Software development target analysis device and method, and storage medium

Abstract

The invention provides a software development target analysis device and method and a storage medium. The software development target analysis device comprises a data acquisition module and an analysis module. The data acquisition module is used for acquiring multi-source data of a user about a software development target. And the analysis module comprises a value point extraction unit, a fact point extraction unit, a correlation analysis unit and a purpose induction unit. The value point extraction unit is configured to extract at least one value point pursued by a user from the multi-source data. The fact point extraction unit is configured to extract a fact point of at least one fact from the multi-source data. The correlation analysis unit is configured to perform semantic analysis on each extracted value point and each fact point so as to determine the correlation between each fact point and each value point. The target induction unit is configured to determine key value points of which the total weight is greater than a preset first threshold value according to the relevance of each fact point to each value point; and determining a software development target according to the key value point and the corresponding related fact point.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a software development target analysis device, a software development target analysis method, and a computer-readable storage medium. Background Art

[0002] In the modern software development lifecycle, customer needs analysis is the cornerstone that determines project success or failure. Accurately understanding and translating the customer's true, underlying needs is crucial to ensuring the ultimate value of a software product. However, current industry-wide technologies for addressing software customer needs have significant limitations.

[0003] Traditional manual analysis methods rely on product managers or requirements analysts to gather information through meetings, interviews, questionnaires, and other methods. These methods are severely limited by the analysts' personal experience, communication skills, and subjective judgment. This leads to low efficiency and high costs, and can easily lead to distorted requirements due to information omissions and misunderstandings, creating significant project risks. Project and task management tools like JIRA and Trello manage only defined requirements and are unable to automatically analyze, mine, and extract deeper objectives from raw, ambiguous customer communications. Furthermore, when applying rudimentary natural language processing techniques to analyze customer needs, keyword extraction and word frequency statistics fail to understand the semantic relationships and context between words, often misinterpreting superficial aspects as core demands. Furthermore, sentiment analysis using rudimentary natural language processing techniques can only determine the emotional polarity of text, failing to reveal the specific reasons behind these sentiments and potential customer goals. General-purpose chatbots or question-answering systems are limited by pre-set rule bases, making it difficult to effectively summarize and reason about open-ended and complex underlying business objectives. In addition, although existing CRM systems are good at recording customer information and interaction history, their analytical capabilities are limited to macro-statistics and lack a deep-dive mechanism to understand the "why" behind customers' specific product feature requirements.

[0004] In order to overcome the above-mentioned defects of the existing technology, the field urgently needs an improved software development goal analysis device, which is used to deeply explore the development goals in the software development process according to user needs, thereby improving the efficiency and automation level of the development goal analysis process, and enhancing the objectivity and accuracy of the analysis results, further reducing the risks of development projects. Summary of the Invention

[0005] The following is a brief summary of one or more aspects to provide a basic understanding of these aspects. This summary is not an exhaustive overview of all conceivable aspects and is neither intended to identify key or critical elements of all aspects nor to define the scope of any or all aspects. Its sole purpose is to present some concepts of one or more aspects in a simplified form as a prelude to the more detailed description that will be provided later.

[0006] In order to overcome the above-mentioned defects of the prior art, the present invention provides an analysis device for software development goals, a method for analyzing software development goals and a computer-readable storage medium. The device can extract value points and fact points from the user's multi-source data on software development goals, and establish a correlation between the value points and the fact points. The device can be used to deeply explore the development goals in the software development process according to user needs, thereby improving the efficiency and automation level in the process of analyzing development goals, enhancing the objectivity and accuracy of the analysis results, and further reducing the risks of development projects.

[0007] Specifically, the analysis device for the above-mentioned software development goals provided according to the first aspect of the present invention includes a data acquisition module and an analysis module. The data acquisition module is used to obtain multi-source data of the user on the software development goals. The analysis module includes a value point extraction unit, a fact point extraction unit, a correlation analysis unit and a purpose summarization unit. The value point extraction unit is configured to extract at least one value point pursued by the user from the multi-source data. The fact point extraction unit is configured to extract at least one fact point of a fact from the multi-source data. The correlation analysis unit is configured to perform semantic analysis on each of the extracted value points and each of the fact points to determine the relevance of each of the fact points to each of the value points. The purpose summarization unit is configured to determine the key value points whose total weight is greater than a preset first threshold value based on the relevance of each of the fact points to each of the value points; and determine the software development goals based on the key value points and their corresponding related fact points.

[0008] Furthermore, in some embodiments of the present invention, the multi-source data is selected from at least one of project management data, online documents, emails, and meeting recordings. The data acquisition module is configured with a business data acquisition unit that connects to the user company's project management system, online document sharing system, email server, and meeting recording transcription system to obtain the user's multi-source data related to the software development goal.

[0009] Furthermore, in some embodiments of the present invention, the data acquisition module is also provided with a preprocessing unit, which is configured to: deduplicate the acquired multi-source data; remove HTML tags from the deduplicated data; perform uniform encoding on the data from which the HTML tags have been removed; and divide the uniformly encoded data into a plurality of semantically complete paragraphs.

