CN111523322A - Requirement document quality evaluation model training method and requirement document quality evaluation method - Google Patents
Requirement document quality evaluation model training method and requirement document quality evaluation method Download PDFInfo
- Publication number
- CN111523322A CN111523322A CN202010335874.8A CN202010335874A CN111523322A CN 111523322 A CN111523322 A CN 111523322A CN 202010335874 A CN202010335874 A CN 202010335874A CN 111523322 A CN111523322 A CN 111523322A
- Authority
- CN
- China
- Prior art keywords
- document
- quality
- quality score
- demand
- evaluated
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000013441 quality evaluation Methods 0.000 title claims abstract description 90
- 238000000034 method Methods 0.000 title claims abstract description 58
- 238000012549 training Methods 0.000 title claims abstract description 37
- 238000011156 evaluation Methods 0.000 claims abstract description 48
- 238000003062 neural network model Methods 0.000 claims abstract description 11
- 230000011218 segmentation Effects 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 4
- 230000006870 function Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000005034 decoration Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000011022 operating instruction Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 235000019800 disodium phosphate Nutrition 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the application provides a demand document quality evaluation model training method and a demand document quality evaluation method. The method comprises the following steps: acquiring a sample demand document and quality scores corresponding to evaluation items included in the sample demand document; extracting characteristic words of the sample requirement document; and taking the sample demand documents, the evaluation items and the feature words as input, taking the quality scores of the sample demand documents as output, and training the deep neural network model to obtain a demand document quality evaluation model. The method comprises the steps of obtaining a first quality score of a to-be-evaluated requirement document based on a requirement document quality evaluation model, obtaining an artificial quality score of the to-be-evaluated requirement document, and determining a final quality score of the to-be-evaluated requirement document by combining the quality score obtained by the quality evaluation model with the artificial quality score.
Description
Technical Field
The application relates to the technical field of computers, in particular to a demand document quality evaluation model training method and a demand document quality evaluation method.
Background
The product requirement document is compiled by a requirement analyst based on the research and development of the functions of the software product, and has important significance for guiding the subsequent development of the software product.
In the prior art, product requirement documents are mostly evaluated manually, but due to the fact that the comprehension of the requirement documents by evaluators is different, the evaluation results given by different evaluators are likely to be different greatly, and normal evaluation of the product requirement documents is affected.
Disclosure of Invention
The present application aims to solve at least one of the above technical drawbacks. The technical scheme adopted by the application is as follows:
in a first aspect, an embodiment of the present application provides a method for training a demand document quality evaluation model, where the method includes:
acquiring a sample demand document and quality scores corresponding to evaluation items included in the sample demand document;
extracting characteristic words of the sample requirement document;
and taking the sample demand documents, the evaluation items and the feature words as input, taking the quality scores of the sample demand documents as output, and training the deep neural network model to obtain a demand document quality evaluation model.
Optionally, extracting feature words of the sample requirement document includes:
performing word segmentation on the text in the sample requirement document;
and clustering the word segmentation result to determine the characteristic words of the sample requirement document.
In a second aspect, an embodiment of the present application provides a method for evaluating quality of a demand document, where the method includes:
acquiring a demand document to be evaluated;
determining a first quality score of a demand document to be evaluated based on a pre-trained demand document quality evaluation model;
acquiring the manual quality score of the required document to be evaluated;
and determining a second quality score of the required document to be evaluated based on the first quality score and the manual quality score.
Optionally, determining a first quality score of the demand document to be evaluated based on the pre-trained demand document quality evaluation model includes:
determining the characteristic words of the required document to be evaluated;
and taking the feature words of the to-be-evaluated requirement document and the evaluation items of the evaluation requirement document as the input of a pre-trained requirement document quality evaluation model, and determining the output of the requirement document quality evaluation model as a first quality score.
Optionally, determining a second quality score of the demand document to be evaluated based on the first quality score and the manual quality score includes:
and determining a second quality score of the required document to be evaluated based on the first quality score and a first preset weight corresponding to the first quality score and based on the artificial quality score and a second preset weight corresponding to the artificial quality score.
