Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments of the present application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
It should be noted that the method and the device for generating the financial demand item disclosed by the application can be used in the technical field of finance, and can also be used in any field except the technical field of finance, and the application field of the method and the device for generating the financial demand item disclosed by the application is not limited.
Aiming at the problems that the existing financial demand item generation mode cannot meet the requirements of financial demand item generation efficiency and the like on the basis of guaranteeing individuality of financial demand items, namely, in the process of outputting demand items, no method capable of automatically generating demand items without manpower is not needed, how to find a solution capable of automatically inducing generation of demand items from known problems is a technical problem to be solved in the field, the embodiment of the application provides a financial demand item generation method, which extracts keywords for generating financial demand items from a problem data set of segmented words based on a preset financial vocabulary set to obtain a target problem data set composed of each keyword, wherein the problem data set comprises test problems in a plurality of iterative processes corresponding to each development item, clusters each test problem in the target problem data set to obtain a corresponding keyword set, inputs the keyword set into a preset financial demand item text template to generate corresponding financial demand items, extracts keywords for generating financial demand items based on the preset financial vocabulary set in the segmented words in the data set, extracts keywords from the keyword set to be used for generating the financial demand items, and the keyword set is applicable to the target problem data set can be accurately clustered, the test problem data set can be more accurately processed by the target problem data set, and the target problem data set can be more accurately clustered, the target problem data set can be more accurately processed, and the target problem data set can be more accurately, by inputting the keyword word set into a preset text template of the financial demand item, individuation, accuracy and reliability of generating the financial demand item can be effectively improved, the automation degree and efficiency of the financial demand item generating process can be effectively improved, and further, the efficiency and reliability of online and optimizing financial software products according to the financial demand item are improved, and user experience of financial software product developers is effectively improved.
In one or more embodiments of the application, the conditional random field CRF (Conditional Random Fields) algorithm is a conditional probability distribution model of another set of output sequences given a set of input sequences, and is widely used in natural language processing.
In one or more embodiments of the application, fudanNLP kits are kits developed for chinese natural language processing, and also contain machine learning algorithms and datasets for accomplishing these tasks. The method comprises the functions of Chinese word segmentation, part-of-speech tagging, named entity recognition, dependency syntactic analysis, keyword extraction, time phrase recognition, text classification, news clustering, hierarchical classification, online learning and the like.
In one or more embodiments of the present application, an LP (Layer-Partition) clustering algorithm is based on the idea of partitioning and hierarchical clustering, and each time a cluster distance is calculated, the current optimal solution is found depending on the last calculation result, so that similarity among all clusters is avoided and the overall clustering speed is improved.
Based on the foregoing, the present application further provides a financial demand item generating device for implementing the financial demand item generating method provided in one or more embodiments of the present application, where the financial demand item generating device may be a server, see fig. 1, and the financial demand item generating device may be connected with each client device by itself or through a third party server or the like in a sequential communication manner, and the financial demand item generating device may receive a financial demand item generating request sent by the client device, extract keywords for generating a financial demand item in a segmented question data set based on a preset vocabulary set to obtain a target question data set composed of each keyword, where the question data set includes test questions in a plurality of iterative processes corresponding to each development item, cluster each test question in the target question data set to obtain a corresponding keyword set, input the keyword set into a preset financial demand item text template to generate a corresponding financial demand item, extract keywords for generating a request item in the segmented question data set based on the preset vocabulary set, send the keyword set to each question data set to display the specific request item, and send the keyword to each financial demand item to a client device to display the specific demand display financial demand item, and the like.
In another practical application, the foregoing part of the financial requirement item generating device for generating the financial requirement item may be executed in a server as described above, or all operations may be completed in the client device. The selection may be specifically performed according to the processing capability of the ue and the limitation of the usage scenario of the user. The application is not limited in this regard. If all operations are completed in the ue, the ue may further include a processor for specific processing of the financial requirement item generation.
It is understood that the mobile terminal may include any mobile device capable of loading applications, such as a smart phone, a tablet electronic device, a network set top box, a portable computer, a Personal Digital Assistant (PDA), a vehicle-mounted device, a smart wearable device, etc. Wherein, intelligent wearing equipment can include intelligent glasses, intelligent wrist-watch, intelligent bracelet etc..
