Enterprise question and answer recommendation method and device

Abstract

The present invention discloses a method and device for recommending enterprise questions and answers, which relates to the field of artificial intelligence technology. The method includes: establishing a business node knowledge graph of an enterprise system; for each business node in the enterprise system, determining reserved questions and answers corresponding to different employee positions at the business node, and operational process information for solving different processing faults at the business node; detecting the current business node at which a target employee logs into the enterprise system to perform business processing; when the target business processing feature fails to match at least one of the historical business processing features of the current business node in the business node knowledge graph, determining that the target employee has a processing fault at the current business node; and recommending the reserved questions and answers for the position at the current business node in the enterprise processing solution knowledge base and the operational process information of the current business node to the target employee. The present invention is used to improve the efficiency and accuracy of enterprise question and answer recommendations, increase employee satisfaction, and reduce operating costs.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a method and device for recommending enterprise questions and answers. Background Art

[0002] This section is intended to provide a background or context to the embodiments of the invention that are recited in the claims. No statement herein is admitted to be prior art by virtue of its inclusion in this section.

[0003] Existing customer service systems display frequently asked questions to customers before connecting to human customer service. Traditional intelligent customer service Q&A systems often rely on a fixed knowledge base, using the same scripts and questions for all users. This knowledge base is also manually updated. Large enterprises have numerous IT systems within them. Therefore, customer service systems serving fixed employees can customize scripts and Q&A based on user positions, levels, departments, and time of employment. This allows intelligent customer service Q&A to resolve employee issues, reducing the number of manual customer service calls and lowering labor costs.

[0004] However, existing Q&A recommendation technology can only be manually maintained by operations staff. Questions are the same for all employees, making it impossible to provide personalized recommendations for different employee positions, and even more difficult to automatically update and optimize the customer service Q&A knowledge base. For large enterprises with numerous and complex IT systems, the inability to personalize Q&A for each employee results in low efficiency in employee query and resolution. Summary of the Invention

[0005] An embodiment of the present invention provides a method for recommending enterprise Q&A, which is used to improve the efficiency and accuracy of enterprise Q&A recommendations, increase employee satisfaction, and reduce operating costs. The method includes:

[0006] Establish a business node knowledge graph for the enterprise system based on the historical business processing characteristics of different business nodes in the enterprise system; the historical business processing characteristics include the following characteristics: business node processing duration, frequency of interface jumps related to the business node, frequency of information call related to the business node, node jump sequence, and average jump interval duration; the business node knowledge graph is used to characterize the connection relationship between each business node in the enterprise system and the historical business processing characteristics of each business node;

[0007] For each business node in the enterprise system, keyword extraction is performed on the historical Q&A records of employees in different positions at that business node to obtain the question keywords and answer keywords for each question and answer in the historical Q&A records; based on the frequency of occurrence of the question keywords and answer keywords, reserved questions and answers corresponding to different employee positions at that business node are determined;

[0008] For each business node in the enterprise system, the node operation information of different employees under the business node is extracted to determine the operation process information for solving different processing faults under the business node; the operation process information is one or more node operation behaviors after the occurrence of historical processing faults in the node operation information;

[0009] Establishing an enterprise fault handling solution knowledge base based on the reserved questions and answers associated with different employee positions at each business node and the operational process information of each business node; the enterprise fault handling solution knowledge base includes the reserved questions and answers associated with different employee positions at each business node and the operational process information of each business node;

[0010] Detect the current business node where the target employee logs into the enterprise system to process business;

[0011] Matching the target business processing feature of the current business node with the business node knowledge graph; if the matching result indicates that the target business processing feature fails to match at least one of the historical business processing features of the current business node in the business node knowledge graph, determining that the target employee has a processing failure at the current business node;

[0012] When it is determined that the target employee has a problem handling at the current business node, the position of the target employee is determined; the reserved questions and answers for the position under the current business node in the enterprise's fault handling solution knowledge base and the operation process information of the current business node are recommended to the target employee.

[0013] An embodiment of the present invention further provides an enterprise Q&A recommendation device for improving the efficiency and accuracy of enterprise Q&A recommendations, increasing employee satisfaction, and reducing operating costs. The device includes:

[0014] A business node knowledge graph establishment module is used to establish a business node knowledge graph for the enterprise system based on the historical business processing characteristics of different business nodes in the enterprise system. The historical business processing characteristics include the following characteristics: business node processing duration, frequency of interface jumps related to the business node, frequency of calling information related to the business node, node jump sequence, and average jump interval duration. The business node knowledge graph is used to characterize the connection relationship between each business node in the enterprise system and the historical business processing characteristics of each business node.