[0010] Furthermore, in some embodiments of the present invention, the value point extraction unit is configured with a pre-trained and fine-tuned large language model, which is configured to: ask questions to each of the multi-source data one by one according to a preset prompt project to extract at least one value point pursued by the user.

[0011] Furthermore, in some embodiments of the present invention, the data collection module is configured with a user data acquisition unit for acquiring characteristic data of multiple users for user classification. The value point extraction unit is further configured to, based on a preset prompting process, ask questions of each of the multi-source data of each category of users one by one to extract at least one value point pursued by each category of users.

[0012] Furthermore, in some embodiments of the present invention, the fact point extraction unit is configured with a pre-trained named entity recognition model, which is configured to: parse each of the multi-source data one by one according to pre-named entities of multiple preset dimensions, and form a fact point of at least one fact based on the recognized named entities. The multiple preset dimensions are selected from at least one of a person's name, an organization's name, a job title, a product's name, an action's name, a degree's name, and a duration of time.

[0013] Furthermore, in some embodiments of the present invention, the fact point extraction unit is also configured to: determine a reliability weight based on the data source and / or clarity of the fact point; determine an importance weight based on the number of occurrences of the fact point in the multi-source data; determine the fact point weight of the corresponding fact point based on the reliability weight and the importance weight; and retain valid fact points whose fact point weight reaches a preset second threshold, and filter out invalid fact points whose fact point weight is less than the second threshold.

[0014] Furthermore, in some embodiments of the present invention, the fact point extraction unit is also configured with a pre-trained clarity classification model, which is configured to: in response to a fact point that forms at least one fact, perform semantic analysis on the fact point via the clarity classification model to determine a corresponding clarity classification.

[0015] Furthermore, in some embodiments of the present invention, a pre-trained association classification model is configured in the association analysis unit. The step of performing semantic analysis on the extracted value points and fact points to determine the relevance of each fact point to each value point includes: combining each value point with each fact point into a high-dimensional vector to calculate the correlation between the two; inputting the high-dimensional vector whose correlation reaches a preset third threshold into the association classification model to determine the relevance label of the fact vector to the corresponding value vector. A positive relevance label indicates that the fact vector supports the corresponding value vector. A negative relevance label indicates that the fact vector opposes the corresponding value vector.

[0016] Furthermore, in some embodiments of the present invention, the step of determining key value points whose total weight is greater than a preset first threshold based on the correlation between each fact point and each value point includes: for each value point, marking the fact point weight of the fact point corresponding to each of its positive correlation labels as positive, and calculating the cumulative value as the total weight of the value point; and determining the value point whose total weight is greater than the first threshold as the key value point.

[0017] Furthermore, in some embodiments of the present invention, the step of determining the software development goal based on the key value point and its corresponding related fact point includes: filling the value vector V1 of the key value point and the fact vector F1 of the corresponding related fact point into a preset software development goal template to output the software development goal.

[0018] Furthermore, in some embodiments of the present invention, the purpose induction unit is also configured to: for each of the value points, mark the fact point weights of the fact points corresponding to its respective reverse correlation labels as negative, and calculate the accumulated value as the total weight of the value point; and determine the value points whose total weight is less than the fourth threshold as the valid value points.

[0019] Furthermore, in some embodiments of the present invention, the step of determining the software development goal based on the key value point and its corresponding related fact point includes: filling the value vector V2 of the value point that is both the key value point and the effective value point and the fact vector F2 of the corresponding related fact point into the preset software development goal template to output the software development goal.

[0020] Furthermore, in some embodiments of the present invention, the analysis device further includes a display module configured to provide a display interface with at least one tab to display the software development goal and its corresponding value points, fact points, support relationships, and / or opposition relationships. The support relationships and / or opposition relationships are displayed in the form of a relationship diagram, and the weights between the value point and the first fact point supporting it and / or the second fact point opposing it are indicated.

[0021] Furthermore, in some embodiments of the present invention, the display module also supports an editing function and is configured to: add or subtract value points and / or fact points in the display interface, and / or adjust the relationship between at least one of the value points and the corresponding fact point according to the user's editing operation on the relationship diagram.

[0022] Furthermore, in some embodiments of the present invention, the analysis device further includes a modification assistance module. The modification assistance module is connected to the display module and the purpose summarizing unit of the analysis module and is configured to: obtain a modification instruction provided by a user based on natural language and / or images; perform natural language parsing and / or image parsing on the modification instruction to determine at least one editing operation instruction for the relationship graph; transmit the at least one editing operation instruction to the display module to implement the corresponding editing operation; and transmit the at least one editing operation instruction to the purpose summarizing unit to redefine the key value point.