The mobile terminal may have a communication module (i.e. a communication unit) and may be in communication connection with a remote server, so as to implement data transmission with the server. The server may include a server on the side of the task scheduling center, and in other implementations may include a server of an intermediate platform, such as a server of a third party server platform having a communication link with the task scheduling center server. The server may include a single computer device, a server cluster formed by a plurality of servers, or a server structure of a distributed device.
Any suitable network protocol may be used between the server and the mobile terminal, including those not yet developed on the filing date of the present application. The network protocols may include, for example, TCP/IP protocol, UDP/IP protocol, HTTP protocol, HTTPS protocol, etc. Of course, the network protocol may also include, for example, RPC protocol (Remote Procedure Call Protocol ), REST protocol (Representational STATE TRANSFER) or the like used above the above-described protocol.
The following embodiments and application examples are described in detail.
In order to solve the problem that the existing financial demand item generating method cannot meet the requirement of the financial demand item generating efficiency on the basis of guaranteeing the individuality of the financial demand item, the application provides an embodiment of a financial demand item generating method, referring to fig. 2, the financial demand item generating method executed based on a financial demand item generating device specifically comprises the following contents:
and 100, extracting keywords for generating financial demand items from a segmented question data set based on a preset financial vocabulary set to obtain a target question data set composed of the keywords, wherein the question data set comprises test questions in a plurality of iterative processes corresponding to development projects.
In step 100, the financial vocabulary set may be pre-stored in a database local to the financial demand item generating device or accessible to the financial demand item generating device, and the financial vocabulary set is used for storing preset financial vocabularies such as banking professional vocabularies, which may be specifically pre-input by the user into the database local to the financial demand item generating device or accessible to the financial demand item generating device for storage. In one or more embodiments of the present application, the problem data set includes a plurality of iterative processes corresponding to each development project, where the problem data set is used to store a unique identifier of a test problem and a correspondence between test problem contents in the plurality of iterative processes corresponding to each development project.
The unique identification of each test question stored in the question data set is the complete test question content before the question data set is word segmented, and the test question content corresponding to the unique identification of each test question stored in the question data set is the content composed of each word divided (e.g. separated by punctuation) after the question data set is word segmented.
After the keyword is extracted in the question dataset, the content of the test question corresponding to the unique identification of each test question stored in the question dataset is a content composed of each financial vocabulary (i.e., keyword), and the question dataset is confirmed as the target question dataset requiring the clustering process of step 200 at this time. That is, the target question data set is still used to store the correspondence between the unique identifiers of the test questions and the test question contents in the multiple iterative processes corresponding to the development projects, but the test question contents at this time are not complete test question contents or words after word segmentation, but are all financial words related in the original complete test question contents.
And 200, clustering each test question in the target question data set to obtain a corresponding keyword question word set.
In step 200, clustering the test questions in the target question data set means that each test question in the target question data set consisting of each financial vocabulary is clustered to improve accuracy of finding similar test questions in the target question data set.
In one or more embodiments of the present application, the keyword vocabulary set is also used to store the correspondence between the unique identifiers of the test questions and the test question contents in a plurality of iterative processes corresponding to each development project, where the test question contents are contents composed of each financial vocabulary (i.e., keywords), and the number of unique identifiers of the test questions is significantly less than the number of unique identifiers of the test questions in the target question data set, because similar test questions are clustered in step 200, so that the total number of unique identifiers of corresponding test questions is correspondingly less.
And 300, inputting the keyword sets into a preset financial requirement item text template to generate corresponding financial requirement items.
In step 300, a text template of the financial requirement item can be set, and the manual modification of the requirement party is supported, and the complete requirement item output is completed by assembling the keyword set to output the corresponding requirement item description.
As can be seen from the above description, according to the method for generating a financial demand item provided by the embodiment of the present application, by extracting keywords for generating a financial demand item from a segmented problem dataset based on a preset financial vocabulary set, the target problem dataset can be specially adapted to the financial industry on the basis of effectively reducing the data volume of the segmented problem dataset, and further the reliability, accuracy and applicability of the subsequent clustering process on the target problem dataset can be effectively improved; the method comprises the steps of clustering all test questions in a target question data set to obtain a corresponding key question word set, effectively improving accuracy, automation degree and intelligence degree of finding similar test questions in the target question data set, inputting the key question word set into a preset financial demand item text template, effectively improving individuation, accuracy and reliability of generating financial demand items, effectively improving automation degree and efficiency of a financial demand item generation process, further improving efficiency and reliability of online and optimizing financial software products according to the financial demand items, and effectively improving user experience of financial software product developers.
