For those skilled in the art, the present specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present specification shall be included in the scope of the claims of the present specification.

Claims

1. A business project processing method, characterized in that: Applied to a server, the method comprises: Receive target requirement items of a business project; wherein the target requirement items are used to represent sub-development links in the development process of the business project; Extracting key business information of the target demand item, and determining the business type to which the target demand item belongs based on the key business information as the target business type; Acquire a product application association rule corresponding to the target business type, wherein the product application association rule is used to characterize a potential association relationship between product applications involved in the target business type; Determine the product application associated with the target demand item based on the product application association rule, so as to implement the processing of the target demand item by using the determined product application; The determining of the business type to which the target demand item belongs based on the business key information includes: Processing the key business information using a pre-built business classification model to obtain the business type to which the target demand item belongs; The process of realizing the target requirement item by using the determined product application includes: The target requirement item is allocated to the product application associated with the target requirement item, so as to complete various functions or processing logic requirements of the target requirement item based on the product application associated with the target requirement item.

2. The method according to claim 1, characterized in that The business classification model is constructed in the following way: Extract the requirements, key business information of the requirements and the business types to which the requirements belong from the project data of the developed business projects; For any requirement item, the business key information of the requirement item is used to construct the input vector of the corresponding requirement item, and the business type of the requirement item is used as the label of the corresponding requirement item; The input vector and label of the demand item are used as samples to obtain a sample set; A business classification model is constructed using the sample set.

3. The method according to claim 2, characterized in that The sample set is processed using a naive Bayes classification algorithm to obtain a business classification model.

4. The method according to claim 1, characterized in that: The method further comprises: Extract the requirements, the business types to which the requirements belong, and the product applications used to implement the corresponding requirements from the project data of the developed business projects as data sources; Extracting product applications involved in any business type from the data source to obtain a product application set corresponding to the corresponding business type; For any business type, the potential association relationship between the product applications in the product application set corresponding to the business type is extracted to obtain the product application association rule of the corresponding business type.

5. The method according to claim 4, characterized in that The Apriori algorithm is used to extract the potential association relationship between the product applications in the product application set corresponding to the business type.

6. The method according to claim 5, characterized in that The extracting potential associations between product applications in the product application set corresponding to the business type by using the Apriori algorithm includes: Extracting frequent item sets of the product application set under the k-item set; wherein the k-item set refers to a set containing k product applications in the product application set; the initial value of k is 1, k is a positive integer less than or equal to n-1, and n is the total number of product applications in the product application set; Based on the frequent itemsets under the k itemset, construct the k+1 itemset of the product application set, and extract the frequent itemsets of the k+1 itemset; Perform iterative steps until the value of k is equal to n-1, and output the frequent item sets of the product application set under each number; Filtering out frequent item sets whose confidence is greater than a confidence parameter from the frequent item sets under the number of items; The potential association relationship between the product applications in the product application set is determined based on the filtered frequent item sets.

7. A business item processing device, characterized in that: The device comprises: A receiving module, used to receive target requirement items of a business project; wherein the target requirement items are used to represent sub-development links in the development process of the business project; An extraction module, used to extract the business key information of the target demand item, so as to determine the business type to which the target demand item belongs based on the business key information as the target business type; An association rule acquisition module, used to acquire a product application association rule corresponding to the target business type, wherein the product application association rule is used to characterize a potential association relationship between product applications involved in the target business type; An associated application determination module, used to determine the product application associated with the target demand item based on the product application association rule, so as to implement the processing of the target demand item by using the determined product application; The determining of the business type to which the target demand item belongs based on the business key information includes: Processing the key business information using a pre-built business classification model to obtain the business type to which the target demand item belongs; The process of realizing the target requirement item by using the determined product application includes: The target requirement item is allocated to the product application associated with the target requirement item, so as to complete various functions or processing logic requirements of the target requirement item based on the product application associated with the target requirement item.

8. An electronic device, characterized in that: The electronic device comprises at least one processor and a memory for storing processor executable instructions, wherein the instructions implement the steps of the method according to any one of claims 1 to 6 when executed by the processor.

9. A computer-readable storage medium having computer instructions stored thereon, characterized in that: When the instructions are executed, the steps of the method according to any one of claims 1 to 6 are implemented.

Images