Optionally, obtaining the manual quality score of the document to be evaluated includes:
determining a requirement type and a service type of a requirement document to be evaluated;
and determining the manual quality score of the demand document to be evaluated based on the demand type and the service type.
Optionally, the method for evaluating the quality of the requirement document further includes:
and if the difference value between the first quality score and the manual quality score exceeds a preset value, sending alarm information.
In a third aspect, an embodiment of the present application provides a training device for a demand document quality evaluation model, where the training device includes:
the acquisition module is used for acquiring the sample demand document and the quality scores corresponding to the evaluation items included in the sample demand document;
the characteristic word extraction module is used for extracting the characteristic words of the sample requirement document;
and the training module is used for taking the sample demand documents, the evaluation items and the feature words as input, taking the quality scores of the sample demand documents as output, and training the deep neural network model to obtain a demand document quality evaluation model.
Optionally, the feature word extraction module is specifically configured to:
performing word segmentation on the text in the sample requirement document;
and clustering the word segmentation result to determine the characteristic words of the sample requirement document.
In a fourth aspect, an embodiment of the present application provides a device for evaluating quality of a demand document, where the device includes:
the evaluation-to-demand document acquisition module is used for acquiring a evaluation-to-demand document;
the first quality score acquisition module is used for determining a first quality score of the required document to be evaluated based on the required document quality evaluation model;
the manual quality score acquisition module is used for acquiring the manual quality score of the required document to be evaluated;
and the quality scoring module is used for determining a second quality score of the to-be-evaluated requirement document based on the first quality score and the manual quality score.
Optionally, the first quality score obtaining module is specifically configured to:
determining the characteristic words of the required document to be evaluated;
and taking the feature words of the to-be-evaluated requirement document and the evaluation items of the evaluation requirement document as the input of a pre-trained requirement document quality evaluation model, and determining the output of the requirement document quality evaluation model as a first quality score.
Optionally, the quality scoring module is specifically configured to:
and determining a second quality score of the required document to be evaluated based on the first quality score and a first preset weight corresponding to the first quality score and based on the artificial quality score and a second preset weight corresponding to the artificial quality score.
Optionally, the manual quality score obtaining module is specifically configured to:
determining a requirement type and a service type of a requirement document to be evaluated;
and determining the manual quality score of the demand document to be evaluated based on the demand type and the service type.
Optionally, the device for evaluating quality of a requirement document further includes:
and the alarm module is used for sending alarm information when the difference value between the first quality score and the manual quality score exceeds a preset value.
In a fifth aspect, an embodiment of the present application provides an electronic device, including: a processor and a memory;
a memory for storing operating instructions;
a processor, configured to execute a training method of a requirement document quality evaluation model as shown in any implementation of the first aspect of the present application or a requirement document quality evaluation method as shown in any implementation of the second aspect of the present application by calling an operation instruction.
In a sixth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the method for training a demand document quality evaluation model shown in any implementation of the first aspect of the present application or the method for evaluating the demand document quality shown in any implementation of the second aspect of the present application.
The technical scheme provided by the embodiment of the application has the following beneficial effects:
according to the scheme provided by the embodiment of the application, the first quality score of the to-be-evaluated requirement document is obtained based on the pre-trained requirement document quality evaluation model, the manual quality score of the to-be-evaluated requirement document is obtained, the final quality score of the to-be-evaluated requirement document is determined by combining the quality score obtained by the quality evaluation model and the manual quality score, the accuracy and consistency of the requirement document evaluation can be guaranteed based on the scheme, and a foundation is effectively provided for the subsequent software product development based on the requirement document.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings used in the description of the embodiments of the present application will be briefly described below.
FIG. 1 is a schematic flowchart of a method for training a demand document quality evaluation model according to an embodiment of the present disclosure;
FIG. 2 is a flowchart illustrating a method for evaluating quality of a document according to an embodiment of the present disclosure;
FIG. 3 is a schematic structural diagram of a training apparatus for a requirement document quality evaluation model according to an embodiment of the present disclosure;
FIG. 4 is a schematic structural diagram of a demand document quality evaluation apparatus according to an embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
Reference will now be made in detail to embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are exemplary only for the purpose of explaining the present application and are not to be construed as limiting the present invention.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. As used herein, the term "and/or" includes all or any element and all combinations of one or more of the associated listed items.