[0023] In addition, the above-mentioned software development goal analysis method provided according to the second aspect of the present invention includes the following steps: obtaining multi-source data of users about software development goals; extracting at least one value point pursued by the user from the multi-source data, and extracting at least one fact point of a fact; performing semantic analysis on each of the extracted value points and each of the fact points to determine the relevance of each of the fact points to each of the value points; determining key value points whose total weight is greater than a preset first threshold based on the relevance of each of the fact points to each of the value points; and determining the software development goals based on the key value points and their corresponding related fact points.

[0024] Furthermore, the computer-readable storage medium provided in accordance with the third aspect of the present invention stores computer instructions, which, when executed by a processor, implement the software development target analysis method provided in accordance with the second aspect of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The above features and advantages of the present invention will be better understood after reading the detailed description of the embodiments of the present disclosure in conjunction with the following drawings. In the drawings, the components are not necessarily drawn to scale, and components with similar related properties or characteristics may have the same or similar reference numerals.

[0026] Figure 1 A schematic structural diagram of a software development target analysis device provided according to some embodiments of the present invention is shown.

[0027] Figure 2 A flowchart of a method for analyzing software development objectives provided according to some embodiments of the present invention is shown.

[0028] Figure 3 A schematic diagram illustrating the principles of a method for analyzing software development objectives provided according to some embodiments of the present invention is shown.

[0029] Reference numerals:

[0030] 10Data acquisition module

[0031] 11Business data collection unit

[0032] 12 pre-processing units

[0033] 13 User data acquisition unit

[0034] 20 analysis modules

[0035] 21 value point extraction unit

[0036] 22Fact point extraction unit

[0037] 23 Association Analysis Unit

[0038] 24-purpose summary unit

[0039] 30 display modules

[0040] 40 Modify auxiliary modules DETAILED DESCRIPTION

[0041] The following specific embodiments illustrate the embodiments of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. Although the description of the present invention will be introduced in conjunction with the preferred embodiment, this does not mean that the features of this invention are limited to this embodiment. On the contrary, the purpose of introducing the invention in conjunction with the embodiment is to cover other options or modifications that may be extended based on the claims of the present invention. In order to provide a deep understanding of the present invention, the following description will include many specific details. The present invention can also be implemented without using these details. In addition, in order to avoid confusion or blurring the focus of the present invention, some specific details will be omitted in the description.

[0042] In the description of the present invention, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they may refer to fixed, detachable, or integral connections; mechanical or electrical connections; direct or indirect connections through an intermediate medium; and internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on the specific circumstances.

[0043] Furthermore, the terms "upper," "lower," "left," "right," "top," "bottom," "horizontal," and "vertical" used in the following description should be understood to refer to the orientations depicted in that section and the accompanying drawings. These relative terms are used solely for convenience of description and do not necessarily imply that the devices described herein must be manufactured or operated in a specific orientation. Therefore, they should not be construed as limiting the present invention.

[0044] It will be understood that although the terms "first," "second," "third," etc. may be used herein to describe various components, regions, layers, and / or portions, these components, regions, layers, and / or portions should not be limited by these terms, and these terms are merely used to distinguish different components, regions, layers, and / or portions. Thus, a first component, region, layer, and / or portion discussed below may be referred to as a second component, region, layer, and / or portion without departing from some embodiments of the present invention.

[0045] As mentioned above, traditional manual analysis methods rely on product managers or requirements analysts to collect information through meetings, interviews, questionnaires, and other methods. Their effectiveness is severely limited by the analysts' personal experience, communication skills, and subjective judgment. This leads to low efficiency and high costs, and can easily lead to distorted requirements due to information omissions and misunderstandings, creating significant project risks. Project and task management tools like JIRA and Trello can only manage clearly defined requirements and are unable to automatically analyze, mine, and extract deeper objectives from raw, ambiguous customer communications. Furthermore, when applying rudimentary natural language processing techniques to analyze customer needs, keyword extraction and word frequency statistics fail to understand the semantic relationships and context between words, often misinterpreting superficial aspects as core demands. Furthermore, sentiment analysis using rudimentary natural language processing techniques can only determine the emotional polarity of text, failing to reveal the specific reasons behind these sentiments and potential customer goals. General-purpose chatbots or question-answering systems are limited by pre-set rule bases, making it difficult to effectively summarize and reason about open-ended and complex underlying business objectives. In addition, although existing CRM systems are good at recording customer information and interaction history, their analytical capabilities are limited to macro-statistics and lack a deep-dive mechanism to understand the "why" behind customers' specific product feature requirements.

[0046] In order to overcome the above-mentioned defects of the prior art, the present invention provides an analysis device for software development goals, a method for analyzing software development goals and a computer-readable storage medium. The device can extract value points and fact points from the user's multi-source data on software development goals, and establish a correlation between the value points and the fact points. The device can be used to deeply explore the development goals in the software development process according to user needs, thereby improving the efficiency and automation level in the process of analyzing development goals, enhancing the objectivity and accuracy of the analysis results, and further reducing the risks of development projects.

[0047] In some non-limiting embodiments, the software development target analysis device provided in the first aspect of the present invention may be implemented based on the software development target analysis method provided in the second aspect of the present invention.