In order to enable the target problem data set to be specially adapted to the financial industry, in one embodiment of the financial requirement item generating method provided by the present application, referring to fig. 3, the following is specifically included before step 100 of the financial requirement item generating method:
Step 010, obtaining test questions in a plurality of iterative processes corresponding to each development project, and generating corresponding question data sets.
In step 010, the test problems in the multiple iteration processes of the multiple items are imported, and then the usability problems with incomplete modification in the iteration process are screened out, and the cleaned data source to be processed, namely the initial problem data set, is formed.
Step 020, preprocessing the problem data set.
Step 030, performing word segmentation on the preprocessed problem data set based on a preset conditional random field CRF algorithm to obtain a segmented problem data set.
Specifically, basic Chinese word segmentation is performed by using a CRF algorithm, a value set { B, E, M, S } is established for calculating labeling probability between words, a vector F (x, y) and a weight vector w are set, a sequence x is observed, and a recursive function is setCalculating, outputting a y set as an optimal path output, whereinAnd recognizing professional vocabularies by combining banking vocabularies, and screening out keywords which can be used for generating banking demand items.
As can be seen from the above description, according to the financial demand item generating method provided by the embodiment of the present application, by performing word segmentation processing on the preprocessed problem dataset based on the preset conditional random field CRF algorithm, an accurate and effective data basis can be provided for extracting keywords for generating financial demand items in the segmented problem dataset, so that the target problem dataset can be specially applied to the financial industry on the basis of effectively reducing the data volume of the segmented problem dataset, and further the reliability, accuracy and applicability of the clustering processing on the target problem dataset can be effectively improved.
In order to improve the effectiveness and efficiency of data preprocessing, in one embodiment of the method for generating a financial demand item provided in the present application, referring to fig. 4, step 020 of the method for generating a financial demand item specifically includes the following steps:
and 021, cleaning the data of the problem data set.
And step 022, formatting the problem data set after data cleaning so that the problem data set contains the unique identification of each test problem and the corresponding relation between the content of the test problem, wherein the content of the test problem is divided by each attribute, and each attribute comprises a project name, a service type, a service scene, a problem description and related application.
Specifically, the cleaned data is constructed according to the attributes such as project names, service types, service scenes, problem descriptions and related applications, the data after the attribute construction is regularly output, and the data is transformed into a modeling data source capable of modeling and identifying.
As can be seen from the above description, in the financial requirement item generating method provided by the embodiment of the present application, the problem dataset after data cleaning is formatted, so that the problem dataset includes the unique identifier of each test problem and the corresponding relationship between the content of the test problem, so that the effectiveness and efficiency of data preprocessing can be effectively improved, and further the efficiency and reliability of word segmentation processing on the preprocessed problem dataset can be effectively improved.
In order to improve the validity and application reliability of the keywords in the target question dataset, in one embodiment of the method for generating a financial demand item provided in the present application, referring to fig. 5, step 100 of the method for generating a financial demand item specifically includes the following:
step 110, a preset financial vocabulary set is called.
And 120, extracting financial words used for generating financial requirement items in the financial word set in the segmented problem data set.
And 130, labeling the parts of speech of each financial word by using a preset FudanNLP tool kit, and extracting the financial words with the parts of speech of nouns and verbs as keywords to form a target problem data set consisting of the keywords.
Specifically, the CRF algorithm is firstly utilized to carry out basic Chinese word segmentation, the algorithm is based on a sequence labeling model, the problems of Chinese ambiguity and the like generated during the description of the test problem can be well processed, professional vocabulary is combined with banking vocabulary recognition, keywords which can be used for generating banking demand items are screened out, and the part of speech is labeled by utilizing FudanNLP tool kit.
As can be seen from the above description, in the financial demand item generating method provided by the embodiment of the present application, by labeling the parts of speech of each financial vocabulary by applying the preset FudanNLP tool kit, and extracting the financial vocabularies in which the parts of speech are nouns and verbs as keywords, the validity and application reliability of the keywords in the target problem dataset can be improved on the basis of effectively reducing the data volume of the target problem dataset, and further, the individuation, accuracy and reliability of the generated financial demand item can be further improved, and the method is especially suitable for the financial industry, and the automation degree and efficiency of the financial demand item generating process can be effectively improved.