To make the objects, technical solutions and advantages of the present application more clear, embodiments of the present application will be described in further detail below with reference to the accompanying drawings.
The following describes the technical solutions of the present application and how to solve the above technical problems with specific embodiments. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments. Embodiments of the present application will be described below with reference to the accompanying drawings.
Fig. 1 shows a schematic flowchart of a method for training a demand document quality evaluation model according to an embodiment of the present application, and as shown in fig. 1, the method mainly includes:
step S110: and acquiring the sample requirement document and the quality scores corresponding to the evaluation items included in the sample requirement document.
In the embodiment of the application, the demand document may include a plurality of evaluation items, such as risk analysis content, project background, business process, business rule, and the like, and in the quality evaluation, each evaluation item may be evaluated manually, and then the quality scores of each evaluation item are summarized to obtain the quality score of the demand document.
The sample requirement documents as training samples have been previously subjected to quality scoring by experts for each evaluation item of each sample requirement document.
Step S120: and extracting the characteristic words of the sample requirement document.
In the embodiment of the application, the characteristic words can be extracted from the sample requirement document, and the characteristic words can represent the content of the sample requirement document. Multiple characteristic words can exist in one sample requirement document, and the same characteristic words can exist in different sample requirement documents, so that the association between different sample requirement documents can be established based on the characteristic words.
Step S130: and taking the sample demand documents, the evaluation items and the feature words as input, taking the quality scores of the sample demand documents as output, and training the deep neural network model to obtain a demand document quality evaluation model.
In the embodiment of the application, the sample demand documents, the evaluation items of the sample demand documents and the feature words can be spliced to obtain the feature vectors which are used as the input of the deep neural network model, the quality scores of the sample demand documents are used as the output of the deep neural network model to train the deep neural network model, and therefore the demand document quality evaluation model is obtained.
The training method for the demand document quality evaluation model, provided by the embodiment of the application, can realize quality evaluation on the demand document by training the demand document quality evaluation model, obtain quality scores, can realize automatic evaluation on the demand document, and can avoid the large difference of evaluation results caused by manual evaluation.
In an optional manner of the embodiment of the present application, extracting feature words of a sample requirement document includes:
performing word segmentation on the text in the sample requirement document;
and clustering the word segmentation result to determine the characteristic words of the sample requirement document.
In the embodiment of the application, when the feature words of the sample demand document are extracted, word segmentation processing can be performed on the text in the sample demand document, clustering processing can be performed on the obtained word segmentation results, the feature words of the sample demand document are determined based on the clustering results, and for example, the central words of the clustering results can be used as the feature words.
Fig. 2 is a schematic flow chart of a method for evaluating quality of a requirement document according to an embodiment of the present disclosure, and as shown in fig. 2, the method mainly includes:
step S210: acquiring a demand document to be evaluated;
step S220: determining a first quality score of a demand document to be evaluated based on a pre-trained demand document quality evaluation model;
step S230: acquiring the manual quality score of the required document to be evaluated;
step S240: and determining a second quality score of the required document to be evaluated based on the first quality score and the manual quality score.
In the embodiment of the application, when quality evaluation is performed on a demand document to be evaluated, a first quality score can be obtained based on a demand document quality evaluation model trained by the method shown in fig. 1.
In the embodiment of the application, a second quality score can be determined based on the first quality score and the manual quality score of the document requiring evaluation, and the second quality score is used as the quality score of the document requiring evaluation.
In the embodiment of the application, the quality score obtained by the quality evaluation model is combined with the manual quality score, so that the accuracy of the quality score can be improved.
