CN-121996554-A - Quality evaluation method, device and equipment for engineering document and storage medium
Abstract
The application discloses a quality evaluation method, a device, equipment and a storage medium of an engineering document, which are applied to the field of financial science and technology. The method comprises the steps of obtaining an engineering test document to be evaluated, carrying out text segmentation processing on the engineering test document, carrying out semantic feature extraction on segmented text units to generate semantic context features, carrying out dependency feature extraction on the semantic context features based on a two-way long-short-term memory network, giving position attention weight to a dependency feature extraction result through a gating mechanism to generate a domain entity tag space, determining an optimal tag sequence based on legal tag transfer rules and the domain entity tag space, determining a structured entity tree corresponding to the engineering test document based on the optimal tag sequence, and carrying out quality evaluation on the engineering test document based on the structured entity tree. By the technical scheme, the quality evaluation accuracy of the engineering test document is improved.
Inventors
- WANG ZHIJIE
Assignees
- 中国工商银行股份有限公司
Dates
- Publication Date
- 20260508
- Application Date
- 20260121
Claims (10)
- 1. A method for evaluating the quality of an engineering document, comprising: Acquiring an engineering test document to be evaluated, performing text segmentation processing on the engineering test document, and performing semantic feature extraction on segmented text units to generate semantic context features, wherein the semantic context features are context semantic features of at least two feature dimensions; based on a two-way long-short-term memory network, extracting the dependency characteristics of the semantic context characteristics, and giving position attention weight to the dependency characteristic extraction result through a gating mechanism to generate a domain entity label space; determining an optimal tag sequence based on legal tag transfer rules and the domain entity tag space, and determining a structured entity tree corresponding to the engineering test document based on the optimal tag sequence; and carrying out quality evaluation on the engineering test document based on the structured entity tree.
- 2. The method of claim 1, wherein the quality assessment of the engineering test document based on the structured entity tree comprises: Traversing tree nodes in the structured entity tree, clustering the tree nodes according to the label attribute of the nodes, and generating at least one tree node group; Aiming at node values of any two tree nodes in the tree node group, carrying out term consistency detection based on semantic similarity calculation and character similarity calculation; Traversing tree nodes in the structured entity tree, extracting at least one target tree node with entity tag attribute as step tag, and constructing a target directed acyclic graph for the at least one target tree node according to the node attribute of the target tree node; Traversing the target directed acyclic graph according to a preset test step execution rule, and detecting step time sequence, wherein the test step time sequence detection is used for determining whether an edge dependency relationship error and loop risk exist in the target directed acyclic graph; And carrying out quality evaluation on the engineering test document based on the term consistency detection result and the step time sequence detection result.
- 3. The method of claim 1, wherein evaluating the quality of the engineering test document based on the term consistency test result and the step timing test result comprises: And weighting different document defects according to the defect occurrence times of inconsistent terms and the defect occurrence times of step time sequence errors, and determining the quality evaluation score of the engineering test document.
- 4. The method of claim 1, wherein the determining an optimal tag sequence based on legal tag transfer rules and the domain entity tag space comprises: Determining a label transfer probability matrix according to the legal label transfer rule, wherein the label transfer probability matrix is used for representing the connection probability among different entity labels; And respectively carrying out weighted summation on the label feature vectors corresponding to the text units in the field entity label space according to the label transition probability matrix, and taking the entity label sequence with the highest path score as the optimal label sequence.
- 5. The method of claim 4, wherein each text unit has a respective corresponding tag feature vector in the domain entity tag space, wherein the tag feature vector is used to characterize a maximum tag probability for each text unit under at least one entity tag, and wherein the maximum tag probability is used to characterize a likelihood that a text unit is under one entity tag.
- 6. The method of claim 1, wherein the determining a structured entity tree corresponding to the engineering test document based on the optimal tag sequence comprises: Traversing the optimal tag sequence, and triggering entity extraction to start if the current traversed object is a first target tag; In the entity extraction process, if the current traversal object is a second target label, triggering the entity extraction to be finished; And carrying out text merging on text units corresponding to the traversed entity tag sequences in the entity extraction process, and generating a structured entity tree corresponding to the engineering test document according to the text objects after merging and the text attributes of the text units corresponding to the tag sequences.
