Project management method for intelligent dialogue and computer equipment

Abstract

The invention discloses an intelligent dialogue project management method and computer equipment, and relates to the field of artificial intelligence, and the method comprises the steps: obtaining a user question; performing semantic analysis on the user question to obtain a user demand; matching the user demand with a question set in a preset question and answer knowledge base to obtain a target question; determining a corresponding target answer in a preset question and answer knowledge base according to the target question; returning the target answer to the user and obtaining user feedback; in response to user confirmation in the user feedback to trigger an automatic process operation in the project system, determining a target request operation for triggering the project system according to the target problem; determining a corresponding target interface parameter in a preset program interface request library according to the target request operation; and returning the target operation result to the user. By implementing the method, the question and answer dialog box can be associated with the project system, a link from dialogue to execution is opened, data sharing and interaction are realized, and the efficiency is improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence, and in particular to a project management method and computer device for intelligent dialogue. Background Art

[0002] With the rapid development of information technology, project management, as a comprehensive activity of systematic planning, organization, command, coordination, control and evaluation, increasingly relies on computer technology to improve its efficiency and effectiveness. Among many project management tools, intelligent dialogue systems are favored by enterprises because of their strong interactivity and convenient operation. Through intelligent dialogue systems, project-related personnel can query project information through natural language to improve the efficiency of project management.

[0003] However, relevant technologies may not be able to cope with more complex project management needs. For example, these systems may lack personalization and initiative in user interaction experience, making it difficult to provide more customized services based on the user's specific situation. Summary of the invention

[0004] The present application provides a project management method and computer device for intelligent dialogue, which are used to associate a question-and-answer dialog box with a project system, open up a link from dialogue to execution, realize data sharing and interaction, and improve efficiency.

[0005] In a first aspect, the present application provides a project management method for intelligent dialogue, which is applied to a computer device, and the method includes: obtaining a user question, which is a text content entered by a user in a dialog box; performing semantic analysis on the user question to obtain a user demand; matching the user demand with a question set in a preset question and answer knowledge base to obtain a target question, the preset question and answer knowledge base includes a question set and an answer set, and the questions in the question set correspond to the answers in the answer set one by one; determining a corresponding target answer in the preset question and answer knowledge base according to the target question; returning the target answer to the user and obtaining user feedback, the user feedback is used to determine whether the user triggers an automated process operation in a project system; in response to the user confirming in the user feedback that an automated process operation in the project system is triggered, determining a target request operation to trigger the project system according to the target question; determining corresponding target interface parameters in a preset program interface request library according to the target request operation, the preset program interface request library includes interface parameters corresponding to each request operation in the project system; after determining that the project system executes the target request operation through the target interface parameters to obtain a target operation result, the target operation result is returned to the user.

[0006] In the above embodiment, the computer device understands the real needs of the user through semantic analysis, rather than matching by keywords, which improves the accuracy of understanding the needs. At the same time, the computer device uses the preset question and answer knowledge base to match the user needs to determine the target question, so as to quickly give high-quality and accurate target answers, reduce user waiting time, and improve user experience. The computer device pre-stores the interface parameters required for each request operation in the preset program interface request library, and directly calls it during execution, reducing the development workload and reducing the risk of errors. In addition, the computer device obtains user feedback. If the user needs to trigger the automated process operation in the project system, the question and answer dialog box is associated with the project system, and connected through the interface parameters, opening up the link from dialogue to execution, realizing data sharing and interaction, and improving efficiency.

[0007] In combination with some embodiments of the first aspect, in some embodiments, semantic analysis is performed on user questions to obtain user needs, specifically including: performing preprocessing operations on user questions, the preprocessing operations including word segmentation, removal of stop words and part-of-speech tagging to obtain question text; extracting key information from the question text to construct a semantic representation of the question; and converting the semantic representation of the question into user needs.

[0008] In the above embodiment, the computer device removes the noise in the user's question through preprocessing operations, providing clear input for subsequent semantic analysis. The computer device extracts key information from the question text to construct a semantic representation of the question, grasps the core content of the user's question, and reflects the intelligence of semantic analysis. Traditional keyword matching often cannot accurately understand the true semantics of the sentence and is prone to mismatching. This solution uses semantic analysis technology to mine semantic information from the shallow to the deep through multiple steps, greatly improving the accuracy of demand understanding.

[0009] In combination with some embodiments of the first aspect, in some embodiments, user needs are matched with a question set in a preset question and answer knowledge base to obtain a target question, the preset question and answer knowledge base includes a question set and an answer set, and the questions in the question set correspond one-to-one with the answers in the answer set, specifically including: calculating the semantic similarity between the user needs and each question in the question set; determining the question with the highest semantic similarity to the user needs as the target question.

[0010] In the above embodiment, the computer device matches the user's needs with each question in the question set by calculating the semantic similarity, and the question with the highest semantic similarity to the user's needs is used as the final matching result, i.e., the target question, thereby reducing misunderstandings and wrong matches, and thus providing a more accurate answer. Automatically matching the question with the highest semantic similarity to the user's needs reduces manual intervention, speeds up retrieval, and thus improves the efficiency of the entire project management process.