According to the method for evaluating the quality of the demand document, the first quality score of the demand document to be evaluated is obtained based on the pre-trained demand document quality evaluation model, the manual quality score of the demand document to be evaluated is obtained, the final quality score of the demand document to be evaluated is determined by combining the quality score obtained by the quality evaluation model with the manual quality score, and based on the scheme, the accuracy and consistency of the evaluation of the demand document can be guaranteed, and a foundation is effectively provided for the development of subsequent software products based on the demand document.
In an optional mode of the embodiment of the present application, determining a first quality score of a to-be-evaluated demand document based on a pre-trained demand document quality evaluation model includes:
determining the characteristic words of the required document to be evaluated;
and taking the feature words of the to-be-evaluated requirement document and the evaluation items of the evaluation requirement document as the input of a pre-trained requirement document quality evaluation model, and determining the output of the requirement document quality evaluation model as a first quality score.
In the embodiment of the application, the characteristic words can represent the content of the requirement document. When extracting the characteristic words of the requirement document, the words of the text in the requirement document can be cut, the obtained word cutting results are clustered, and the characteristic words of the requirement document are determined based on the clustering results.
In the embodiment of the application, after the feature words of the demand document are determined, the demand document, the evaluation items of the demand document and the feature words can be spliced to obtain the feature vectors which are used as the input of the deep neural network model, and the output of the demand document quality evaluation model is determined as the first quality score.
In an optional manner of the embodiment of the present application, determining a second quality score of a document to be evaluated based on the first quality score and the manual quality score includes:
and determining a second quality score of the required document to be evaluated based on the first quality score and a first preset weight corresponding to the first quality score and based on the artificial quality score and a second preset weight corresponding to the artificial quality score.
In the embodiment of the application, a first preset weight can be assigned to the first quality score, a second preset weight can be assigned to the human working medium quality score, and the second quality score can be determined by performing weighted calculation.
As one example, the second quality score may be determined by the following formula:
P＝a×P1+b×P2
the first quality score is P1, the first preset weight is a, the artificial quality score is P2, the first preset weight is b, the second quality score is P, and a + b is 1.
The first preset weight and the second preset weight may be adjusted according to actual needs, for example, the second preset weight may be set to a higher value at an initial operation stage of the requirement document quality evaluation model.
In an optional mode of the embodiment of the application, acquiring the manual quality score of the document to be evaluated includes:
determining a requirement type and a service type of a requirement document to be evaluated;
determining artificial quality scores of demand documents to be evaluated based on demand types and business types
In the embodiment of the application, the requirement type and the service type of the required document to be evaluated can be determined, the required document to be evaluated is classified according to the requirement type and the service type, and experts with corresponding experience are correspondingly equipped for evaluating the required documents to be evaluated, so that the accuracy of a manual evaluation result is ensured.
In an optional manner of the embodiment of the present application, the method further includes:
and if the difference value between the first quality score and the manual quality score exceeds a preset value, sending alarm information.
In actual use, the difference between the first quality score and the artificial quality score can be monitored, and when the difference between the first quality score and the artificial quality score exceeds a preset value, the evaluation result can be considered to be abnormal, and an expert can review the evaluation result.
Based on the same principle as the method shown in fig. 1, fig. 3 shows a schematic structural diagram of a training device of a requirement document quality evaluation model provided by an embodiment of the present application, and as shown in fig. 3, the training device 30 of the requirement document quality evaluation model may include:
an obtaining module 310, configured to obtain a sample requirement document and quality scores corresponding to evaluation items included in the sample requirement document;
the feature word extraction module 320 is used for extracting feature words of the sample requirement document;
the training module 330 is configured to take the sample requirement documents, the evaluation items, and the feature words as inputs, take the quality scores of the sample requirement documents as outputs, and train the deep neural network model to obtain a requirement document quality evaluation model.
The training device of the demand document quality evaluation model, provided by the embodiment of the application, can realize the quality evaluation of the demand document through the training of the demand document quality evaluation model, obtain the quality score, can realize the automatic evaluation of the demand document, and can avoid the large difference of evaluation results caused by manual evaluation.
