Target demand evaluation method and device, storage medium and electronic equipment

Abstract

The invention discloses a target demand evaluation method and device, a storage medium and electronic equipment. The method comprises the steps of obtaining demand data of a to-be-evaluated target demand; performing preprocessing and feature extraction processing on the demand data to obtain a demand feature vector corresponding to the target demand; the target demand is evaluated according to the demand feature vector through a target evaluation model, an evaluation result is obtained, the target evaluation model is obtained by training a deep learning model according to the sample data set, and the evaluation result at least comprises feasibility information, resource demand prediction information and risk level information of the target demand. According to the method and the device, the problem of relatively low assessment accuracy due to the fact that the demand is assessed depending on manpower in related technologies is solved.

Description

Technical Field

[0001] This application relates to the field of data analysis, and more specifically, to a method and apparatus for evaluating target requirements, a storage medium, and an electronic device. Background Technology

[0002] In today's digital age, whether it's software development projects, product development processes, or various business process optimizations, a large number of requirements need to be evaluated. Currently, the requirements evaluation methods in related technologies often rely on manual analysis, which is highly subjective, has low evaluation efficiency and accuracy, and makes it difficult to comprehensively and deeply uncover the hidden information behind the requirements.

[0003] There is currently no effective solution to the problem that relying on manual assessment of demand in related technologies results in low accuracy. Summary of the Invention

[0004] The main objective of this application is to provide a method, apparatus, storage medium, and electronic device for evaluating target requirements, in order to solve the problem that the evaluation accuracy is low when relying on manual evaluation of requirements in related technologies.

[0005] To achieve the above objectives, according to one aspect of this application, a method for evaluating target requirements is provided. The method includes: acquiring requirement data of the target requirement to be evaluated; preprocessing and extracting features from the requirement data to obtain a requirement feature vector corresponding to the target requirement; evaluating the target requirement based on the requirement feature vector using a target evaluation model to obtain an evaluation result, wherein the target evaluation model is trained on a deep learning model using a sample dataset, and the evaluation result includes at least feasibility information, resource requirement prediction information, and risk level information of the target requirement.

[0006] Furthermore, the preprocessing and feature extraction of the demand data to obtain the demand feature vector corresponding to the target demand includes: cleaning the demand data to obtain cleaned demand data; extracting features from the text data in the cleaned demand data using a natural language processing model to obtain text feature vectors; extracting features from the numerical data in the cleaned demand data to obtain numerical feature vectors; and determining the demand feature vector based on the text feature vectors and numerical feature vectors.

[0007] Furthermore, the target requirement is evaluated based on the requirement feature vector by the target evaluation model, and the evaluation result is obtained by: receiving the requirement feature vector through the input layer of the target evaluation model; performing a nonlinear transformation on the requirement feature vector through the hidden layer of the target evaluation model to obtain the transformed intermediate feature representation; and generating the evaluation result through the output layer of the target evaluation model based on the transformed intermediate feature representation.

[0008] Furthermore, after obtaining the evaluation results, the method also includes: converting the evaluation results into a visualization format and displaying the visualization format evaluation results to the target object.

[0009] Further, the target evaluation model is obtained through the following steps: obtaining a sample dataset, which includes sample requirement feature vectors and corresponding evaluation result labels; constructing an initial evaluation model based on a deep learning model, and training the initial evaluation model according to the sample dataset until the preset conditions are met, thereby obtaining the target evaluation model.

[0010] Furthermore, before obtaining the sample dataset, the method also includes: collecting data from multiple data sources to obtain sample requirement data; and performing data cleaning, data labeling, and feature extraction processing on the sample requirement data to obtain the sample dataset.

[0011] Furthermore, the initial evaluation model is trained based on the sample dataset until the preset conditions are met to obtain the target evaluation model, which includes: splitting the sample dataset into a training set, a validation set, and a test set; training the initial evaluation model based on the training set to obtain the first evaluation model; optimizing the parameters of the first evaluation model based on the validation set to obtain the second evaluation model; and optimizing the performance of the second evaluation model based on the test set until the preset conditions are met to obtain the target evaluation model.