[0011] In combination with some embodiments of the first aspect, in some embodiments, in response to user confirmation in user feedback that triggers an automated process operation in a project system, determining a target request operation to trigger the project system according to a target question, specifically including: judging the type of user feedback; when the user feedback is that the user denies triggering an automated process operation in the project system, reacquiring the user question and performing semantic analysis to obtain new user needs; when the user feedback is that the user needs to supplement the automated process operation in the project system, acquiring supplementary information, and determining the precise target operation in combination with the target question and the supplementary information; when the user feedback is that the user confirms that the automated process operation in the project system is triggered, determining the target request operation to trigger the project system according to the target question.

[0012] In the above embodiment, the subsequent process is dynamically adjusted according to user feedback, which reflects the flexibility and humanization of the solution. When the user denies triggering the automated process operation in the project system, it means that the user may not want to perform this operation, the computer equipment has an identification error, and the user needs need to be re-acquired; when the user needs to supplement the automated process operation in the project system, it means that the information obtained by the computer is not comprehensive enough, and the user is guided to further clarify the supplement to achieve a complete and accurate target operation; when the user confirms the triggering of the automated process operation in the project system, the target request operation of the project system is determined according to the target problem. The accuracy of demand understanding is improved, and the execution plan can be further refined and optimized, and the overall process is more intelligent and efficient. Traditional human-computer interaction is often rigid, either completely dominated by machines or completely determined by people, and lacks flexibility. This solution introduces a dynamic execution mechanism driven by user feedback to improve the user's operating experience.

[0013] In combination with some embodiments of the first aspect, in some embodiments, after the step of matching user needs with a question set in a preset question and answer knowledge base to obtain a target question, the preset question and answer knowledge base includes a question set and an answer set, and the questions in the question set correspond one-to-one with the answers in the answer set, the method also includes: if the question set in the preset question and answer knowledge base does not contain a question corresponding to the user need, generating a new question according to the user need; determining a new answer corresponding to the new question; and returning the new answer to the user.

[0014] In the above embodiment, when facing new demands that are not covered by the preset question-and-answer knowledge base, the computer device intelligently generates new questions, gives new answers corresponding to the new questions, and dynamically generates question-and-answer pairs to supplement and improve the preset question-and-answer knowledge base, which is more versatile and intelligent. Traditional knowledge base applications are usually unable to handle problems beyond the coverage of the knowledge base, and are helpless when encountering unknown areas. This solution introduces a dynamic generation mechanism to deal with this situation, making the boundaries of the preset question-and-answer knowledge base more open and extensible, greatly enhancing practicality.

[0015] In combination with some embodiments of the first aspect, in some embodiments, after determining that the project system executes the target request operation through the interface request parameters to obtain the target operation result, and returning the target operation result to the user, the method also includes: when receiving a request to add to the preset question and answer knowledge base, adding the new questions and new answers to the preset question and answer knowledge base; when receiving a request to modify the preset question and answer knowledge base, providing a function of modifying defective questions and defective answers, and updating the content of the defective questions and the content of the defective answers; when receiving a request to delete the preset question and answer knowledge base, deleting invalid questions and invalid answers corresponding to the invalid questions in the preset question and answer knowledge base.

[0016] In the above embodiment, the computer device provides modification and deletion functions for the original content, and can continuously correct the existing erroneous information and outdated information in the preset question and answer knowledge base, dynamically correct errors, and maintain a high degree of accuracy and timeliness of the preset question and answer knowledge base. New questions and new answers are persisted in the preset question and answer knowledge base, so that the preset question and answer knowledge base continues to grow through learning and accumulation, forming a positive cycle. Traditional knowledge bases usually lack dynamic maintenance and optimization methods, and the knowledge is seriously outdated and cannot keep up with actual needs. This solution has established a set of operating methods around the preset question and answer knowledge base, which greatly improves the practicality and sustainability of the application of the preset question and answer knowledge base.

[0017] In combination with some embodiments of the first aspect, in some embodiments, the method also includes: obtaining user information; matching the user information with member information of the project system to determine the user identity; based on the user identity, filtering the content in the project system that the user has the authority to operate, and building a personalized question and answer knowledge base corresponding to the user.

[0018] In the above embodiment, the computer device introduces user identity, so that intelligent dialogue and knowledge retrieval can be adjusted according to the user identity, which greatly improves the degree of personalization and interactive experience. The content of the project system seen by different users will be dynamically adjusted according to the user's authority to avoid information leakage. Traditional knowledge base applications often open all knowledge to all users, lacking the necessary privacy protection and authority control. This solution cleverly uses user information to personalize the knowledge base, achieving a better balance between interactive experience and information security.

[0019] In a second aspect, an embodiment of the present application provides a computer device, comprising: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to cause the computer device to execute the method described in the first aspect and any possible implementation method of the first aspect.

[0020] In a third aspect, an embodiment of the present application provides a computer program product comprising instructions, which, when executed on a computer device, enables the computer device to execute the method described in the first aspect and any possible implementation of the first aspect.

[0021] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, comprising instructions, which, when executed on a computer device, enable the computer device to execute the method described in the first aspect and any possible implementation of the first aspect.

[0022] It is understandable that the computer device provided in the second aspect, the computer program product provided in the third aspect, and the computer storage medium provided in the fourth aspect are all used to execute the method provided in the embodiment of the present application. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method, which will not be repeated here.