- 7. A quality evaluation device of an engineering document, characterized by comprising: The semantic feature extraction module is used for acquiring an engineering test document to be evaluated, carrying out text segmentation processing on the engineering test document, and carrying out semantic feature extraction on segmented text units to generate semantic context features, wherein the semantic context features are context semantic features of at least two feature dimensions; The label space generating module is used for extracting the dependency characteristics of the semantic context characteristics based on a two-way long-short-term memory network, giving position attention weight to the dependency characteristic extraction result through a gating mechanism and generating a domain entity label space; The structure tree generation module is used for determining an optimal label sequence based on legal label transfer rules and the domain entity label space, and determining a structured entity tree corresponding to the engineering test document based on the optimal label sequence; and the quality evaluation module is used for evaluating the quality of the engineering test document based on the structured entity tree.
- 8. An electronic device, comprising: One or more processors; a memory for storing one or more programs; The one or more programs, when executed by the one or more processors, cause the one or more processors to implement the quality assessment method of an engineering document of any of claims 1-6.
- 9. A computer-readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements a method for quality assessment of an engineering document according to any one of claims 1-6.
- 10. A computer program product comprising a computer program which, when executed by a processor, implements the quality assessment method of an engineering document according to any one of claims 1-6.
Description
Quality evaluation method, device and equipment for engineering document and storage medium Technical Field The embodiment of the application relates to the technical field of computers, and can be applied to the field of financial science and technology, in particular to a quality evaluation method, device and equipment of engineering documents and a storage medium. Background At present, in the project development testing stage of each application field, the document quality of the test engineering document of the application project is particularly important, and the test quality of the application project is directly influenced. Therefore, there is a need for a quality assessment method of engineering documents suitable for the field of software testing, so as to improve the document quality of the engineering documents in the field of software testing. Disclosure of Invention The application provides a quality evaluation method, device and equipment of engineering documents and a storage medium, which are used for improving the document quality of the engineering documents in the field of software testing. According to an aspect of the present application, there is provided a quality assessment method of an engineering document, the method comprising: Acquiring an engineering test document to be evaluated, performing text segmentation processing on the engineering test document, and performing semantic feature extraction on segmented text units to generate semantic context features, wherein the semantic context features are context semantic features of at least two feature dimensions; based on a two-way long-short-term memory network, extracting the dependency characteristics of the semantic context characteristics, and giving position attention weight to the dependency characteristic extraction result through a gating mechanism to generate a domain entity label space; determining an optimal tag sequence based on legal tag transfer rules and the domain entity tag space, and determining a structured entity tree corresponding to the engineering test document based on the optimal tag sequence; and carrying out quality evaluation on the engineering test document based on the structured entity tree. According to another aspect of the present application, there is provided a quality assessment apparatus of an engineering document, the apparatus comprising: The semantic feature extraction module is used for acquiring an engineering test document to be evaluated, carrying out text segmentation processing on the engineering test document, and carrying out semantic feature extraction on segmented text units to generate semantic context features, wherein the semantic context features are context semantic features of at least two feature dimensions; The label space generating module is used for extracting the dependency characteristics of the semantic context characteristics based on a two-way long-short-term memory network, giving position attention weight to the dependency characteristic extraction result through a gating mechanism and generating a domain entity label space; The structure tree generation module is used for determining an optimal label sequence based on legal label transfer rules and the domain entity label space, and determining a structured entity tree corresponding to the engineering test document based on the optimal label sequence; and the quality evaluation module is used for evaluating the quality of the engineering test document based on the structured entity tree. According to another aspect of the present application, there is provided an electronic apparatus including: One or more processors; a memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement any of the quality assessment methods for engineering documents provided by the embodiments of the present application. According to another aspect of the present application, there is provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a quality assessment method of any one of the engineering documents provided by the embodiments of the present application. According to another aspect of the present application, there is provided a computer program product comprising a computer program which, when executed by a processor, implements a method for quality assessment of any one of the engineering documents provided by the embodiments of the present application. According to the application, the semantic context feature and the dependency feature are extracted twice for the engineering test document, so that the domain entity tag space corresponding to the engineering test document is determined, the entity boundary judgment precision is improved, and the quality evaluation precision of the engineering test document is further improved. Drawings FIG. 1 is a flow chart o