[0012] To achieve the above objectives, according to another aspect of this application, an apparatus for evaluating target requirements is provided. The apparatus includes: a first acquisition unit for acquiring requirement data of the target requirement to be evaluated; a first processing unit for preprocessing and feature extraction of the requirement data to obtain a requirement feature vector corresponding to the target requirement; and a second processing unit for evaluating the target requirement based on the requirement feature vector using a target evaluation model to obtain an evaluation result. The target evaluation model is trained on a deep learning model using a sample dataset, and the evaluation result includes at least feasibility information, resource requirement prediction information, and risk level information of the target requirement.

[0013] Furthermore, the first processing unit includes: a first processing subunit for cleaning the demand data to obtain cleaned demand data; a second processing subunit for extracting features from the text data in the cleaned demand data using a natural language processing model to obtain text feature vectors; a third processing subunit for extracting features from the numerical data in the cleaned demand data to obtain numerical feature vectors; and a fourth processing subunit for determining demand feature vectors based on the text feature vectors and numerical feature vectors.

[0014] Furthermore, the second processing unit includes: a fifth processing subunit, used to receive the demand feature vector through the input layer of the target evaluation model; a sixth processing subunit, used to perform a nonlinear transformation on the demand feature vector through the hidden layer of the target evaluation model to obtain the transformed intermediate feature representation; and a seventh processing subunit, used to generate an evaluation result based on the transformed intermediate feature representation through the output layer of the target evaluation model.

[0015] Furthermore, the device also includes a display unit, which, after obtaining the evaluation results, converts the evaluation results into a visual format and displays the visual evaluation results to the target object.

[0016] Furthermore, the device also includes the following units for obtaining the target evaluation model through the following steps: a second acquisition unit for acquiring a sample dataset, wherein the sample dataset includes sample requirement feature vectors and corresponding evaluation result labels; and a training unit for constructing an initial evaluation model based on a deep learning model and training the initial evaluation model according to the sample dataset until preset conditions are met, thereby obtaining the target evaluation model.

[0017] Furthermore, the device also includes: a data acquisition unit, used to acquire data from multiple data sources before obtaining the sample dataset to obtain sample requirement data; and a third processing unit, used to perform data cleaning, data labeling, and feature extraction processing on the sample requirement data to obtain the sample dataset.

[0018] Furthermore, the training unit includes: a splitting subunit for splitting the sample dataset into a training set, a validation set, and a test set; a first training subunit for training the initial evaluation model based on the training set to obtain a first evaluation model; a second training subunit for optimizing the parameters of the first evaluation model based on the validation set to obtain a second evaluation model; and a third training subunit for optimizing the performance of the second evaluation model based on the test set until preset conditions are met to obtain the target evaluation model.

[0019] According to another aspect of the present invention, an electronic device is also provided, comprising: a memory storing an executable program; and a processor for running the program, wherein the program, when running, performs an evaluation method for the target requirements of any of the above-mentioned items.

[0020] According to another aspect of the present invention, a computer-readable storage medium is also provided, wherein a program is stored in the storage medium, and an evaluation method for the target requirement of any of the above is used to control the device where the storage medium is located to perform the program during runtime.

[0021] In this embodiment, the following steps are employed: acquiring the demand data of the target demand to be evaluated; preprocessing and extracting features from the demand data to obtain the demand feature vector corresponding to the target demand; evaluating the target demand based on the demand feature vector using a target evaluation model to obtain the evaluation result. The target evaluation model is trained on a deep learning model using a sample dataset, and the evaluation result includes at least feasibility information, resource demand prediction information, and risk level information of the target demand. This solves the technical problem of low accuracy in related technologies that rely on manual demand evaluation. In this solution, evaluation using a deep learning model overcomes the subjectivity of manual evaluation and provides more objective and accurate evaluation results. The model can comprehensively consider multiple dimensions of the demand, including feasibility, resource demand, and risk level, thereby providing comprehensive evaluation information and effectively improving the accuracy and efficiency of demand evaluation. Attached Figure Description

[0022] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0023] Figure 1 A hardware block diagram of a computer terminal for an evaluation method to achieve target requirements is shown.