In order to improve the reliability and accuracy of clustering each test problem in the target problem data set, in one embodiment of the financial requirement item generating method provided by the present application, referring to fig. 6, the following are specifically included between step 100 and step 200 of the financial requirement item generating method:
and 140, dividing keywords corresponding to each test question in the target question data set into professional nouns, non-professional nouns, professional verbs and non-professional verbs based on a preset professional vocabulary dividing rule.
And 150, respectively carrying out weight assignment on the keywords belonging to the professional noun, the non-professional noun, the professional verb and the non-professional verb according to the sequence of the weight values from large to small.
The method comprises the steps of reserving the words belonging to the technical nouns, the non-technical nouns, the professional verbs and the non-professional verbs in each question description, constructing a keyword set, and setting weight values w1 to w4 according to the technical nouns, the non-technical verbs, the professional verbs and the non-professional verbs in sequence from large to small, wherein each test question is composed of a plurality of keywords, one question S is constructed by adopting a VSM method to construct a vector space model and can be expressed as S (1 when t1,t2,...,tn),ti appears and 0 when the question S does not appear, so that each question forms an n-dimensional space vector; but the similarity degree is difficult to be finely distinguished by adopting a calculation mode of only 0 and 1 when the vector calculation is adopted, and the text vector Sc＝S(w11,w21,w32,w43,......wnn corresponding to the test question set S is constructed by sequentially setting weight values w1 to w4 according to the professional verbs, the non-technical verbs and the non-professional verbs, and the default values are respectively 100, 50, 10 and 5.
As can be seen from the foregoing description, in the financial demand item generating method provided by the embodiment of the present application, by dividing the keywords corresponding to each test problem in the target problem data set into the professional noun, the non-professional noun, the professional verb and the non-professional verb, and performing weight assignment on the keywords belonging to the professional noun, the non-professional noun, the professional verb and the non-professional verb, an effective and reliable data basis can be provided for clustering each test problem in the target problem data set, so that reliability and accuracy for clustering each test problem in the target problem data set can be effectively improved.
In order to improve the effectiveness of the keyword sets, in one embodiment of the method for generating financial requirement items provided in the present application, referring to fig. 7, step 200 of the method for generating financial requirement items specifically includes the following:
Step 210, clustering each test question in the target question data set after keyword weight assignment based on a preset LP clustering algorithm to obtain a corresponding keyword word set.
Specifically, a Layer-Partition (LP) clustering algorithm is used for constructing an algorithm model, the clustering algorithm inherits the idea based on division and hierarchical clustering, the distance between each calculated class cluster depends on the last calculation result to find the current optimal solution, the similarity among all class clusters is avoided to be compared, the overall clustering speed is improved, a test problem set S= { S1,S2,...,Sm }, the similarity Sim among each problem is calculated (Si,Sj), the similarity calculation adopts cosine theorem for calculation, and the distance threshold is set to be alpha. Each Si is initially taken as a single cluster Ti, one Ti is selected at will, the distance between each Sj and each Ti is calculated in sequence, if the distance is smaller than alpha, Sj is classified as Ti until all the rest Sj is larger than alpha, then the last Tj which is least similar to the clustering starting point is selected as the starting point, and the distance calculating step is repeated until all clusters participate in clustering. Setting each term as the maximum keyword, and outputting a clustering result surrounding the maximum keyword.
As can be seen from the above description, in the financial demand item generating method provided by the embodiment of the present application, by clustering each test problem in the target problem dataset after keyword weight assignment based on the preset LP clustering algorithm, the effectiveness of the keyword vocabulary can be effectively improved, and the accuracy, automation degree and intelligence degree of finding similar test problems in the target problem dataset can be effectively improved.
In order to improve the convenience and efficiency of users such as research staff to learn about automatically generated financial demand items, in one embodiment of the method for generating financial demand items provided in the present application, referring to fig. 8, step 300 of the method for generating financial demand items further specifically includes the following:
and 400, outputting the financial requirement item.
Specifically, each financial requirement item generated in step 300 may be sent to a preset display device for display, or a notification message containing specific content of each financial requirement item may be sent to a client device such as a developer, etc.
As can be seen from the above description, by outputting the financial demand item, the financial demand item generating method provided by the embodiment of the present application can effectively improve convenience and efficiency of users such as research personnel learning the automatically generated financial demand item, further improve user experience of the research personnel, and further improve efficiency and reliability of online and optimizing financial software products according to the financial demand item, and effectively improve user experience of developers of the financial software products.