[0023] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. Due to the use of intelligent semantic analysis and question-answer knowledge base matching technology, computer equipment can deeply understand user intentions, determine target questions, and quickly provide high-quality and accurate target answers, effectively solving problems such as insufficient intelligence level, low conversation quality, and poor user experience in related technologies, thereby realizing efficient, accurate, and humanized intelligent conversational project management.

[0024] 2. Due to the adoption of a dynamic execution mechanism driven by user feedback, computer equipment can give users greater initiative and control in human-computer collaboration, flexibly adjust execution strategies according to user intentions, and effectively solve the problems of rigid system processes and inability to dynamically optimize in related technologies, thereby achieving flexibility and efficiency improvements in process execution.

[0025] 3. Due to the use of customized personalized question-and-answer knowledge base technology, computer equipment can dynamically allocate knowledge within the corresponding authority scope according to the identity information of different users, effectively solving the problems of chaotic knowledge access and stereotyped user experience in related technologies, and thus realizing personalized intelligent services based on user characteristics. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 This is a flowchart of a project management method for intelligent dialogue in an embodiment of the present application; Figure 2 is another flowchart of the project management method of intelligent dialogue in an embodiment of the present application; Figure 3 It is a schematic diagram of a physical device structure of a computer device in an embodiment of the present application. DETAILED DESCRIPTION

[0027] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification of the present application, the singular expressions "one", "a kind of", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to any or all possible combinations comprising one or more of the listed items.

[0028] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0029] See also Figure 1 , which is a flow chart of the project management method of intelligent dialogue in an embodiment of the present application.

[0030] S101, obtaining a user question, where the user question is text content entered by the user in a dialog box; The computer device obtains the user's question, that is, the text content entered by the user in the dialog box through the keyboard, touch screen, etc. The dialog box can be a graphical human-computer interaction interface or a voice interaction dialogue scene, which is not limited here. The text content entered by the user in the dialog box obtained by the computer device can contain one or more complete sentences, expressing the user's needs or inquiries about certain aspects of project management. The computer device needs to accurately obtain the full content of the user's question to provide a data basis for subsequent analysis.

[0031] For example, in the intelligent customer service dialog box of a project system, the user enters a question such as "How is the progress of the project this week?" The computer device obtains the user's question expressed in natural language by monitoring the user's input on the UI interface. It should be noted that in addition to text input, user questions can also be obtained through voice input. In this case, the computer device needs to use voice recognition technology to convert the voice signal into text. In short, the computer device needs to obtain the user's question expressed in natural language as input for subsequent processing.

[0032] S102, performing semantic analysis on user questions to obtain user needs; The computer device performs semantic analysis on the user question obtained in step S101 to obtain the user requirements. Here, semantic analysis is a key technology in the field of natural language processing, aiming to enable the computer device to "understand" the true intention expressed by the user, that is, the user requirements, just like a human being. Taking the above example, the user question "How is the project progress this week?" actually contains two key pieces of information: time (this week) and theme (project progress), and the user requirement is to understand the degree of project completion within this week. Through complex semantic analysis algorithms, such as rule-based, statistical, or deep learning methods, the computer device extracts this structured information from the user question and transforms it into a form that the computer device can understand and process. Semantic analysis enables the computer to have the ability to understand complex languages, greatly improving the intelligence level of communication and interaction.

[0033] Optionally, generally, semantic analysis of the user question to obtain the user requirements can be achieved through the following steps: perform preprocessing operations on the user question, where the preprocessing operations include word segmentation, stop word removal, and part-of-speech tagging to obtain the question text; extract key information from the question text to construct a question semantic representation; and transform the question semantic representation into the user requirements.

[0034] First, the computer device performs preprocessing operations on the user question. Preprocessing operations are common operations in natural language processing, aiming to convert the original text into a format that is easier for the computer to understand and process. Among them, word segmentation is to split continuous text into individual words, such as splitting "How to view the project progress" into words like "How", "view", "project", "progress", etc. Stop word removal is to remove function words, conjunctions, etc. that have no actual contribution to semantic understanding in the sentence, such as "of", "吗" (in Chinese, equivalent to "ma" in English). Part-of-speech tagging is to assign corresponding part-of-speech tags to each word, such as noun, verb, adjective, etc. After these processes, the user question is structured into a neat text composed of key words. This step removes the redundant information in the original text and highlights the key semantic components.

[0035] Next, the computer device extracts key information from the preprocessed question text and constructs a semantic representation. Common information extraction techniques include named entity recognition, keyword extraction, semantic role labeling, etc. For example, named entity recognition can discover specific project names, dates, people's names, etc. mentioned in the question text; keyword extraction can find the central words in the question text, such as "progress", "deadline", etc.; semantic role labeling can analyze the semantic roles of words in the question text, such as "project" is the object of "view". The computer device organizes the extracted semantic information according to a certain data structure to form a question semantic representation, which not only contains the key content of the question but also reflects the logical relationship between the contents. This step is a further refinement and structuring of the question semantics.