Optionally, the feature word extraction module is specifically configured to:
performing word segmentation on the text in the sample requirement document;
and clustering the word segmentation result to determine the characteristic words of the sample requirement document.
It is understood that the above-described modules of the training apparatus of the demand document quality evaluation model in the present embodiment have functions of implementing the respective steps of the training method of the demand document quality evaluation model in the embodiment shown in fig. 1. The function can be realized by hardware, and can also be realized by executing corresponding software by hardware. The hardware or software includes one or more modules corresponding to the functions described above. The modules can be software and/or hardware, and each module can be implemented independently or by integrating a plurality of modules. For the functional description of each module of the training apparatus for the requirement document quality evaluation model, reference may be specifically made to the corresponding description of the training method for the requirement document quality evaluation model in the embodiment shown in fig. 1, and details are not repeated here.
Based on the same principle as the method shown in fig. 2, fig. 4 shows a schematic structural diagram of a demand document quality evaluation device provided by an embodiment of the present application, and as shown in fig. 4, the demand document quality evaluation device 40 may include:
a to-be-evaluated requirement document obtaining module 410, configured to obtain a to-be-evaluated requirement document;
the first quality score obtaining module 420 is configured to determine a first quality score of the to-be-evaluated demand document based on the demand document quality evaluation model;
the manual quality score obtaining module 430 is used for obtaining the manual quality score of the required document to be evaluated;
and the quality scoring module 440 is configured to determine a second quality score of the document to be evaluated based on the first quality score and the manual quality score.
The demand document quality evaluation device provided by the embodiment of the application acquires a first quality score of a demand document to be evaluated based on a pre-trained demand document quality evaluation model, acquires an artificial quality score of the demand document to be evaluated, and determines a final quality score of the demand document to be evaluated by combining the quality score acquired by the quality evaluation model with the artificial quality score.
Optionally, the first quality score obtaining module is specifically configured to:
determining the characteristic words of the required document to be evaluated;
and taking the feature words of the to-be-evaluated requirement document and the evaluation items of the evaluation requirement document as the input of a pre-trained requirement document quality evaluation model, and determining the output of the requirement document quality evaluation model as a first quality score.
Optionally, the quality scoring module is specifically configured to:
and determining a second quality score of the required document to be evaluated based on the first quality score and a first preset weight corresponding to the first quality score and based on the artificial quality score and a second preset weight corresponding to the artificial quality score.
Optionally, the manual quality score obtaining module is specifically configured to:
determining a requirement type and a service type of a requirement document to be evaluated;
and determining the manual quality score of the demand document to be evaluated based on the demand type and the service type.
Optionally, the device for evaluating quality of a requirement document further includes:
and the alarm module is used for sending alarm information when the difference value between the first quality score and the manual quality score exceeds a preset value.
It is understood that the above-described modules of the demand document quality evaluation apparatus in the present embodiment have functions of implementing the respective steps of the demand document quality evaluation method in the embodiment shown in fig. 2. The function can be realized by hardware, and can also be realized by executing corresponding software by hardware. The hardware or software includes one or more modules corresponding to the functions described above. The modules can be software and/or hardware, and each module can be implemented independently or by integrating a plurality of modules. For the functional description of each module of the requirement document quality evaluation apparatus, reference may be specifically made to the corresponding description of the requirement document quality evaluation method in the embodiment shown in fig. 2, and details are not repeated here.
The embodiment of the application provides an electronic device, which comprises a processor and a memory;
a memory for storing operating instructions;
the processor is used for executing the training method of the demand document quality evaluation model or the demand document quality evaluation method provided in any embodiment of the application by calling the operation instruction.
As an example, fig. 5 shows a schematic structural diagram of an electronic device to which an embodiment of the present application is applicable, and as shown in fig. 5, the electronic device 2000 includes: a processor 2001 and a memory 2003. Wherein the processor 2001 is coupled to a memory 2003, such as via a bus 2002. Optionally, the electronic device 2000 may also include a transceiver 2004. It should be noted that the transceiver 2004 is not limited to one in practical applications, and the structure of the electronic device 2000 is not limited to the embodiment of the present application.