[0048] Please refer to Figure 1 . Figure 1 A schematic structural diagram of a software development target analysis device provided according to some embodiments of the present invention is shown.

[0049] exist Figure 1 In the illustrated embodiment, the software development goal analysis device provided by the first aspect of the present invention includes a data collection module 10 and an analysis module 20. The data collection module 10 is used to obtain multi-source data from users regarding software development goals. The analysis module 20 includes a value point extraction unit 21, a fact point extraction unit 22, a correlation analysis unit 23, and a goal summarization unit 24.

[0050] Furthermore, in some non-limiting embodiments, the software development target analysis device provided in the first aspect of the present invention includes a memory and a processor. The memory includes, but is not limited to, the computer-readable storage medium provided in the third aspect, having computer instructions stored thereon. The processor is connected to the memory and configured to execute the computer instructions stored in the memory to implement the software development target analysis method provided in the second aspect of the present invention.

[0051] The following will describe the working principle of the above-mentioned analysis device for software development targets in conjunction with some embodiments of the analysis method for software development targets. Those skilled in the art will understand that the embodiments of these analysis methods are only some non-limiting implementation methods provided by the present invention, which are intended to clearly demonstrate the main concept of the present invention and provide some specific solutions that are convenient for the public to implement, rather than limiting all functions or all working modes of the analysis device. Similarly, the analysis device for software development targets is also only a non-limiting implementation method provided by the present invention, and does not constitute a limitation on the execution subject and execution order of each step in the analysis method for these software development targets.

[0052] Please refer to the specific Figure 2 and Figure 3 . Figure 2 A flowchart of a method for analyzing software development objectives provided according to some embodiments of the present invention is shown. Figure 3 A schematic diagram illustrating the principles of a method for analyzing software development objectives provided according to some embodiments of the present invention is shown.

[0053] like Figure 2 and Figure 3 As shown, the software development target analysis device provided by the first aspect of the present invention can first obtain the multi-source data of the user on the software development target through the data acquisition module 10.

[0054] Further, in Figure 1 In the illustrated embodiment, the data collection module 10 includes a business data collection unit 11, which connects to the user's company's project management system (e.g., JIRA), online document sharing system (e.g., Confluence knowledge base), email server, and meeting recording transcription system to obtain multi-source data related to the user's software development goals through API interfaces, web crawlers, or file uploads. The multi-source data is selected from at least one of project management data, online documents, emails, and meeting recordings.

[0055] For example, the business data collection unit 11 can obtain tasks defined by the customer in the current work project in the JIRA system. The data nature of this data is the customer's thinking on how to decompose and define the development work of the project. Here, the JIRA system is a project management system whose basic function is to establish, assign, and track sub-tasks.

[0056] For another example, the business data collection unit 11 can obtain an online document from the Confluence knowledge base containing a client's project description of the project development work. The project description includes but is not limited to business scenarios, requirement definitions, interface definitions, and business logic. The Confluence knowledge base is an online document sharing system typically used to share summary information within or between software teams.

[0057] In addition, Figure 1In the embodiment shown, the data acquisition module 10 is further configured with a preprocessing unit 12 for preprocessing the multi-source data acquired above. Specifically, during the preprocessing process, the preprocessing unit 12 can first perform deduplication processing on the acquired multi-source data. Afterwards, the preprocessing unit 12 can remove HTML tags from the deduplication-processed data. Thereafter, the preprocessing unit 12 can perform unified encoding processing on the data with the HTML tags removed (for example: unified encoding as UTF-8). Thereafter, the preprocessing unit 12 can divide the data processed with unified encoding into a plurality of semantically complete paragraphs.

[0058] Furthermore, in some embodiments, the pre-processing unit 12 can perform hierarchical segmentation on the uniformly encoded data. For example, the pre-processing unit 12 can segment a semi-structured long document into chapters, sub-chapter, paragraphs, and sentences according to its original hierarchical structure.

[0059] Alternatively, in some embodiments, the pre-processing unit 12 is configured with a pre-trained and fine-tuned large language model (e.g., GPT-4). Specifically, during data segmentation, the pre-processing unit 12 can leverage the understanding capabilities of the large language model to perform segmentation. For example, the pre-processing unit 12 can issue a segmentation instruction to the large language model: "Please segment the following long text into multiple semantically coherent and complete sections. Each section should revolve around a core theme. Please use the special marker [END_OF_CHUNK] at the end of each section to identify the segmentation point."

[0060] Those skilled in the art will understand that the above-mentioned examples of preprocessing the acquired multi-source data are merely some non-limiting implementation methods provided by the present invention, which are intended to clearly demonstrate the main concepts of the present invention and provide some specific solutions that are convenient for the public to implement, rather than to limit the scope of protection of the present invention.

[0061] Optionally, in other embodiments, those skilled in the art may not perform pre-processing operations such as removing HTML tags, uniformly encoding or segmenting the acquired multi-source data, and may directly use the data for subsequent operations.