[0024] Figure 2 This is a flowchart of the method for evaluating target requirements according to the embodiments of this application;

[0025] Figure 3 This is a schematic diagram of the architecture of the demand assessment model provided in the embodiments of this application;

[0026] Figure 4 This is a schematic diagram of the requirements assessment process provided according to an embodiment of this application;

[0027] Figure 5 This is a schematic diagram of an evaluation apparatus for target requirements provided in an embodiment of this application;

[0028] Figure 6 This is a structural block diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0029] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0030] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0031] It should be noted that the information collected in this application (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data used for analysis, etc.) are information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of this data all comply with relevant laws, regulations, and standards, necessary confidentiality measures have been taken, and they do not violate public order and good morals. Corresponding operation entry points are provided for users to choose to authorize or refuse. For example, interfaces are set up between this system and relevant users or organizations, providing users with corresponding operation entry points for them to choose to agree to or refuse automated decision results; if the user chooses to refuse, the process proceeds to the expert decision-making stage.

[0032] Example 1

[0033] According to an embodiment of this application, a method embodiment for evaluating target requirements is also provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0034] The method embodiment provided in Embodiment 1 of this application can be executed on a mobile terminal, computer terminal, or similar computing device. Figure 1A hardware block diagram of a computer terminal (or mobile device) for an evaluation method to achieve target requirements is shown. Figure 1 As shown, the computer terminal 10 (or mobile device) may include one or more processors 102 (shown as 102a, 102b, ..., 102n in the figure) 102 (processor 102 may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of a BUS bus), a network interface, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, computer terminal 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0035] It should be noted that the aforementioned one or more processors 102 and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be integrated, in whole or in part, into any other element within the computer terminal 10 (or mobile device). As involved in the embodiments of this application, the data processing circuits serve as a processor control mechanism (e.g., selection of a variable resistor termination path connected to an interface).

[0036] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the target requirement evaluation method in this embodiment. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby realizing the aforementioned target requirement evaluation method. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0037] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the computer terminal 10. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0038] The display may be a touchscreen liquid crystal display (LCD) that allows the user to interact with the user interface of the computer terminal 10 (or mobile device).

[0039] Under the aforementioned operating environment, this application provides the following: Figure 2 The method for evaluating target requirements is shown. Figure 2 This is a flowchart of a method for evaluating target requirements according to Embodiment 1 of this application. The method for evaluating target requirements includes:

[0040] Step S201: Obtain the requirement data of the target requirement to be evaluated;

[0041] Step S202: Preprocess and extract features from the demand data to obtain the demand feature vector corresponding to the target demand;

[0042] Step S203: The target requirement is evaluated based on the requirement feature vector using the target evaluation model to obtain the evaluation result. The target evaluation model is trained on a deep learning model based on a sample dataset. The evaluation result includes at least the feasibility information of the target requirement, the resource requirement prediction information, and the risk level information.

[0043] Optionally, the evaluation system first acquires the requirement data of the target requirement to be evaluated (such as software development requirements, product function requirements, business requirements, etc.), performs preprocessing and feature extraction on the requirement data to obtain the requirement feature vector corresponding to the target requirement, and then inputs it into the trained target evaluation model. The model evaluates the requirement based on the learned knowledge and outputs a vector containing multiple evaluation index values, such as the feasibility score of the requirement (e.g., 0-10 points, the higher the score, the higher the feasibility), resource requirement prediction (e.g., manpower hours, capital budget, etc.), risk level assessment (e.g., low, medium, high risk), etc.

[0044] In summary, this solution addresses the technical problem of low accuracy in demand assessments relying on manual evaluation. Our approach utilizes a deep learning model, overcoming the subjectivity of manual assessments and providing more objective and accurate results. The model comprehensively considers multiple dimensions of demand, including feasibility, resource requirements, and risk levels, thus providing comprehensive assessment information and effectively improving the accuracy and efficiency of demand assessment.