The processor 2001 is applied to the embodiment of the present application to implement the method shown in the above method embodiment. The transceiver 2004 may include a receiver and a transmitter, and the transceiver 2004 is applied to the embodiments of the present application to implement the functions of the electronic device of the embodiments of the present application to communicate with other devices when executed.
The Processor 2001 may be a CPU (Central Processing Unit), general Processor, DSP (Digital Signal Processor), ASIC (Application specific integrated Circuit), FPGA (Field Programmable Gate Array) or other Programmable logic device, transistor logic device, hardware component, or any combination thereof. Which may implement or perform the various illustrative logical blocks, modules, and circuits described in connection with the disclosure. The processor 2001 may also be a combination of computing functions, e.g., comprising one or more microprocessors, DSPs and microprocessors, and the like.
The Memory 2003 may be a ROM (Read Only Memory) or other type of static storage device that can store static information and instructions, a RAM (Random Access Memory) or other type of dynamic storage device that can store information and instructions, an EEPROM (Electrically erasable programmable Read Only Memory), a CD-ROM (Compact disk Read Only Memory) or other optical disk storage, optical disk storage (including Compact disk, laser disk, optical disk, digital versatile disk, blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited to these.
Optionally, the memory 2003 is used for storing application program code for performing the disclosed aspects, and is controlled in execution by the processor 2001. The processor 2001 is configured to execute the application program code stored in the memory 2003 to implement the method for training the requirement document quality evaluation model or the method for evaluating the requirement document quality provided in any of the embodiments of the present application.
The electronic device provided by the embodiment of the application is applicable to any embodiment of the method, and is not described herein again.
Compared with the prior art, the electronic equipment has the advantages that the first quality score of the to-be-evaluated requirement document is obtained based on the pre-trained requirement document quality evaluation model, the manual quality score of the to-be-evaluated requirement document is obtained, the final quality score of the to-be-evaluated requirement document is determined by combining the quality score obtained by the quality evaluation model and the manual quality score, accuracy and consistency of evaluation of the requirement document can be guaranteed based on the scheme, and a foundation is effectively provided for subsequent software product development based on the requirement document.
The embodiment of the application provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the computer program implements the method for training the demand document quality evaluation model or the method for evaluating the demand document quality shown in the above method embodiment.
The computer-readable storage medium provided in the embodiments of the present application is applicable to any of the embodiments of the foregoing method, and is not described herein again.
Compared with the prior art, the method and the device have the advantages that the first quality score of the to-be-evaluated requirement document is obtained based on the pre-trained requirement document quality evaluation model, the manual quality score of the to-be-evaluated requirement document is obtained, the final quality score of the to-be-evaluated requirement document is determined by combining the quality score obtained by the quality evaluation model and the manual quality score, accuracy and consistency of requirement document evaluation can be guaranteed based on the scheme, and a foundation is effectively provided for subsequent software product development based on the requirement document.
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and may be performed in other orders unless explicitly stated herein. Moreover, at least a portion of the steps in the flow chart of the figure may include multiple sub-steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, which are not necessarily performed in sequence, but may be performed alternately or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
The foregoing is only a partial embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (11)
1. A training method for a demand document quality evaluation model is characterized by comprising the following steps:
acquiring a sample demand document and quality scores corresponding to evaluation items included in the sample demand document;
extracting feature words of the sample requirement document;
and taking the sample demand document, the evaluation item and the feature word as input, taking the quality score of the sample demand document as output, and training a deep neural network model to obtain a demand document quality evaluation model.
2. The method of claim 1, wherein the extracting the feature words of the sample requirement document comprises:
performing word segmentation on the text in the sample requirement document;
and clustering the word segmentation result, and determining the characteristic words of the sample requirement document.
3. A method for evaluating the quality of a demand document is characterized by comprising the following steps:
acquiring a demand document to be evaluated;
determining a first quality score of the to-be-evaluated demand document based on a pre-trained demand document quality evaluation model;
acquiring the manual quality score of the document to be evaluated;
and determining a second quality score of the to-be-evaluated requirement document based on the first quality score and the manual quality score.