[0062] Optionally, in other embodiments, those skilled in the art may also select one or more of the above preprocessing operations, or adopt other preprocessing operations according to the data conditions of the multi-source data actually acquired.

[0063] Afterwards, if Figure 2 and Figure 3As shown, the software development goal analysis device provided by the first aspect of the present invention can extract at least one value point pursued by the user from the multi-source data via the value point extraction unit 21 of the analysis module 20 .

[0064] Furthermore, in some preferred embodiments, the value point extraction unit 21 is configured with a pre-trained and fine-tuned large language model (e.g., GPT, BERT, etc.). Specifically, the value point extraction unit 21 can ask questions to each of the multiple source data one by one based on a preset prompting process to extract at least one value point sought by the user.

[0065] For example, in some embodiments, the value point extraction unit 21 may ask the large language model, "What core expectations or success criteria does this text express for the user?" The value point extraction unit 21 may then extract value point V1: "Improve sales team collaboration efficiency."

[0066] In addition, Figure 1 In the illustrated embodiment, the data collection module 10 is configured with a user data acquisition unit 13 for acquiring characteristic data of multiple users for classification. For example, this characteristic data may include fields (e.g., semiconductors, construction, finance, etc.), positions (e.g., engineer, tester, sales, etc.), gender, age, and educational background. Specifically, the value point extraction unit 21 can, based on a preset prompting process, ask questions of each user category in the multi-source data to extract at least one value point sought by each user category.

[0067] In this way, by classifying users based on objective data, the present invention can characterize the needs and values ​​of corresponding categories of users according to the different characteristics of user needs and values ​​in various fields, positions, genders, ages, and educational backgrounds, thereby accurately analyzing their software development goals.

[0068] In addition, if Figure 2 and Figure 3 As shown, the software development target analysis device provided by the first aspect of the present invention can extract at least one fact point via the fact point extraction unit 22 .

[0069] Furthermore, in some preferred embodiments, the fact point extraction unit 22 is configured with a pre-trained named entity recognition (NER) model. Specifically, the fact point extraction unit 22 can parse each of the multi-source data one by one based on pre-defined named entities of multiple dimensions, and generate a fact point for at least one fact based on the recognized named entities.

[0070] Furthermore, in some embodiments, the plurality of preset dimensions are selected from at least one of a person's name, an organization's name, a job title, a product's name, an action's name, a degree's name, and a length of time.

[0071] In addition, in some embodiments, the fact point extraction unit 22 may also determine a reliability weight based on the data source of the fact point (e.g., a project management system, an online document sharing system, an email server, a conference recording transcription system) and / or clarity (e.g., verb name "complain", "praise"; degree name "very", "likely"; time length "1 minute", "1 hour").

[0072] Afterwards, the fact point extraction unit 22 may determine an importance weight according to the number of occurrences of the fact point in the multi-source data.

[0073] Thereafter, the fact point extraction unit 22 may determine a fact point weight corresponding to the fact point according to the reliability weight and the importance weight.

[0074] Thereafter, the fact point extraction unit 22 may retain valid fact points whose fact point weights reach a preset second threshold (eg, 0.3), and filter out invalid fact points whose fact point weights are less than the second threshold.

[0075] For example, fact point extraction unit 22 extracts fact point F1: "Salesperson A complains that it takes one hour each day to manually enter customer visit records into the Customer Relationship Management (CRM) system." Fact point extraction unit 22 can then determine a reliability weight of 0.9 for fact point F1 based on its source (e.g., a transcript of an interview recording) and clarity.

[0076] Afterwards, the fact point extraction unit 22 may determine that the importance weight of the fact point is 0.8 based on the fact point being mentioned in multiple places.

[0077] Thereafter, the fact point extraction unit 22 may determine the fact point weight corresponding to the fact point according to the reliability weight and the importance weight:

[0078]

[0079] in, 、 is a hyperparameter, .

[0080] Thereafter, in response to the fact point weight of the fact point F1 being greater than the second threshold, the fact point extraction unit 22 may retain the fact point F1.

[0081] On the contrary, for another fact point F2: "I heard that Company B uses DeepSeek for sales forecasting", the fact point extraction unit 22 determines that its fact point weight is less than the second threshold, and the fact point extraction unit 22 can filter out the fact point F2.

[0082] Furthermore, in some embodiments, the fact point extraction unit 22 is further configured with a pre-trained clarity classification model. Specifically, in response to a fact point that forms at least one fact, the fact point extraction unit 22 may perform semantic analysis on the fact point using the clarity classification model to determine a corresponding clarity classification (e.g., "clear" (1), "relatively clear" (0.5), or "unclear" (0.3)).

[0083] Then, if Figure 2 and Figure 3 As shown, the software development target analysis device provided by the first aspect of the present invention can perform semantic analysis on the extracted value points and fact points via the association analysis unit 23 to determine the association between each fact point and each value point.