[0036] Finally, the computer device converts the constructed semantic representation of the question into user needs. The computer device performs intent recognition on the semantic representation of the question to determine which intent category it belongs to. Common intent recognition methods include rule-based methods and machine learning-based methods. The former summarizes the key features of the intent category and formulates corresponding matching rules; the latter uses labeled intent data sets to train classification models. After identifying the intent category, the corresponding key information is extracted from the semantic representation of the question and filled into the slot of the intent category to form a structured user need, such as "Query project progress {project name: xxx}". This step completes the transformation from the user's natural language question to the structured user need that the system can execute.

[0037] S103, matching the user's needs with a question set in a preset question-answering knowledge base to obtain a target question, wherein the preset question-answering knowledge base includes a question set and an answer set, and the questions in the question set correspond to the answers in the answer set one by one; The computer device matches the user needs obtained in step S103 with the question set in the preset question and answer knowledge base to obtain the target question most relevant to the user needs. The preset question and answer knowledge base here refers to a collection of common questions and corresponding answers that are stored in advance and summarized and sorted by professionals, usually organized in the form of question-answer pairs. Taking project management as an example, the preset question and answer knowledge base will contain various questions that are frequently consulted by project-related personnel, such as "how to view project progress" and "how to assess project delay risks". When a user asks a user question, the computer device will compare the question with the questions in the preset question and answer knowledge base one by one to determine the most matching target question. This matching usually utilizes the correspondence between the question and the answer in the question-answer pair.

[0038] Continuing with the example of the project progress question above, assuming that a question like "How to check the completion status of this week's project" already exists in the preset question-and-answer knowledge base, the computer device can identify it as the target question through semantic similarity matching, and then find the accurate answer, that is, the target answer.

[0039] Optionally, in general, the user needs are matched with a question set in a preset question and answer knowledge base to obtain a target question. The preset question and answer knowledge base includes a question set and an answer set. The one-to-one correspondence between the questions in the question set and the answers in the answer set can be achieved in the following ways: calculating the semantic similarity between the user needs and each question in the question set; determining the question with the highest semantic similarity to the user needs as the target question.

[0040] First, the computer device calculates the semantic similarity between the user demand and each question in the question set. Semantic similarity is used to measure the degree of similarity between the user demand and each question in the question set at the semantic level. The computer device represents the user demand and each question in the question set as a semantic vector, and then calculates the similarity between these semantic vectors to obtain the semantic similarity between the user demand and each question in the question set. Common semantic vector representation methods include TF-IDF based on word frequency, text vector based on word vector weighting, etc. These methods can capture the key semantic information of the text. The calculation of vector similarity can use cosine similarity, Euclidean distance, etc. Through these calculations, the user demand and each question in the question library obtain a semantic similarity. The higher the semantic similarity, the closer the semantics.

[0041] Next, the computer device finds the question most similar to the user's needs as the target question based on the semantic similarity. Specifically, the computer device sorts the semantic similarities between all user needs and each question in the question library, and takes the question with the highest semantic similarity to the user's needs as the final target question.

[0042] For example, a user asks "When will this project be completed?" The preset question-and-answer knowledge base includes questions such as "When will the project be completed?", "When will the project start?", and "What are the conditions for project completion?". The computer device calculates the semantic similarity between the user's needs and these questions, and the semantic similarities obtained are 0.9, 0.5, and 0.6 respectively. Therefore, the question with the highest semantic similarity, "When will the project be completed?", is selected as the final matched target question, and the corresponding target answer can be directly replied to the user.

[0043] S104, determining a corresponding target answer in a preset question-and-answer knowledge base according to the target question; The computer device needs to find the corresponding target answer in the preset question and answer knowledge base according to the target question determined in step S103. Since there is a one-to-one correspondence between questions and answers in the preset question and answer knowledge base, the target answer can be locked through the target question. For example, if the target question is determined to be "How to view the completion progress of this week's project", and there is a question-answer pair of "How to view the completion progress of this week's project" and "You can view the completion progress of all projects within this week in the progress report module of the project system" in the preset question and answer knowledge base, then the computer device can determine "You can view the completion progress of all projects within this week in the progress report module of the project system" as the target answer that is finally returned to the user based on this corresponding relationship. The corresponding mechanism of the preset question and answer knowledge base can avoid the risk of the computer device piecing together the answer by itself, thereby ensuring the standardization and quality of the answer.

[0044] S105, returning the target answer to the user and obtaining user feedback, where the user feedback is used to determine whether the user triggers an automated process operation in the project system; The computer device returns the target answer determined in step S104 directly to the user. At the same time, the computer device also needs to obtain the user's feedback on the target answer to determine whether the user wishes to further trigger the automated process operation in the project system. For example, for the target question of "viewing the progress of this week's project", after the computer device returns the target answer, it can ask the user "Do you need to directly open the progress report to view the progress of this week's project?" If the user selects "Yes", it confirms that the user wants to trigger the operation of automatically opening the report module, and the computer device can continue the subsequent process. If the user selects "No", it indicates that the user only needs an answer and does not need to trigger the automated process operation in the project system. Introducing user feedback can determine the user's true intentions and avoid the consequences of subjective assumptions of the computer device.