4. The method of claim 3, wherein determining a first quality score for the desired document to be evaluated based on a pre-trained desired document quality evaluation model comprises:
determining the characteristic words of the document to be evaluated;
and taking the feature words of the to-be-evaluated requirement document and the evaluation items of the evaluation requirement document as the input of a pre-trained requirement document quality evaluation model, and determining the output of the requirement document quality evaluation model as a first quality score.
5. The method according to claim 3 or 4, wherein the determining a second quality score of the to-be-evaluated requirement document based on the first quality score and the manual quality score comprises:
and determining a second quality score of the required document to be evaluated based on the first quality score and a first preset weight corresponding to the first quality score and based on the artificial quality score and a second preset weight corresponding to the artificial quality score.
6. The method according to claim 3 or 4, wherein the obtaining of the manual quality score of the document requiring evaluation comprises:
determining the demand type and the service type of the demand document to be evaluated;
and determining the manual quality score of the demand document to be evaluated based on the demand type and the service type.
7. The method of claim 3 or 4, further comprising:
and if the difference value between the first quality score and the manual quality score exceeds a preset value, sending alarm information.
8. A training device for a demand document quality evaluation model is characterized by comprising:
the system comprises an acquisition module, a quality evaluation module and a quality evaluation module, wherein the acquisition module is used for acquiring a sample demand document and quality scores corresponding to evaluation items included in the sample demand document;
the characteristic word extraction module is used for extracting the characteristic words of the sample requirement document;
and the training module is used for taking the sample requirement document, the evaluation item and the feature word as input, taking the quality score of the sample requirement document as output, and training the deep neural network model to obtain a requirement document quality evaluation model.
9. A demand document quality evaluation apparatus, characterized by comprising:
the evaluation-to-be-evaluated document acquisition module is used for acquiring a demand document to be evaluated;
the first score acquisition module is used for determining a first quality score of the to-be-evaluated required document based on a pre-trained required document quality evaluation model;
the manual grade acquisition module is used for acquiring the manual quality grade of the document to be evaluated;
and the scoring module is used for determining a second quality score of the to-be-evaluated requirement document based on the first quality score and the manual quality score.
10. An electronic device comprising a processor and a memory;
the memory is used for storing operation instructions;
the processor is used for executing the method of any one of claims 1-7 by calling the operation instruction.
11. A computer-readable storage medium, characterized in that the storage medium has stored thereon a computer program which, when being executed by a processor, carries out the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010335874.8A CN111523322A (en) | 2020-04-25 | 2020-04-25 | Requirement document quality evaluation model training method and requirement document quality evaluation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010335874.8A CN111523322A (en) | 2020-04-25 | 2020-04-25 | Requirement document quality evaluation model training method and requirement document quality evaluation method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111523322A true CN111523322A (en) | 2020-08-11 |
Family
ID=71904140
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010335874.8A Pending CN111523322A (en) | 2020-04-25 | 2020-04-25 | Requirement document quality evaluation model training method and requirement document quality evaluation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111523322A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112579729A (en) * | 2020-12-25 | 2021-03-30 | 百度(中国)有限公司 | Training method and device for document quality evaluation model, electronic equipment and medium |
| CN114625340A (en) * | 2022-05-11 | 2022-06-14 | 深圳市商用管理软件有限公司 | Commercial software research and development method, device, equipment and medium based on demand analysis |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105427204A (en) * | 2015-12-18 | 2016-03-23 | 重庆市科学技术研究院 | Service platform system of technology transfer and entrepreneurship incubation |