[0084] Furthermore, in some preferred embodiments, the association analysis unit 23 is configured with a pre-trained association classification model. Specifically, the association analysis unit 23 may first combine each value point with each fact point into a high-dimensional vector (V, F) to calculate the correlation between the two (e.g., cosine similarity, Euclidean distance, etc.). The fact points are preferably valid fact points.

[0085] Those skilled in the art will understand that the above-mentioned embodiments of calculating the correlation between value points and fact points based on cosine similarity are merely some non-limiting implementation methods provided by the present invention, which are intended to clearly demonstrate the main concepts of the present invention and provide some specific solutions that are convenient for the public to implement, rather than to limit the scope of protection of the present invention.

[0086] Optionally, in other embodiments, those skilled in the art may also determine the correlation between the value points and the fact points based on Euclidean distance, Pearson correlation coefficient, Jaccard similarity, or adjusted cosine similarity.

[0087] Afterwards, the association analysis unit 23 inputs the high-dimensional vector whose correlation reaches a preset third threshold (for example: 0.7) into the association classification model to determine the association label of the fact vector F to the corresponding value vector V, wherein the positive association label indicates that the fact vector F supports the corresponding value vector V, and the negative association label indicates that the fact vector F opposes the corresponding value vector V.

[0088] Furthermore, in some embodiments, the aforementioned association analysis model can also determine whether fact point F has a positive or negative correlation with value point V. For example, in the customer demand data for "desiring the system to automatically synchronize data," fact point F supports value point V, meaning it has a positive correlation with it. For another example, in the customer demand data for "slow data entry leads to low efficiency," fact point F is a counterexample to value point V, meaning it has a negative correlation with it.

[0089] Then, if Figure 2 and Figure 3 As shown, the analysis device for the above-mentioned software development goals provided by the first aspect of the present invention can determine the key value points whose total weight is greater than a preset first threshold (for example: 2.5) based on the correlation between each fact point and each value point through the purpose induction unit 24.

[0090] Specifically, the purpose summarizing unit 24 may mark the fact point weights of the fact points corresponding to each positive correlation label as positive for each value point, and calculate the cumulative value thereof: , as the total weight of the value points. Here, the above fact points are preferably valid fact points. Afterwards, the purpose summarization unit 24 can determine the value points with a total weight greater than the first threshold as key value points KV.

[0091] Then, if Figure 2 and Figure 3 As shown, the purpose summarizing unit 24 can determine the software development goal based on the key value points KV and their corresponding related fact points.

[0092] Specifically, during the process of determining the software development goal, the goal summarization unit 24 may enter the value vector V1 of the key value point and the fact vector F1 of the corresponding related fact point into a preset software development goal template to output the software development goal. For example, "To achieve the goal [V1], the problem [F1] must be solved."

[0093] In addition, in some preferred embodiments, the purpose summarizing unit 24 may mark the fact point weights of the fact points corresponding to the reverse correlation labels of each value point as negative, and calculate the cumulative value thereof. , as the total weight of the value point. Here, the fact point is preferably a valid fact point. Then, the purpose induction unit 24 can determine the value point with a total weight less than a fourth threshold (e.g., 0.1) as a valid value point AV.

[0094] Specifically, during the process of determining the software development goal, the goal summarization unit 24 may enter the value vector V2 of a value point that is both a key value point KV and an effective value point AV, and the fact vector F2 of its corresponding related fact point, into a preset software development goal template to output the software development goal. For example, "To achieve the goal [V2], the problem [F2] must be solved."

[0095] In addition, Figure 1 In the illustrated embodiment, the analysis device for the above-mentioned software development goals provided by the first aspect of the present invention also includes a display module 30, which is used to provide a display interface with at least one tab page to display the software development goals, as well as their corresponding value points, fact points, support relationships and / or opposition relationships.

[0096] Furthermore, in some embodiments, the support relationship and / or the opposition relationship is displayed in the form of a relationship graph, and the weights between the value point and the first fact point supporting it and / or the second fact point opposing it are shown.

[0097] Furthermore, the display module 30 also supports editing functions. Specifically, the display module 30 can add or remove value points and / or fact points in the display interface and / or adjust the relationship between at least one value point and the corresponding fact point based on the user's editing operation on the relationship diagram.

[0098] In addition, Figure 1 In the embodiment shown, the software development target analysis device provided by the first aspect of the present invention further includes a modification auxiliary module 40. The modification auxiliary module 40 is connected to the display module 30 and the purpose summarizing unit 24 of the analysis module.

[0099] Specifically, the modification auxiliary module 40 may first obtain a modification instruction based on natural language and / or images provided by the user.

[0100] The modification auxiliary module 40 can then perform natural language parsing and / or image parsing on the modification instruction to identify at least one edit operation instruction for the relationship graph. This edit operation instruction can be a single edit operation instruction or multiple edit operation instructions for batch modification that meet specific conditions. For example, the modification auxiliary module 40 can parse an instruction to delete a node that meets certain conditions and generate a description text as required using the pre-trained large language model configured within it.