[0045] Optionally, in the target requirement evaluation method provided in this application embodiment, the preprocessing and feature extraction of the requirement data to obtain the requirement feature vector corresponding to the target requirement includes: performing data cleaning on the requirement data to obtain cleaned requirement data; extracting features from the text data in the cleaned requirement data using a natural language processing model to obtain a text feature vector; extracting features from the numerical data in the cleaned requirement data to obtain a numerical feature vector; and determining the requirement feature vector based on the text feature vector and the numerical feature vector.

[0046] In an optional embodiment, the requirement data is cleaned to remove duplicate, erroneous, and incomplete data records. For example, duplicate user feedback records are identified and deleted using a data deduplication algorithm, data with incorrect formatting is corrected, and records with many missing values ​​are filled or deleted as appropriate, thus obtaining cleaned requirement data. Then, for text-based requirement data, a natural language processing model is used for feature extraction. For example, a word vector model is used to convert each word in the requirement text into a vector representation. The semantic features of the text are extracted by calculating the average or weighted average of the word vectors, or by using deep learning models such as convolutional neural networks, recurrent neural networks, and their variants, resulting in a text feature vector. For numerical data, such as the expected cost and completion time corresponding to the requirement, the numerical values ​​are directly extracted as features to obtain a numerical feature vector. Some related numerical features are then normalized to map them to the same numerical range, eliminating differences in the units of measurement between different features and improving the stability and accuracy of model training.

[0047] Optionally, in the target requirement evaluation method provided in this application embodiment, the target requirement is evaluated based on the requirement feature vector by the target evaluation model to obtain the evaluation result, including: receiving the requirement feature vector through the input layer of the target evaluation model; performing a nonlinear transformation on the requirement feature vector through the hidden layer of the target evaluation model to obtain the transformed intermediate feature representation; and generating the evaluation result based on the transformed intermediate feature representation through the output layer of the target evaluation model.

[0048] In an optional embodiment, Figure 3 This is a schematic diagram of the architecture of the demand assessment model provided in the embodiments of this application, such as... Figure 3As shown, a simple multilayer perceptron model is used as an example to illustrate the structure of the input layer, hidden layer, and output layer, as well as the connections between each layer. The input layer receives the demand feature vector after feature extraction, and through the nonlinear transformation of the hidden layer, the final output layer outputs the demand evaluation result.

[0049] Optionally, in the target requirement evaluation method provided in the embodiments of this application, after obtaining the evaluation result, the method further includes: converting the evaluation result into a visualization format and displaying the visualization format evaluation result to the target object.

[0050] In an optional embodiment, the evaluation results are presented to the user in an intuitive way, such as through tables, charts, etc. To increase the interpretability of the evaluation results, attention mechanisms and feature importance analysis are used to explain why the model gives such evaluation results. For example, attention mechanisms are used to analyze the degree of attention the model pays to different features when evaluating needs, and the features with higher attention and their corresponding weights are displayed to the user to help the user understand the model's decision-making basis.

[0051] Optionally, in the target requirement evaluation method provided in this application embodiment, the target evaluation model is obtained through the following steps: obtaining a sample dataset, wherein the sample dataset includes sample requirement feature vectors and corresponding evaluation result labels; constructing an initial evaluation model based on a deep learning model, and training the initial evaluation model according to the sample dataset until the preset conditions are met, thereby obtaining the target evaluation model.

[0052] Optionally, in the target requirement evaluation method provided in the embodiments of this application, before obtaining the sample dataset, the method further includes: collecting data from multiple data sources to obtain sample requirement data; and performing data cleaning, data annotation, and feature extraction processing on the sample requirement data to obtain the sample dataset.

[0053] Optionally, in the target requirement evaluation method provided in this application embodiment, training an initial evaluation model based on a sample dataset until a preset condition is met to obtain a target evaluation model includes: splitting the sample dataset into a training set, a validation set, and a test set; training the initial evaluation model based on the training set to obtain a first evaluation model; optimizing the parameters of the first evaluation model based on the validation set to obtain a second evaluation model; and optimizing the performance of the second evaluation model based on the test set until a preset condition is met to obtain a target evaluation model.