In order to solve the problem that the existing financial demand item generating manner cannot meet the requirement of financial demand item generating efficiency on the basis of guaranteeing the individuality of the financial demand item, the application provides an embodiment of a financial demand item generating device for executing all or part of the contents in the financial demand item generating method, referring to fig. 9, wherein the financial demand item generating device specifically comprises the following contents:
The data extraction module 10 is configured to extract keywords for generating financial demand items from a segmented question dataset based on a preset financial vocabulary set, so as to obtain a target question dataset composed of the keywords, where the question dataset includes test questions in a plurality of iterative processes corresponding to development projects;
The data clustering module 20 is configured to cluster each test problem in the target problem data set to obtain a corresponding keyword term set;
the template generating module 30 is configured to input the keyword set into a preset text template of the financial requirement item, so as to generate a corresponding financial requirement item.
The embodiment of the financial demand item generating apparatus provided by the present application may be specifically used to execute the processing flow of the embodiment of the financial demand item generating method in the above embodiment, and the functions thereof are not described herein in detail, and reference may be made to the detailed description of the above method embodiment.
As can be seen from the above description, the financial demand item generating device provided by the embodiment of the application extracts the keywords for generating the financial demand item from the segmented problem data set based on the preset financial vocabulary set, so that the target problem data set can be specially applied to the financial industry on the basis of effectively reducing the data volume of the segmented problem data set, further the reliability, accuracy and applicability of the subsequent clustering processing of the target problem data set can be effectively improved, the corresponding keyword word set is obtained by clustering each test problem in the target problem data set, the accuracy, automation degree and intelligence degree of the similar test problem in the target problem data set can be effectively improved, the individuation, accuracy and reliability of the generated financial demand item can be effectively improved, the automation degree and efficiency of the financial demand item generating process can be effectively improved, and further the online and optimizing financial software product efficiency and reliability according to the financial demand item can be effectively improved.
In order to further explain the scheme, the application example of the application provides a financial demand item generation method based on a test problem set and an LP clustering algorithm, relates to the field of product demand, and aims to solve the problem that in the field of product demand, no method for automatically generating demand items without manpower is needed in the process of outputting the demand items.
The application provides a method for automatically generating a demand item based on a test problem set, which mainly comprises the following steps:
and 1) preprocessing the test problem set by the data preprocessing device, analyzing the test problem set into a standardized problem format including project names, service types, service scenes, problem descriptions, application and the like, and providing the new data set to the cluster analysis device.
And 2) a cluster analysis device, wherein the device uses a word segmentation algorithm of a conditional random field CRF algorithm as a basic word segmentation algorithm, combines banking professional vocabularies to form a special test problem set word segmentation tool, and marks parts of speech by using FudanNLP tool packages. Compared with the traditional word segmentation mode, the method can identify the bank technical nouns, provides a part-of-speech tagging function, and can conveniently organize the keyword word sequence finally generated by the required items through part-of-speech tagging. The LP clustering algorithm is used for constructing a clustering analysis model to find out a key question word set of a similar test question scene, and inherits the thought based on division and hierarchical clustering, so that similarity among all kinds of clusters is avoided, the overall clustering speed can be improved, and the key words are conveniently provided for a demand item generating device.
And step 3) setting a special template of the demand item, supporting the manual modification of the demand party, and outputting the corresponding demand item description by assembling the keyword set to complete the complete demand item output.
Referring to fig. 10, the financial requirement item generating system for implementing the financial requirement item generating method provided by the application example of the present application specifically includes the following contents:
the system comprises a data preprocessing device, a cluster analysis device and a demand item generation device.
The data preprocessing device is connected with the cluster analysis device, and the cluster analysis device is connected with the demand item generating device.
(1) The data preprocessing device is used for cleaning and processing the original test problem data set, including test problems in a plurality of iterative processes of a plurality of items, screening out usability problems, cleaning and constructing attributes of the data, wherein the attributes comprise item names, service types, service scenes, problem descriptions, application and the like. And after the reconstruction is completed, providing the obtained product to a cluster analysis device.
(2) The cluster analysis device is used for inputting the preprocessed data sources, constructing a model by adopting a clustering algorithm, and outputting key question word sets corresponding to various business scenes. The CRF algorithm is firstly utilized to carry out basic Chinese word segmentation, the algorithm is based on a sequence labeling model, the problems of Chinese ambiguity and the like generated during the description of the test problem can be well processed, professional vocabularies are identified by combining with banking vocabularies, keywords which can be used for generating banking demand items are screened out, and the part of speech is labeled by utilizing FudanNLP tool bags. On the basis of marking parts of speech such as nouns and verbs by Chinese segmentation, the segmentation weights of the professional vocabularies and nouns in banking industry are increased, a cluster analysis model is constructed by using an LP cluster algorithm, and a key question set of similar test question scenes is found and provided for a demand item generating device.