[0101] Afterwards, the modification auxiliary module 40 may transmit at least one editing operation instruction to the display module to implement the corresponding editing operation.

[0102] Afterwards, the modification auxiliary module 40 may transmit at least one editing operation instruction to the target summarizing unit 24 to redefine the key value point KV, and feed back its judgment result to the display module 30 in real time.

[0103] In summary, the above-mentioned software development goal analysis device, software development goal analysis method, and computer-readable storage medium provided by the present invention can all extract value points and fact points from the user's multi-source data on software development goals, and establish a correlation between value points and fact points, so as to deeply explore development goals in the software development process according to user needs, thereby improving the efficiency and automation level in the process of analyzing development goals, and enhancing the objectivity and accuracy of the analysis results, and further reducing the risks of development projects.

[0104] Although the above methods are illustrated and described as a series of acts for simplicity of explanation, it is to be understood and appreciated that these methods are not limited by the order of the acts, as some acts may occur in a different order and / or concurrently with other acts from those illustrated and described herein or not illustrated and described herein but understandable to those skilled in the art according to one or more embodiments.

[0105] Those skilled in the art will appreciate that information, signals, and data may be represented using any of a variety of different technologies and techniques. For example, data, instructions, commands, information, signals, bits, symbols, and chips referenced throughout the foregoing description may be represented by voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields or particles, or any combination thereof.

[0106] Those skilled in the art will further appreciate that the various illustrative logic blocks, modules, circuits, and algorithmic steps described in conjunction with the embodiments disclosed herein can be implemented as electronic hardware, computer software, or a combination of the two. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps are generally described above in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system. A skilled person may implement the described functionality in different ways for each specific application, but such implementation decisions should not be interpreted as resulting in a departure from the scope of the present invention.

[0107] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. The software module may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor so that the processor can read and write information from / to the storage medium. In an alternative, the storage medium may be integrated into the processor. The processor and storage medium may reside in an ASIC. The ASIC may reside in a user terminal. In an alternative, the processor and storage medium may reside in a user terminal as discrete components.

[0108] In one or more exemplary embodiments, the functions described may be implemented in hardware, software, firmware, or any combination thereof. If implemented in software as a computer program product, the functions may be stored on or transmitted via a computer-readable medium as one or more instructions or code. Computer-readable media includes both computer storage media and communication media, including any medium that facilitates the transfer of a computer program from one location to another. A storage medium may be any available medium that can be accessed by a computer. By way of example and not limitation, such computer-readable media may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, 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. Any connection is also properly referred to as a computer-readable medium. For example, if software is transmitted from a website, server, or other remote source using a coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwave, then the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included in the definition of medium. As used herein, disk and disc include compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), floppy disk and Blu-ray disc, where disks typically reproduce data magnetically, while discs reproduce data optically with lasers. Combinations of the above should also be included within the scope of computer-readable media.

[0109] The previous description of the disclosure is provided to enable any person skilled in the art to make or use the disclosure. Various modifications to the disclosure will be apparent to those skilled in the art, and the general principles defined herein may be applied to other variations without departing from the spirit or scope of the disclosure. Thus, the disclosure is not intended to be limited to the examples and designs described herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A software development target analysis device, characterized in that: include: Data collection module, used to obtain multi-source data about the user's software development goals; as well as The analysis module includes a value point extraction unit, a fact point extraction unit, a correlation analysis unit, and a purpose summarization unit, wherein: The value point extraction unit is configured to extract at least one value point pursued by the user from the multi-source data, The fact point extraction unit is configured to extract at least one fact point from the multi-source data. The association analysis unit is configured to: perform semantic analysis on the extracted value points and fact points to determine the association between the fact points and the value points, The purpose summarizing unit is configured to: determine key value points whose total weight is greater than a preset first threshold value based on the relevance of each fact point to each value point; and determine the software development goal based on the key value points and their corresponding related fact points.

2. The analysis device according to claim 1, wherein The multi-source data is selected from at least one of project management data, online documents, emails, and meeting recordings. The data acquisition module is configured with a business data acquisition unit, which is connected to the user company's project management system, online document sharing system, mailbox server, and conference recording transcription system to obtain the user's multi-source data on the software development goals.

3. The analysis device according to claim 2, wherein The data acquisition module is also provided with a pre-processing unit, which is configured to: performing deduplication processing on the acquired multi-source data; Removing HTML tags from the deduplication-processed data; Performing unified encoding processing on the data after the HTML tags are removed; as well as The data processed by the unified encoding is divided into a plurality of semantically complete paragraphs.

4. The analysis device according to claim 1, wherein The value point extraction unit is equipped with a pre-trained and fine-tuned large language model, which is configured as follows: According to a preset prompting project, questions are asked to each of the multi-source data one by one to extract at least one value point pursued by the user.