[0054] In an optional embodiment, multi-source data collection is performed first. Requirement-related data is collected from various channels, such as user feedback, survey data, business documents, and historical project data. For example, user expectations for product features are collected through online questionnaires, business rules and requirement constraints are obtained from business process documents, and successful and failed requirement case data are extracted from databases of similar past projects. This yields sample requirement data. The collected data is then cleaned to remove duplicate, erroneous, and incomplete records. For instance, duplicate user feedback records are identified and deleted using data deduplication algorithms, data with incorrect formats is corrected, and records with many missing values ​​are filled or deleted as appropriate. Next, data annotation is performed, adding annotation information to the cleaned data. For example, requirements are categorized into functional requirements, performance requirements, and security requirements, and attributes such as priority and urgency are also labeled. Annotation can be done manually or in conjunction with semi-supervised learning algorithms. A small number of manually annotated samples are used to train the model, which then automatically annotates a large amount of unannotated data, improving annotation efficiency.

[0055] Further, feature extraction is performed. For text-based requirement data, natural language processing models are used for feature extraction. For example, word vector models are used to convert each word in the requirement text into a vector representation. The semantic features of the text are extracted by calculating the average or weighted average of the word vectors, or by using deep learning models such as convolutional neural networks, recurrent neural networks, and their variants, resulting in a text feature vector. For numerical data, such as the expected cost and completion time corresponding to the requirement, numerical values ​​are directly extracted as features to obtain numerical feature vectors. Some related numerical features are then normalized to map them to the same numerical range, eliminating differences in the units of measurement between different features and improving the stability and accuracy of model training. This yields the sample dataset.

[0056] Further, model building and training are carried out. Deep learning models, such as multilayer perceptrons, convolutional neural networks, or recurrent neural networks and their variants, are used to build an initial demand assessment model. The model's input is the demand feature vector obtained after feature extraction, and the output is the demand assessment result, including feasibility score, resource demand prediction, and risk level assessment. For example, using a multilayer perceptron model, multiple hidden layers are used to perform nonlinear transformations on the input feature vector, ultimately outputting a vector containing multiple assessment index values. The sample dataset is divided into training, validation, and test sets. The training set is used to train the model, the validation set is used to adjust the model's hyperparameters, such as the number of hidden layer nodes, learning rate, and number of iterations, and the test set is used to evaluate the performance of the trained model. For example, the dataset can be divided in a 70%, 15%, and 15% ratio. For example, the built model is trained using the training set data, and the model's parameters are continuously adjusted using the backpropagation algorithm to minimize the error between the model's prediction results and the actual assessment results. During training, optimization algorithms such as stochastic gradient descent and adaptive moment estimation are used to accelerate the model's convergence speed and improve training efficiency. The model can be optimized by evaluating its performance on the validation set, using metrics such as accuracy, recall, and mean squared error. For example, if overfitting is observed on the validation set, regularization techniques or Dropout methods can be used to reduce model complexity and prevent overfitting.

[0057] In an optional embodiment, Figure 4 This is a schematic diagram of the requirements assessment process provided according to the embodiments of this application, such as... Figure 4 As shown, the process includes data acquisition, data preprocessing, feature extraction, model building and training, requirements assessment, and result output. Specific implementation details are as described in the foregoing embodiments and will not be repeated here.

[0058] The target requirement assessment method provided in this application includes the following steps: acquiring requirement data of the target requirement to be assessed; preprocessing and extracting features from the requirement data to obtain the requirement feature vector corresponding to the target requirement; and assessing the target requirement based on the requirement feature vector using a target assessment model to obtain the assessment result. The target assessment model is trained on a deep learning model using a sample dataset. The assessment result includes at least feasibility information, resource requirement prediction information, and risk level information of the target requirement. This solves the technical problem of low accuracy in related technologies that rely on manual assessment of requirements. In this solution, assessment using a deep learning model overcomes the subjectivity of manual assessment and provides more objective and accurate assessment results. The model can comprehensively consider multiple dimensions of the requirement, including feasibility, resource requirements, and risk level, thereby providing comprehensive assessment information and effectively improving the accuracy and efficiency of requirement assessment.