(3) The demand item generating device is used for taking the keyword set obtained by the cluster analysis as an input data source, setting a demand item text template to automatically fill the keyword set to form a complete demand item, supporting manual modification and storage, and finally outputting the complete demand item generated based on the test problem set.
Referring to fig. 11, the data preprocessing apparatus 1 specifically includes the following:
A data acquisition unit 11, a data cleansing unit 12, an attribute construction unit 13, and a data conversion unit 14.
(1) The data acquisition unit 11 is used for importing test questions in a plurality of iterative processes of a plurality of items.
(2) And the data cleaning unit 12 is used for screening out the usability problem of incomplete modification in the iterative process and forming a cleaned data source to be processed.
(3) The attribute construction unit 13 is used for constructing the cleaned data according to the project name, the service type, the service scene, the problem description, the application related attribute and the like.
(4) The data transformation unit 14 is used for regularized output of the data after attribute construction and transforming the data into a modeling data source capable of modeling and identifying.
Examples of such test problems are shown in Table 1:
table 1 test question example table
Referring to fig. 12, the cluster analysis device 2 specifically includes:
a word segmentation unit 21, a data screening unit 22, a weight calculation unit 23, a cluster calculation unit 24 and a result output unit 25.
(1) The word segmentation unit 21 performs basic Chinese word segmentation by using CRF algorithm, establishes a value set { B, E, M, S } for calculating labeling probability between characters, sets a vector F (y, x) and a weight vector w, observes a sequence x, and sets a recursive functionCalculating, outputting a y set as an optimal path output, whereinAnd recognizing professional vocabularies by combining banking vocabularies, screening out keywords which can be used for generating banking demand items, and marking parts of speech by utilizing FudanNLP tool packages. On the basis of marking parts of speech such as nouns and verbs by Chinese segmentation, special symbols, adjectives, auxiliary words and other useless words are required to be filtered, so that dimension reduction of a word vector model is facilitated, and the keyword word sequence finally generated by the required items can be conveniently organized through part of speech marking.
(2) The data filtering unit 22 reserves the nouns belonging to the professional class, the non-professional class, the professional class verbs and the non-professional class verbs in each question description to construct a keyword set.
(3) The weight calculation unit 23, assuming that the number of terms in the keyword set is n, a certain keyword is ti, each test question is composed of a plurality of keywords, a vector space model constructed by a VSM method for one question S can be expressed as S (t1,t2,...,tn),ti is recorded as 1, and the space model is recorded as 0 when the question does not appear, so that each question forms an n-dimensional space vector, but if the similarity degree is difficult to distinguish carefully by adopting a calculation mode of 0 and 1 in vector calculation, weight values w1 to w4 are sequentially set according to the terms of the professional noun, the non-professional noun, the professional verb and the non-professional verb from large to small, and default values are respectively 100, 50, 10 and 5, so that a text vector Sc＝S(w11,w21,w32,w43,......wnn corresponding to the test question set S is constructed.
(4) The clustering calculation unit 24 uses a Layer-Partition (LP) clustering algorithm to construct an algorithm model, the clustering algorithm inherits the thought of Partition and hierarchical clustering, each time the distance between the calculated clusters depends on the last calculation result to find the current optimal solution, the similarity among all clusters is avoided, the overall clustering speed is improved, a test problem set S= { S1,S2,...,Sm }, the similarity Sim among each problem is calculated (Si,Sj), the similarity calculation adopts cosine theorem to calculate, and the distance threshold value is set to be alpha. Each Si is initially taken as a single cluster Ti, one Ti is selected at will, the distance between each Sj and each Ti is calculated in sequence, if the distance is smaller than alpha, Sj is classified as Ti until all the rest Sj is larger than alpha, then the last Tj which is least similar to the clustering starting point is selected as the starting point, and the distance calculating step is repeated until all clusters participate in clustering. Setting each term as the maximum keyword, and outputting a clustering result surrounding the maximum keyword.
(5) And the result output unit 25 is used for sending the clustering result to the text template.
Referring to fig. 13, the demand item generating apparatus 3 specifically includes:
A text template setting unit 31, a text typesetting unit 32, a personalization setting unit 33, and a demand item issuing unit 34.