[0045] S106, in response to the user confirmation in the user feedback triggering the automated process operation in the project system, determining the target request operation that triggers the project system according to the target problem; If the computer device obtains user feedback in step S105 that confirms the triggering of automated process operations in the project system, it is necessary to decide to send a target operation request to the project system based on the target question. For example, if the target question is "How to view the progress of this week's project" and the user also confirms that he wants to directly open the project system to view it, the computer device can determine that it needs to send a target operation request of "open the progress report" to the project system. The computer device semantically matches the determined target question based on the user question, and then maps it to the actual operation in the project system, completing the closed loop from the user's intelligent dialogue to the project system behavior, and achieving the effect of coordinated cooperation between the intelligent dialogue and the project system.

[0046] Optionally, under normal circumstances, in response to user confirmation in user feedback that triggers the automated process operation in the project system, determining the target request operation that triggers the project system according to the target question can be achieved in the following way: judging the type of user feedback; when the user feedback is that the user denies triggering the automated process operation in the project system, re-acquiring the user question and performing semantic analysis to obtain new user needs; when the user feedback is that the user needs to supplement the automated process operation in the project system, obtaining supplementary information, and determining the precise target operation in combination with the target question and the supplementary information; when the user feedback is that the user confirms that the automated process operation in the project system is triggered, determining the target request operation that triggers the project system according to the target question.

[0047] First, the computer device needs to determine the type of user feedback. The types of user feedback mainly include the following situations: when the user feedback is that the user denies triggering the automated process operation in the project system, it means that the user may not want to perform subsequent operations or the computer device has misunderstood the user's needs. The computer device needs to re-acquire the user's question and perform semantic analysis to obtain new user needs; when the user feedback is that additional information is needed to trigger the automated process operation in the project system, it means that the information obtained by the computer device is not comprehensive and accurate. At this time, the computer device needs to guide the user to provide additional information, and combine the target question and additional information to determine the precise target operation; when the user feedback is to confirm triggering the automated process operation in the project system, the target request operation that actually needs to be triggered can be directly determined based on the target question.

[0048] For example, for the question "How much project progress has been completed this week?", if the user denies opening the progress report, the computer device will need to ask the user again; if the user says that additional time range information is needed, the computer device will ask the user to specify the time period to accurately locate the operation; if the user directly confirms opening the progress report, the computer device can determine "open the progress report" as the target request operation.

[0049] The above method allows computer equipment to dynamically adjust subsequent processes based on different user feedback, making the overall interaction more intelligent and humane, and avoiding unnecessary consequences caused by machine subjective conjecture.

[0050] S107, determining corresponding target interface parameters in a preset program interface request library according to the target request operation, wherein the preset program interface request library includes interface parameters corresponding to each request operation in the project system; In this step, the computer device needs to find the corresponding target interface parameters in the preset program interface request library according to the target request operation determined in step S106, so as to call the interface of the project system later. The preset program interface request library here predefines the mapping relationship between various request operations in the project system (such as opening modules, exporting reports, etc.) and the interface parameters required for them. For example, if the target request operation is "open progress report", there will be such a mapping relationship in the preset program interface request library: "open progress report" -> "ReportID=123, TimeSpan=week". The computer device directly obtains the target interface parameters required to trigger this target request operation. Using the preset program interface request library, it is possible to avoid the need to redefine the interface parameters every time, reduce duplication of work, and improve work efficiency.

[0051] S108. After determining that the project system executes the target request operation through the target interface parameters to obtain the target operation result, the target operation result is returned to the user.

[0052] The computer device needs to call the interface of the project system and pass in the target interface parameters determined in step S107, such as ReportID and TimeSpan, to trigger the execution of the target request operation, such as opening a specific progress report. After the project system successfully executes the target request operation, the computer device needs to obtain the target operation result, such as the content of the report, and then the computer device returns the content of the report to the user. At this point, the entire process from the user asking a question to the computer device presenting the result is completed. For example, the user may initially ask "How much project progress has been completed this week", and after a series of steps, the computer device intelligently understands the user's intention and directly returns a specific project progress report for the user to view. This achieves natural language interaction and system integration, and improves the user experience.

[0053] In the above embodiment, the computer device understands the real needs of the user through semantic analysis, rather than matching by keywords, which improves the accuracy of understanding the needs. At the same time, the computer device uses the preset question and answer knowledge base to match the user needs to determine the target question, so as to quickly give high-quality and accurate target answers, reduce user waiting time, and improve user experience. The computer device pre-stores the interface parameters required for each request operation in the preset program interface request library, and directly calls it during execution, reducing the development workload and reducing the risk of errors. In addition, the computer device obtains user feedback. If the user needs to trigger the automated process operation in the project system, the question and answer dialog box is associated with the project system, and connected through the interface parameters, opening up the link from dialogue to execution, realizing data sharing and interaction, and improving efficiency.

[0054] See also Figure 2 , which is another flow chart of the project management method of intelligent dialogue in an embodiment of the present application.

[0055] S201, obtaining a user question, where the user question is text content entered by the user in a dialog box; For details, please refer to step S101, which will not be described in detail here.

[0056] S202, performing semantic analysis on user questions to obtain user needs; For details, please refer to step S102, which will not be described in detail here.

[0057] S203, matching the user's needs with a question set in a preset question-answering knowledge base to obtain a target question, wherein the preset question-answering knowledge base includes a question set and an answer set, and the questions in the question set correspond to the answers in the answer set one by one; For details, please refer to step S103, which will not be described in detail here.