| CN107977798A (en) * | 2017-12-21 | 2018-05-01 | 中国计量大学 | A kind of risk evaluating method of e-commerce product quality |
| CN108363687A (en) * | 2018-01-16 | 2018-08-03 | 深圳市脑洞科技有限公司 | Subjective item scores and its construction method, electronic equipment and the storage medium of model |
| CN109829155A (en) * | 2019-01-18 | 2019-05-31 | 平安科技（深圳）有限公司 | Determination method, automatic scoring method, apparatus, equipment and the medium of keyword |
| CN110675017A (en) * | 2019-08-13 | 2020-01-10 | 平安科技（深圳）有限公司 | Performance evaluation method and device based on artificial intelligence |
| CN111061870A (en) * | 2019-11-25 | 2020-04-24 | 三角兽（北京）科技有限公司 | Article quality evaluation method and device |
-
2020
- 2020-04-25 CN CN202010335874.8A patent/CN111523322A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105427204A (en) * | 2015-12-18 | 2016-03-23 | 重庆市科学技术研究院 | Service platform system of technology transfer and entrepreneurship incubation |
| CN107977798A (en) * | 2017-12-21 | 2018-05-01 | 中国计量大学 | A kind of risk evaluating method of e-commerce product quality |
| CN108363687A (en) * | 2018-01-16 | 2018-08-03 | 深圳市脑洞科技有限公司 | Subjective item scores and its construction method, electronic equipment and the storage medium of model |
| CN109829155A (en) * | 2019-01-18 | 2019-05-31 | 平安科技（深圳）有限公司 | Determination method, automatic scoring method, apparatus, equipment and the medium of keyword |
| CN110675017A (en) * | 2019-08-13 | 2020-01-10 | 平安科技（深圳）有限公司 | Performance evaluation method and device based on artificial intelligence |
| CN111061870A (en) * | 2019-11-25 | 2020-04-24 | 三角兽（北京）科技有限公司 | Article quality evaluation method and device |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112579729A (en) * | 2020-12-25 | 2021-03-30 | 百度(中国)有限公司 | Training method and device for document quality evaluation model, electronic equipment and medium |
| CN112579729B (en) * | 2020-12-25 | 2024-05-21 | 百度(中国)有限公司 | Training method and device for document quality evaluation model, electronic equipment and medium |
| CN114625340A (en) * | 2022-05-11 | 2022-06-14 | 深圳市商用管理软件有限公司 | Commercial software research and development method, device, equipment and medium based on demand analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111695352A (en) | Grading method and device based on semantic analysis, terminal equipment and storage medium | |
| CN107423278B (en) | Evaluation element identification method, device and system | |
| CN110858269B (en) | Fact description text prediction method and device | |
| CN110807314A (en) | Text emotion analysis model training method, device and equipment and readable storage medium | |
| CN111382248B (en) | Question replying method and device, storage medium and terminal equipment | |
| CN113360711B (en) | Model training and executing method, device, equipment and medium for video understanding task | |
| CN111611386B (en) | Text classification method and device | |
| CN111523322A (en) | Requirement document quality evaluation model training method and requirement document quality evaluation method | |
| CN112100374A (en) | Text clustering method and device, electronic equipment and storage medium | |
| CN114036283A (en) | Text matching method, device, equipment and readable storage medium | |
| CN112579781A (en) | Text classification method and device, electronic equipment and medium | |
| CN115080745A (en) | Multi-scene text classification method, device, equipment and medium based on artificial intelligence | |
| CN113836297B (en) | Training method and device for text emotion analysis model | |
| CN115758245A (en) | Multi-mode data classification method, device, equipment and storage medium | |
| CN115774784A (en) | Text object identification method and device | |
| CN115278757A (en) | Method and device for detecting abnormal data and electronic equipment | |
| CN114970666A (en) | Spoken language processing method and device, electronic equipment and storage medium | |
| CN114724144A (en) | Text recognition method, model training method, device, equipment and medium | |
| CN113515591A (en) | Text bad information identification method and device, electronic equipment and storage medium | |
| CN114091458A (en) | Entity identification method and system based on model fusion | |
| CN113469176A (en) | Target detection model training method, target detection method and related equipment thereof | |
| CN113887300A (en) | Method and device for detecting target, human face and human face key point and storage medium | |
| CN111522750A (en) | Method and system for processing function test problem | |
| CN118227768B (en) | Visual question-answering method and device based on artificial intelligence | |
| CN111488738A (en) | Illegal information identification method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200811 |