(1) The text template setting unit 31 is used for presetting text templates generated by a plurality of requirement items, and filling and outputting the text templates according to the reserved templates when the requirement items are released;
(2) The character typesetting unit 32 is used for typesetting the generated demand items, firstly starting two blank boxes, and finally adding blank symbols to perform a simple beautifying function;
(3) The personalized setting unit 33 supports the functions of manually inputting new templates, modifying the existing text templates, deleting templates and the like, and supports modification and storage after the system automatically generates the requirement items.
(4) The demand item issuing unit 34 supports the generation of a complete set of demand items according to the keywords. Tables 1 and 2 show the comparison results of the original problem and the final generated demand item, and the templates ' channel class ', ' noun ', initiating ' scene class ' verb ' are used after clustering, and ' noun ' needs to support ' verb '. "auto-fill generates demand items.
Examples of demand terms for output are shown in Table 2:
Table 2 output demand item example table
According to the financial demand item generation method provided by the application example, a clustering model based on a natural language processing technology is constructed based on a test problem set generated in an item iteration process, keywords in a service scene and problem description are found, and the product demand of the next iteration item is automatically induced and generated. The advantages are as follows:
based on the original data of the test problem set, the found product defects can be collected again by saving manpower, the use value of the usability problem in the test problem is improved, and more functions are exerted in the whole project period.
Keywords in the problems can be found in a self-learning way through a clustering algorithm, and related scenes of the keywords are clustered and mined, so that the time cost of the same class can be greatly saved through the collection of the problems by manpower.
The demand items which depend on the text templates are automatically generated, so that the time for a demand party to write the demand items can be saved, and the templates can be generated by using personalized tools, so that the diversity of different demand generation is kept.
In order to solve the problem that the existing financial demand item generating mode cannot meet the requirements of financial demand item generating efficiency and the like on the basis of guaranteeing individuation of financial demand items, the application provides an embodiment of electronic equipment for realizing all or part of contents in the financial demand item generating method, wherein the electronic equipment specifically comprises the following contents:
Fig. 14 is a schematic block diagram of a system configuration of an electronic device 9600 according to an embodiment of the present application. As shown in fig. 14, the electronic device 9600 can include a central processor 9100 and a memory 9140, the memory 9140 being coupled to the central processor 9100. It is noted that this fig. 14 is exemplary, and that other types of structures may be used in addition to or in place of the structures to implement telecommunications functions or other functions.
In one embodiment, the financial demand item generation function may be integrated into the central processor. Wherein the central processor may be configured to control:
and 100, extracting keywords for generating financial demand items from a segmented question data set based on a preset financial vocabulary set to obtain a target question data set composed of the keywords, wherein the question data set comprises test questions in a plurality of iterative processes corresponding to development projects.
And 200, clustering each test question in the target question data set to obtain a corresponding keyword question word set.
And 300, inputting the keyword sets into a preset financial requirement item text template to generate corresponding financial requirement items.
From the above description, it can be seen that the electronic device provided by the embodiment of the application extracts the keywords for generating the financial demand items from the segmented problem data set based on the preset financial vocabulary set, so that the target problem data set can be specially suitable for the financial industry on the basis of effectively reducing the data volume of the segmented problem data set, further the reliability, accuracy and applicability of the subsequent clustering processing of the target problem data set can be effectively improved, the corresponding keyword word set can be obtained by clustering each test problem in the target problem data set, the accuracy, automation degree and intelligent degree of the similar test problem in the target problem data set can be effectively improved, the individuation, accuracy and reliability of the generated financial demand items can be effectively improved by inputting the keyword word set into the preset financial demand item text template, the automation degree and efficiency of the financial demand item generation process can be effectively improved, further the efficiency and reliability of online and optimizing financial software products according to the financial demand items can be improved, and the user experience of financial software products can be effectively improved.
In another embodiment, the financial demand item generating apparatus may be configured separately from the central processor 9100, for example, the financial demand item generating apparatus may be configured as a chip connected to the central processor 9100, and the financial demand item generating function is implemented by control of the central processor.
As shown in fig. 14, the electronic device 9600 may further include a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It is noted that the electronic device 9600 does not necessarily include all the components shown in fig. 14, and furthermore, the electronic device 9600 may include components not shown in fig. 14, and reference may be made to the prior art.
As shown in fig. 14, the central processor 9100, sometimes referred to as a controller or operational control, may include a microprocessor or other processor device and/or logic device, which central processor 9100 receives inputs and controls the operation of the various components of the electronic device 9600.