[0058] S204: if the question set in the preset question-answering knowledge base does not contain a question corresponding to the user's requirement, then generate a new question according to the user's requirement; If the computer device finds through the previous matching that there are no questions in the question set in the preset question and answer knowledge base that completely correspond to the user's needs, then the computer device needs to actively generate new questions based on the user's needs. This situation usually occurs when the user asks a novel question that is not covered by the preset question and answer knowledge base. In order to cope with this unknown demand, the computer device needs to dynamically construct a new question based on the characteristics of the user's needs to supplement the preset question and answer knowledge base. For example, if the user asks "What are the bug statistics of the Huaxia project this month", and there are no questions related to bug statistics in the preset question and answer knowledge base, the computer device can generate a new question "What are the bug statistics of the Huaxia project this month" based on the key information in the user's needs. This mechanism can expand the coverage of the preset question and answer knowledge base, cope with more unknown situations, avoid only being able to make "not understanding the problem" answers, and improve the user experience.

[0059] S205, determining a new answer corresponding to the new question; The computer device needs to determine a credible new answer for the new question generated in step S204. There are many specific ways to obtain the answer. For example, the computer device can calculate the answer to the new question through the statistical system in the project system, or send the question to the relevant manual customer service, and the customer service will judge the best answer based on experience, and then feed it back to the computer device; you can also train an answer generation model to try to automatically construct the answer. In short, the computer device needs to obtain a credible new answer through some means, form a question-answer pair with the new question, and add it to the preset question and answer knowledge base. For example, for the new question "Bug statistics of Huaxia project this month" constructed in step S204, the computer device can query the statistical system to obtain "The total number of bugs in Huaxia project this month is 27, including 5 serious bugs" as the answer. Such collaborative acquisition of questions and answers can realize the processing of new needs, continuously optimize and improve the knowledge base, and enhance the intelligent response capability of the system.

[0060] S206, returning the newly added answer to the user; The computer device needs to return the new answer corresponding to the new question generated in step S205 to the user, which can avoid the situation where the interaction is interrupted due to only replying "I don't understand the question", making the interaction process smoother and more intelligent.

[0061] For example, if a user asks "What is the average time to resolve bugs found during the testing phase?", but there are no questions related to bug resolution time in the preset question-and-answer knowledge base, the computer device will first generate a corresponding new question "What is the average time to resolve bugs found during the testing phase?", and then calculate a new answer by querying statistical data: "According to statistics, the average time to resolve bugs found during the testing phase is 2 days." The computer device returns this new answer to the user, completing the response to the new question.

[0062] When returning a new answer, the computer device also needs to let the user know that the answer comes from newly generated content rather than the matching result of the existing preset question and answer knowledge base. Special prompt language can be used to inform the user that "this question is not yet in my knowledge base, and the answer after automatic analysis is..." At the same time, the quality of the answer also needs to be considered. For new answers with uncertain reliability, a confirmation feedback step can be added to avoid giving users wrong information.

[0063] In short, appropriately returning new answers can reduce the limitations of the conversation caused by the preset Q&A knowledge base and achieve smoother and more intelligent Q&A interaction. However, attention should still be paid to the control of answer quality to avoid misleading users.

[0064] S207, determining a corresponding target answer in a preset question-and-answer knowledge base according to the target question; For details, please refer to step S104, which will not be described in detail here.

[0065] S208, returning the target answer to the user and obtaining user feedback, where the user feedback is used to determine whether the user triggers an automated process operation in the project system; For details, please refer to step S105, which will not be described in detail here.

[0066] S209, in response to the user confirming in the user feedback that the automated process operation in the project system is triggered, determining a target request operation to trigger the project system according to the target problem; For details, please refer to step S106, which will not be described in detail here.

[0067] S210, determining corresponding target interface parameters in a preset program interface request library according to the target request operation, wherein the preset program interface request library includes interface parameters corresponding to each request operation in the project system; For details, please refer to step S107, which will not be described in detail here.

[0068] S211, after determining that the project system executes the target request operation through the target interface parameters to obtain the target operation result, the target operation result is returned to the user; For details, please refer to step S108, which will not be described in detail here.

[0069] S212: When a request to add to the preset question and answer knowledge base is received, the newly added question and the newly added answer are added to the preset question and answer knowledge base; The computer device can accept requests to add new content to the preset question and answer knowledge base, and such requests usually come from the administrator or relevant professionals of the preset question and answer knowledge base. When the computer receives a request to add to the preset question and answer knowledge base, the computer device needs to formally add the newly added questions and corresponding newly added answers generated by the previous question and answer dialogue to the preset question and answer knowledge base for persistent storage. For example, for new questions such as "This Month's Huaxia Project Bug Statistics" generated during the dialogue and their new answers, the computer device can call the editing interface of the preset question and answer knowledge base to store the new questions and new answers in the preset question and answer knowledge base. In this way, the new question and answer pair officially becomes part of the preset question and answer knowledge base, providing materials for matching the next time it is used. By continuously adding new content, the preset question and answer knowledge base can be continuously enriched and expanded.