5. The analysis device according to claim 4, wherein The data acquisition module is provided with a user data acquisition unit for acquiring characteristic data of multiple users to classify them. The value point extraction unit is further configured to: ask questions to each of the multi-source data of each category of users one by one according to a preset prompt project, so as to respectively extract at least one value point pursued by the corresponding category of users.

6. The analysis device according to claim 1, wherein The fact point extraction unit is configured with a pre-trained named entity recognition model, which is configured as follows: According to pre-named entities of multiple preset dimensions, each of the multi-source data is parsed one by one, and based on the identified named entities, a fact point of at least one fact is formed, wherein the multiple preset dimensions are selected from at least one of a person's name, an organization's name, a position's name, a product's name, an action's name, a degree's name, and a time length.

7. The analysis device according to claim 6, wherein The fact point extraction unit is further configured to: Determining a reliability weight based on the data source and / or clarity of the fact point; Determining an importance weight according to the number of occurrences of the fact point in the multi-source data; Determining a fact point weight corresponding to the fact point according to the reliability weight and the importance weight; as well as Valid fact points whose fact point weights reach a preset second threshold are retained, and invalid fact points whose fact point weights are less than the second threshold are filtered out.

8. The analysis device according to claim 7, wherein The fact point extraction unit is also configured with a pre-trained clarity classification model, which is configured as follows: In response to a fact point forming at least one fact, a semantic analysis is performed on the fact point via the clarity classification model to determine a corresponding clarity classification.

9. The analyzing device according to claim 1, wherein The association analysis unit is configured with a pre-trained association classification model. The step of performing semantic analysis on the extracted value points and fact points to determine the association of each fact point with each value point includes: Combining each of the value points with each of the fact points into a high-dimensional vector to calculate the correlation between the two; A high-dimensional vector whose correlation reaches a preset third threshold is input into the association classification model to determine the association label of the fact vector to the corresponding value vector, wherein a positive association label indicates that the fact vector supports the corresponding value vector, and a negative association label indicates that the fact vector opposes the corresponding value vector.

10. The analysis device according to claim 9, wherein The step of determining the key value points whose total weight is greater than a preset first threshold based on the relevance of each fact point to each value point includes: For each of the value points, mark the fact point weights of the fact points corresponding to each of the positive correlation labels as positive, and calculate the cumulative value thereof as the total weight of the value point; and The value points whose total weight is greater than the first threshold are determined as the key value points.

11. The analysis device according to claim 10, wherein The step of determining the software development goal based on the key value points and their corresponding relevant fact points includes: The value vector of the key value point V 1 and its corresponding fact vector of related fact points F 1. Fill in the preset software development goal templates respectively to output the software development goals.

12. The analysis device according to claim 10, wherein The purpose summarizing unit is further configured to: For each of the value points, mark the fact point weights of the fact points corresponding to each of the reverse correlation labels as negative, and calculate the accumulated value to serve as the total weight of the value point; as well as The value points whose total weight is less than the fourth threshold are determined as the valid value points.

13. The analysis device according to claim 12, wherein The step of determining the software development goal based on the key value points and their corresponding relevant fact points includes: The value vector of the value point that is both the key value point and the effective value point V 2 and its corresponding fact vector of related fact points F 2. Fill in the preset software development goal templates respectively to output the software development goals.

14. The analysis device according to claim 1, wherein Also includes: A display module is used to provide a display interface with at least one tab to display the software development goal and its corresponding value points, fact points, support relationships and / or opposition relationships, wherein the support relationships and / or the opposition relationships are displayed in the form of a relationship diagram, and the weights between the value point and the first fact point supporting it and / or the second fact point opposing it are shown.

15. The analysis device according to claim 14, wherein The display module also supports editing functions and is configured to: According to the user's editing operation on the relationship diagram, value points and / or fact points are added or subtracted on the display interface, and / or the relationship between at least one of the value points and the corresponding fact point is adjusted.

16. The analysis device according to claim 15, wherein The analysis device further includes a modification auxiliary module, which is connected to the display module and the purpose summarizing unit of the analysis module and is configured to: Obtaining modification instructions provided by the user based on natural language and / or images; performing natural language parsing and / or image parsing on the modification instruction to determine at least one editing operation instruction for the relationship graph; Transmitting the at least one editing operation instruction to the display module to implement the corresponding editing operation; as well as The at least one editing operation instruction is transmitted to the target summarizing unit to redefine the key value point.

17. A method for analyzing software development goals, characterized in that: The following steps are involved: Obtain multi-source data from users about software development goals; Extracting at least one value point pursued by the user and at least one fact point from the multi-source data; Performing semantic analysis on the extracted value points and fact points to determine the relevance of each fact point to each value point; Determining key value points whose total weight is greater than a preset first threshold value based on the relevance of each fact point to each value point; as well as The software development goal is determined based on the key value points and their corresponding relevant fact points.

18. A computer-readable storage medium having computer instructions stored thereon, characterized in that: When the computer instructions are executed by a processor, the software development target analysis method according to claim 17 is implemented.

Images