[0059] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0060] Example 2

[0061] This application also provides a target requirement evaluation apparatus. It should be noted that the target requirement evaluation apparatus of this application can be used to execute the target requirement evaluation method provided in this application. The target requirement evaluation apparatus provided in this application will be described below.

[0062] According to an embodiment of this application, an apparatus for evaluating target requirements for implementing the above-described evaluation method for target requirements is also provided, such as... Figure 5 As shown, the device includes: a first acquisition unit 501, a first processing unit 502, and a second processing unit 503.

[0063] The first acquisition unit 501 is used to acquire the requirement data of the target requirement to be evaluated;

[0064] The first processing unit 502 is used to preprocess and extract features from the demand data to obtain the demand feature vector corresponding to the target demand.

[0065] The second processing unit 503 is used to evaluate the target requirement based on the requirement feature vector through the target evaluation model and obtain the evaluation result. The target evaluation model is trained on a deep learning model based on a sample dataset. The evaluation result includes at least the feasibility information of the target requirement, the resource requirement prediction information, and the risk level information.

[0066] The target requirement assessment apparatus provided in this application embodiment acquires requirement data of the target requirement to be assessed through a first acquisition unit 501; a first processing unit 502 preprocesses and extracts features from the requirement data to obtain a requirement feature vector corresponding to the target requirement; and a second processing unit 503 assesses the target requirement based on the requirement feature vector using a target assessment model to obtain an assessment result. The target assessment model is trained on a deep learning model using a sample dataset, and the assessment result includes at least feasibility information, resource requirement prediction information, and risk level information of the target requirement. This solves the technical problem of low accuracy in related technologies that rely on manual assessment of requirements. In this solution, assessment using a deep learning model overcomes the subjectivity of manual assessment and provides more objective and accurate assessment results. The model can comprehensively consider multiple dimensions of the requirement, including feasibility, resource requirements, and risk level, thereby providing comprehensive assessment information and effectively improving the accuracy and efficiency of requirement assessment.

[0067] Optionally, in the target requirement evaluation apparatus provided in this application embodiment, the first processing unit includes: a first processing subunit, used to perform data cleaning processing on the requirement data to obtain cleaned requirement data; a second processing subunit, used to extract features from the text data in the cleaned requirement data using a natural language processing model to obtain a text feature vector; a third processing subunit, used to extract features from the numerical data in the cleaned requirement data to obtain a numerical feature vector; and a fourth processing subunit, used to determine the requirement feature vector based on the text feature vector and the numerical feature vector.

[0068] Optionally, in the target requirement evaluation apparatus provided in this application embodiment, the second processing unit includes: a fifth processing subunit, used to receive a requirement feature vector through the input layer of the target evaluation model; a sixth processing subunit, used to perform a nonlinear transformation on the requirement feature vector through the hidden layer of the target evaluation model to obtain a transformed intermediate feature representation; and a seventh processing subunit, used to generate an evaluation result through the output layer of the target evaluation model based on the transformed intermediate feature representation.

[0069] Optionally, in the target requirement evaluation apparatus provided in the embodiments of this application, the apparatus further includes: a display unit, used to convert the evaluation results into a visual format after obtaining the evaluation results, and display the visual format evaluation results to the target object.

[0070] Optionally, in the target requirement evaluation device provided in the embodiments of this application, the device further includes the following unit, which is used to obtain a target evaluation model through the following steps: a second acquisition unit, which is used to acquire a sample dataset, wherein the sample dataset includes sample requirement feature vectors and corresponding evaluation result labels; and a training unit, which is used to construct an initial evaluation model based on a deep learning model, and train the initial evaluation model according to the sample dataset until a preset condition is met to obtain the target evaluation model.

[0071] Optionally, in the target requirement evaluation device provided in the embodiments of this application, the device further includes: a data acquisition unit, used to acquire data from multiple data sources before acquiring the sample dataset to obtain sample requirement data; and a third processing unit, used to perform data cleaning, data labeling and feature extraction processing on the sample requirement data to obtain the sample dataset.