[0070] S213. When receiving a request to modify the preset question and answer knowledge base, provide a function of modifying defective questions and defective answers, and update the content of the defective questions and the content of the defective answers; The computer device can also accept modification requests for the preset question and answer knowledge base, which are mainly used to correct the erroneous information in the preset question and answer knowledge base. When the computer device receives a request to modify the preset question and answer knowledge base, the computer device can provide a special interface for the administrator of the preset question and answer knowledge base to select and confirm the defective questions and defective answers that need to be modified, and enter the updated correct information. For example, if the answer to a question is outdated due to changes in circumstances, the answer can be corrected to keep it up to date. The computer device will call the update interface of the preset question and answer knowledge base, use the new question text and answer text to replace the original erroneous information, and realize the update and error correction of knowledge. This mechanism can ensure the accuracy and effectiveness of the content of the preset question and answer knowledge base and avoid the adverse effects caused by erroneous knowledge.

[0071] S214: upon receiving a request to delete the preset question and answer knowledge base, deleting invalid questions and invalid answers corresponding to the invalid questions from the preset question and answer knowledge base; The computer device can also accept a request to delete the preset question and answer knowledge base. When requested to delete content, the computer device will ask for confirmation of the invalid questions to be deleted and the invalid answers corresponding to the invalid questions, and provide an interface for the administrator of the preset question and answer knowledge base to select the invalid question and answer pairs to be deleted. After receiving the selection, the computer device will call the deletion interface of the preset question and answer knowledge base to delete the corresponding question and answer data from the preset question and answer knowledge base so that it no longer participates in question and answer matching, and promptly clean up the invalid content in the preset question and answer knowledge base, such as old version information that has been modified and replaced. At the same time, some old content that is no longer applicable can also be deleted according to actual usage. S215, obtaining user information; The computer device needs to obtain the identity information of the user currently in conversation with it, that is, the user information, in preparation for the subsequent implementation of the personalized question-and-answer function. User information can be obtained in a variety of ways, such as the user's account number for logging into the system, or personal information actively provided by the user during the conversation. After obtaining the user information, the computer device can confirm the identity of the interlocutor and perform personalized processing. When obtaining user information, it is necessary to protect the user's privacy, obtain only necessary information, and comply with laws and regulations.

[0072] S216, matching the user information with the member information of the project system to determine the user identity; The computer device needs to match the user information obtained in step S217 with the member information stored in the background of the project system to determine the user identity, such as the name, account number and other information provided by the user. The computer device will query the member library of the project system to see if there is matching member information. If a matching member is found, it can be determined that the current user identity is a project member or management role. If there is no matching result, it may be accessed by non-system internal personnel.

[0073] S217. According to the user identity, filter the content that the user has the authority to operate in the project system, and build a personalized question and answer knowledge base corresponding to the user.

[0074] The computer device will filter out the content that the user has the authority to operate based on the user identity determined in step S216 and the authority control mechanism in the project system, and use this to build a personalized question and answer knowledge base corresponding to the user. For example, for an ordinary member accessing the system, he can only view the project information he is involved in. Then, when answering his questions, the computer device only needs to enable the knowledge content within his authority. For department managers, their authority is broader, and the question and answer knowledge base needs to cover all projects within the department. The content of the personalized question and answer knowledge base of different users is therefore different.

[0075] The construction of this personalized question-and-answer knowledge base can achieve more accurate answers to questions that users are concerned about, while also ensuring that sensitive information will not be leaked due to exceeding permissions. Compared with the traditional uniform external knowledge base, the personalized question-and-answer knowledge base is more in line with the needs of different users, providing more humane and adaptable services, reducing information overload, and improving user experience.

[0076] In the above embodiment, due to the use of a dynamic execution mechanism driven by user feedback, the computer device can give users greater initiative and control in human-computer collaboration, flexibly adjust the execution strategy according to the user's intention, effectively solve the problem of rigid system processes and inability to dynamically optimize in related technologies, and thus achieve flexibility and efficiency improvement in process execution. In addition, the technology of customizing a personalized question-and-answer knowledge base is adopted, so the computer device can dynamically allocate knowledge within the corresponding authority range according to the identity information of different users, effectively solving the problem of chaotic knowledge access and stereotyped user experience in related technologies, and thus realizing personalized intelligent services based on user characteristics.

[0077] The following describes the computer device in the embodiment of the present invention from the perspective of hardware processing. Figure 3 , which is a schematic diagram of a physical device structure of a computer device in an embodiment of the present application.

[0078] It should be noted that Figure 3 The structure of the computer device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0079] like Figure 3 As shown, the computer device includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage part 308 to the random access memory (RAM) 303, such as executing the method described in the above embodiment. In RAM 303, various programs and data required for system operation are also stored. CPU 301, ROM 302 and RAM 303 are connected to each other through bus 304. Input / output (I / O) interface 305 is also connected to bus 304.

[0080] The following components are connected to the I / O interface 305: an input section 306 including an audio input device, a button switch, etc.; an output section 307 including a liquid crystal display (LCD) and an audio output device, an indicator light, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 310 as needed so that a computer program read therefrom is installed into the storage section 308 as needed.

[0081] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 309, and / or installed from a removable medium 311. When the computer program is executed by the central processing unit (CPU) 301, various functions defined in the present invention are performed.

[0082] It should be noted that specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, apparatus, or device.