The memory 9140 may be, for example, one or more of a buffer, a flash memory, a hard drive, a removable media, a volatile memory, a non-volatile memory, or other suitable device. The information about failure may be stored, and a program for executing the information may be stored. And the central processor 9100 can execute the program stored in the memory 9140 to realize information storage or processing, and the like.
The input unit 9120 provides input to the central processor 9100. The input unit 9120 is, for example, a key or a touch input device. The power supply 9170 is used to provide power to the electronic device 9600. The display 9160 is used for displaying display objects such as images and characters. The display may be, for example, but not limited to, an LCD display.
The memory 9140 may be a solid state memory such as Read Only Memory (ROM), random Access Memory (RAM), SIM card, etc. But also a memory which holds information even when powered down, can be selectively erased and provided with further data, an example of which is sometimes referred to as EPROM or the like. The memory 9140 may also be some other type of device. The memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 may include an application/function storage portion 9142, the application/function storage portion 9142 storing application programs and function programs or a flow for executing operations of the electronic device 9600 by the central processor 9100.
The memory 9140 may also include a data store 9143, the data store 9143 for storing data, such as contacts, digital data, pictures, sounds, and/or any other data used by an electronic device. The driver storage portion 9144 of the memory 9140 may include various drivers of the electronic device for communication functions and/or for performing other functions of the electronic device (e.g., messaging applications, address book applications, etc.).
The communication module 9110 is a transmitter/receiver 9110 that transmits and receives signals via an antenna 9111. A communication module (transmitter/receiver) 9110 is coupled to the central processor 9100 to provide input signals and receive output signals, as in the case of conventional mobile communication terminals.
Based on different communication technologies, a plurality of communication modules 9110, such as a cellular network module, a bluetooth module, and/or a wireless local area network module, etc., may be provided in the same electronic device. The communication module (transmitter/receiver) 9110 is also coupled to a speaker 9131 and a microphone 9132 via an audio processor 9130 to provide audio output via the speaker 9131 and to receive audio input from the microphone 9132 to implement usual telecommunications functions. The audio processor 9130 can include any suitable buffers, decoders, amplifiers and so forth. In addition, the audio processor 9130 is also coupled to the central processor 9100 so that sound can be recorded locally through the microphone 9132 and sound stored locally can be played through the speaker 9131.
An embodiment of the present application also provides a computer-readable storage medium capable of implementing all steps in the financial demand item generation method in the above embodiment, the computer-readable storage medium storing thereon a computer program which, when executed by a processor, implements all steps of the financial demand item generation method in the above embodiment in which an execution subject is a server or a client, for example, the processor implements the following steps when executing the computer program:
and 100, extracting keywords for generating financial demand items from a segmented question data set based on a preset financial vocabulary set to obtain a target question data set composed of the keywords, wherein the question data set comprises test questions in a plurality of iterative processes corresponding to development projects.
And 200, clustering each test question in the target question data set to obtain a corresponding keyword question word set.
And 300, inputting the keyword sets into a preset financial requirement item text template to generate corresponding financial requirement items.
As can be seen from the above description, the computer readable storage medium provided by the embodiment of the present application extracts the keywords for generating the financial demand item from the segmented problem data set based on the preset financial vocabulary set, so that the target problem data set can be specially adapted to the financial industry on the basis of effectively reducing the data volume of the segmented problem data set, further the reliability, accuracy and applicability of the subsequent clustering processing of the target problem data set can be effectively improved, the corresponding keyword set can be obtained by clustering each test problem in the target problem data set, the accuracy, automation degree and intelligence degree of the similar test problem in the target problem data set can be effectively improved, and the individuation, accuracy and reliability of the generated financial demand item can be effectively improved by inputting the keyword set into the preset financial demand item text template, and the automation degree and efficiency of the financial demand item generating process can be effectively improved, further the online and optimizing the financial software product efficiency and reliability according to the demand item can be improved, and the financial demand item development personnel experience can be effectively improved.
It will be apparent to those skilled in the art that embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (devices), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While the principles and embodiments of the present invention have been described in detail in the foregoing application of the principles and embodiments of the present invention, the above examples are provided for the purpose of aiding in the understanding of the principles and concepts of the present invention and may be varied in many ways by those of ordinary skill in the art in light of the teachings of the present invention, and the above descriptions should not be construed as limiting the invention.