[0072] Optionally, in the target requirement evaluation device provided in the embodiments of this application, the training unit includes: a splitting subunit for splitting the sample dataset into a training set, a validation set, and a test set; a first training subunit for training an initial evaluation model based on the training set to obtain a first evaluation model; a second training subunit for optimizing the parameters of the first evaluation model based on the validation set to obtain a second evaluation model; and a third training subunit for optimizing the performance of the second evaluation model based on the test set until a preset condition is met to obtain a target evaluation model.

[0073] It should be noted that the first acquisition unit 501, the first processing unit 502, and the second processing unit 503 mentioned above correspond to steps S201 to S203 in Embodiment 1. The three units and the corresponding steps implement the same instances and application scenarios, but are not limited to the content disclosed in Embodiment 1. It should be noted that the above modules or units can be hardware or software components stored in memory (e.g., memory 104) and processed by one or more processors (e.g., processors 102a, 102b, ..., 102n). The above units can also be part of a device and run in the computer terminal 10 provided in Embodiment 1.

[0074] Example 3

[0075] Embodiments of this application may provide an electronic device. Figure 6 This is a structural block diagram of an electronic device according to an embodiment of this application. Figure 6 As shown, the electronic device may include: one or more ( Figure 6 (Only one is shown) Processor 602, memory 604, memory controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.

[0076] The memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the methods and apparatus in the embodiments of this application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby implementing the above-described methods. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0077] The processor can access the information and application programs stored in the memory via the transmission device to perform the following steps: acquiring the demand data of the target demand to be evaluated; preprocessing and feature extraction of the demand data to obtain the demand feature vector corresponding to the target demand; evaluating the target demand based on the demand feature vector using the target evaluation model to obtain the evaluation result, wherein the target evaluation model is trained on a deep learning model based on a sample dataset, and the evaluation result includes at least the feasibility information, resource demand prediction information, and risk level information of the target demand.

[0078] The processor can access information and applications stored in the memory via a transmission device to perform the following steps: clean the demand data to obtain cleaned demand data; extract features from the text data in the cleaned demand data using a natural language processing model to obtain text feature vectors; extract features from the numerical data in the cleaned demand data to obtain numerical feature vectors; and determine the demand feature vectors based on the text feature vectors and numerical feature vectors.

[0079] The processor can access the information and application program stored in the memory via the transmission device to perform the following steps: receiving the demand feature vector through the input layer of the target evaluation model; performing a nonlinear transformation on the demand feature vector through the hidden layer of the target evaluation model to obtain the transformed intermediate feature representation; and generating the evaluation result based on the transformed intermediate feature representation through the output layer of the target evaluation model.

[0080] The processor can access information and applications stored in memory via a transmission device to perform the following steps: after obtaining the evaluation results, convert the evaluation results into a visual format and display the visual evaluation results to the target object.

[0081] The processor can access the information and application stored in the memory via the transmission device to perform the following steps: acquire a sample dataset, which includes sample requirement feature vectors and corresponding evaluation result labels; construct an initial evaluation model based on a deep learning model, and train the initial evaluation model according to the sample dataset until the preset conditions are met to obtain the target evaluation model.

[0082] The processor can access the information and application programs stored in the memory via the transmission device to perform the following steps: before acquiring the sample dataset, data is collected from multiple data sources to obtain the sample requirement data; the sample requirement data is cleaned, labeled, and feature extracted to obtain the sample dataset.

[0083] The processor can access the information and application stored in the memory via the transmission device to perform the following steps: splitting the sample dataset into a training set, a validation set, and a test set; training the initial evaluation model based on the training set to obtain a first evaluation model; optimizing the parameters of the first evaluation model based on the validation set to obtain a second evaluation model; and optimizing the performance of the second evaluation model based on the test set until the preset conditions are met to obtain the target evaluation model.