[0083] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in an order different from that marked in the accompanying drawings.

[0084] Specifically, the computer device of this embodiment includes a processor and a memory. The memory stores a computer program. When the computer program is executed by the processor, the project management method of intelligent dialogue provided in the above embodiment is implemented.

[0085] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the computer device described in the above embodiment; or may exist independently without being assembled into the computer device. The above storage medium carries one or more computer programs, and when the above one or more computer programs are executed by a processor of the computer device, the computer device implements the intelligent dialogue project management method provided in the above embodiment.

[0086] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0087] As used in the above embodiments, the term "when..." may be interpreted to mean "if..." or "after..." or "in response to determining..." or "in response to detecting...", depending on the context. Similarly, the phrases "upon determining..." or "if (the stated condition or event) is detected" may be interpreted to mean "if determining..." or "in response to determining..." or "upon detecting (the stated condition or event)" or "in response to detecting (the stated condition or event)", depending on the context.

[0088] Those skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. When the programs are executed, they can include the processes of the above-mentioned method embodiments. The aforementioned storage media include: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.

Claims

1. An intelligent dialogue project management method, characterized in that: Applied to a computer device, the method comprises: Obtaining a user question, where the user question is text content entered by the user in a dialog box; Perform semantic analysis on the user questions to obtain user needs; Matching the user demand with a question set in a preset question-answering knowledge base to obtain a target question, wherein the preset question-answering knowledge base includes a question set and an answer set, and the questions in the question set correspond to the answers in the answer set one by one; Determine a corresponding target answer in the preset question-and-answer knowledge base according to the target question; Returning the target answer to the user and obtaining user feedback, wherein the user feedback is used to determine whether the user triggers an automated process operation in the project system; In response to the user confirmation in the user feedback triggering the automated process operation in the project system, determining, according to the target question, to trigger the target request operation of the project system; Determine the corresponding target interface parameters in a preset program interface request library according to the target request operation, wherein the preset program interface request library includes interface parameters corresponding to each request operation in the project system; After determining that the project system executes the target request operation through the target interface parameters to obtain a target operation result, the target operation result is returned to the user.

2. The method according to claim 1, characterized in that The semantic analysis of the user question to obtain the user demand specifically includes: Performing a preprocessing operation on the user question, wherein the preprocessing operation includes word segmentation, stop word removal and part-of-speech tagging to obtain a question text; Extract key information from the question text and construct a semantic representation of the question; The problem semantic representation is converted into the user requirement.

3. The method according to claim 1, characterized in that The user demand is matched with a question set in a preset question-answer knowledge base to obtain a target question, wherein the preset question-answer knowledge base includes a question set and an answer set, and the questions in the question set correspond to the answers in the answer set one by one, specifically including: Calculating the semantic similarity between the user demand and each question in the question set; A question having the highest semantic similarity to the user requirement is determined as the target question.

4. The method according to claim 1, characterized in that: The triggering of the automated process operation in the project system in response to the user confirmation in the user feedback and determining the target request operation that triggers the project system according to the target question specifically include: Determining the type of the user feedback; When the user feedback indicates that the user denies triggering the automated process operation in the project system, reacquire the user question and perform semantic analysis to acquire new user requirements; When the user feedback indicates that the user needs to supplement the triggering of the automated process operation in the project system, the supplementary information is obtained, and the precise target operation is determined by combining the target question and the supplementary information; When the user feedback is the user confirmation triggering the automated process operation in the project system, the target request operation that triggers the project system is determined according to the target question.

5. The method according to claim 1, characterized in that After the step of matching the user demand with a question set in a preset question-and-answer knowledge base to obtain a target question, wherein the preset question-and-answer knowledge base includes a question set and an answer set, and the questions in the question set correspond to the answers in the answer set one by one, the method further includes: If the question set in the preset question-and-answer knowledge base does not contain a question corresponding to the user's requirement, generating a new question according to the user's requirement; Determine a new answer corresponding to the new question; The newly added answer is returned to the user.

6. The method according to claim 5, characterized in that After determining that the project system executes the target request operation through the interface request parameter to obtain a target operation result, returning the target operation result to the user specifically includes: When receiving a request to add to the preset question and answer knowledge base, adding the newly added question and the newly added answer to the preset question and answer knowledge base; When receiving a request to modify the preset question and answer knowledge base, providing a function of modifying defect questions and defect answers, and updating the content of the defect questions and the content of the defect answers; When a request to delete the preset question and answer knowledge base is received, invalid questions and invalid answers corresponding to the invalid questions are deleted from the preset question and answer knowledge base.

7. The method according to claim 1, characterized in that The method further comprises: Get user information; Matching the user information with the member information of the project system to determine the user identity; According to the user identity, the content in the project system that the user has the authority to operate is filtered, and a personalized question and answer knowledge base corresponding to the user is constructed.

8. A computer device, characterized in that: The computer device comprises: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code comprises computer instructions, and the one or more processors call the computer instructions so that the computer device executes the method as described in any one of claims 1-7.

9. A computer-readable storage medium comprising instructions, characterized in that: When the instructions are executed on a computer device, the computer device is caused to execute the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that When the computer program product is executed on a computer device, the computer device is caused to execute the method according to any one of claims 1 to 7.

Images