[0084] Those skilled in the art will understand that Figure 6 The structure shown is for illustrative purposes only. Electronic devices can also be smartphones, tablets, handheld computers, mobile internet devices (MIDs), PADs, and other terminal devices. Figure 6 This does not limit the structure of the aforementioned electronic device. For example, electronic devices may also include components that are more... Figure 6 The more or fewer components shown (such as network interfaces, display devices, etc.), or having the same Figure 6 The different configurations shown.

[0085] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0086] Example 4

[0087] Embodiments of this application also provide a computer-readable storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the target requirement evaluation method provided in Embodiment 1.

[0088] Optionally, in this embodiment, the storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals.

[0089] This application also provides a computer program product, which, when executed on a data processing device, is adapted to perform the steps of an evaluation method for target requirements.

[0090] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0091] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0092] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0093] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0094] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0095] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0096] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for evaluating target requirements, characterized in that, include: Obtain the requirement data for the target requirement to be evaluated; The demand data is preprocessed and feature extracted to obtain the demand feature vector corresponding to the target demand; The target requirement is evaluated based on the requirement feature vector using a target evaluation model to obtain an evaluation result. The target evaluation model is trained on a deep learning model using a sample dataset. The evaluation result includes at least the feasibility information, resource requirement prediction information, and risk level information of the target requirement.

2. The method according to claim 1, characterized in that, The requirement data is preprocessed and feature extracted to obtain the requirement feature vector corresponding to the target requirement, including: The demand data is cleaned to obtain cleaned demand data; The text data in the cleaned demand data is feature extracted using a natural language processing model to obtain a text feature vector. Feature extraction is performed on the numerical data in the cleaned demand data to obtain a numerical feature vector; The required feature vector is determined based on the text feature vector and the numerical feature vector.

3. The method according to claim 1, characterized in that, The target requirement is evaluated using the target evaluation model based on the requirement feature vector, and the evaluation results include: The requirement feature vector is received through the input layer of the target evaluation model; The required feature vector is nonlinearly transformed by the hidden layer of the target evaluation model to obtain the transformed intermediate feature representation. The evaluation result is generated by the output layer of the target evaluation model based on the transformed intermediate feature representation.

4. The method according to claim 1, characterized in that, After obtaining the evaluation results, the method further includes: The evaluation results are converted into a visual format and displayed to the target audience.

5. The method according to claim 1, characterized in that, The target evaluation model is obtained through the following steps: Obtain the sample dataset, wherein the sample dataset includes sample requirement feature vectors and corresponding evaluation result labels; An initial evaluation model is constructed based on the deep learning model, and the initial evaluation model is trained on the sample dataset until the preset conditions are met, thereby obtaining the target evaluation model.

6. The method according to claim 5, characterized in that, Before obtaining the sample dataset, the method further includes: Data is collected from multiple data sources to obtain the required sample data; The sample requirement data is cleaned, labeled, and feature extracted to obtain the sample dataset.

7. The method according to claim 5, characterized in that, The initial evaluation model is trained based on the sample dataset until preset conditions are met, resulting in the target evaluation model, which includes: The sample dataset is split into a training set, a validation set, and a test set; The initial evaluation model is trained based on the training set to obtain the first evaluation model; The first evaluation model is optimized based on the validation set to obtain the second evaluation model; The second evaluation model is optimized based on the test set until the preset conditions are met, thus obtaining the target evaluation model.

8. A device for evaluating target requirements, characterized in that, include: The first acquisition unit is used to acquire the requirement data of the target requirement to be evaluated. The first processing unit is used to preprocess and extract features from the demand data to obtain the demand feature vector corresponding to the target demand. The second processing unit is used to evaluate the target requirement based on the requirement feature vector using a target evaluation model to obtain an evaluation result. The target evaluation model is trained on a deep learning model based on a sample dataset. The evaluation result includes at least the feasibility information, resource requirement prediction information, and risk level information of the target requirement.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored executable program, wherein, when the executable program is executed, it controls the device on which the computer-readable storage medium is located to perform the evaluation method for the target requirement as described in any one of claims 1 to 7.

10. An electronic device, characterized in that, include: Memory, which stores executable programs; A processor for running the program, wherein the program, when running, performs the method for evaluating the target requirements as described in any one of claims 1 to 7.

Images