[0015] The reserved question and answer determination module is used to extract keywords from the historical question and answer records of employees in different positions at each business node in the enterprise system, obtain the question keywords and answer keywords of each question and answer in the historical question and answer records; and determine the reserved questions and answers corresponding to different employee positions at the business node based on the frequency of occurrence of the question keywords and answer keywords;

[0016] An operation process information determination module is used to extract the node operation information of different employees at each business node in the enterprise system and determine the operation process information for solving different processing faults at the business node; the operation process information is one or more node operation behaviors after the occurrence of historical processing faults in the node operation information;

[0017] An enterprise fault handling solution knowledge base establishment module is configured to establish an enterprise fault handling solution knowledge base based on the reserved questions and answers associated with different employee positions at each business node and the operational process information for each business node; the enterprise fault handling solution knowledge base includes the reserved questions and answers associated with different employee positions at each business node and the operational process information for each business node;

[0018] The current business node detection module is used to detect the current business node where the target employee logs into the enterprise system to process business;

[0019] an information matching module, configured to perform information matching on the target business processing feature of the current business node and the business node knowledge graph, and determine that a processing failure has occurred on the target employee at the current business node when a matching result indicates that the target business processing feature fails to match at least one of the historical business processing features of the current business node in the business node knowledge graph;

[0020] The information recommendation module is used to determine the position of the target employee when it is determined that the target employee has a fault to handle at the current business node; and recommend the reserved questions and answers for the position under the current business node in the enterprise fault handling solution knowledge base and the operation process information of the current business node to the target employee.

[0021] An embodiment of the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned enterprise question and answer recommendation method when executing the computer program.

[0022] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned enterprise question and answer recommendation method is implemented.

[0023] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the above-mentioned enterprise question and answer recommendation method.

[0024] In an embodiment of the present invention, a business node knowledge graph of an enterprise system is established based on the historical business processing characteristics of different business nodes of the enterprise system; the historical business processing characteristics include the following characteristics: the duration of the business node processing process, the frequency of interface jumps involving the business node, the frequency of calling information involving the business node, the node jump sequence, and the average duration of the jump interval; the business node knowledge graph is used to characterize the connection relationship between each business node of the enterprise system and the historical business processing characteristics of each business node; for each business node under the enterprise system, the historical question and answer records of employees in different positions of the business node are subjected to keyword extraction to obtain the question keywords and answer keywords of each question and answer in the historical question and answer records; according to the question keywords The frequency of occurrence of words and answer keywords is used to determine the reserved questions and answers corresponding to different employee positions in the business node; for each business node under the enterprise system, the node operation information of different employees under the business node is extracted to determine the operation process information for solving different processing faults under the business node; the operation process information is one or more node operation behaviors after the historical processing fault occurs in the node operation information; according to the reserved questions and answers for different employee positions at each business node, and the operation process information of each business node, an enterprise fault processing solution knowledge base is established; the enterprise fault processing solution knowledge base includes the reserved questions and answers associated with different employee positions under each business node, and the operation process information of each business node; detection target The target employee logs into the enterprise system to perform business processing on the current business node; matches the target business processing characteristics of the current business node with the business node knowledge graph; when the matching result indicates that the target business processing characteristics fail to match at least one characteristic of the historical business processing characteristics of the current business node in the business node knowledge graph, it is determined that the target employee has a processing fault at the current business node; when it is determined that the target employee has a processing fault at the current business node, the position of the target employee is determined; the reserved questions and answers for the position under the current business node in the enterprise fault processing solution knowledge base and the operation process information of the current business node are recommended to the target employee, which is consistent with the technology of providing fixed questions and answers for employees in the enterprise system in the prior art. Compared with the technical solution, by based on the employee's position, when a processing failure occurs in the employee's current processing node, the reserved questions and answers of the position under the current business node in the enterprise's fault processing solution knowledge base and the operation process information of the current business node can be recommended to the employee. The intelligent recommendation of questions and answers can be instructed to the employee, and the operation process of solving the current processing failure can also be provided to the employee. This avoids the problem of recommending fixed questions and answers to different employees under the existing technology, which makes it difficult to recommend personalized questions and answers to employees. It improves the recommendation efficiency and accuracy of the enterprise's questions and answers, and can enable the enterprise customer service system to solve employees' problems to the greatest extent, improve employee satisfaction, and reduce the number of times employees use manual customer service, thereby reducing operating costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0026] Figure 1 Schematic diagram of a process for recommending enterprise questions and answers according to an embodiment of the present invention;

[0027] Figure 2 This is a specific example diagram of a method for recommending enterprise questions and answers in an embodiment of the present invention;

[0028] Figure 3 This is a specific example diagram of a method for recommending enterprise questions and answers in an embodiment of the present invention;

[0029] Figure 4 This is a specific example diagram of a method for recommending enterprise questions and answers in an embodiment of the present invention;

[0030] Figure 5 Schematic diagram of the structure of a device for recommending enterprise questions and answers according to an embodiment of the present invention;

[0031] Figure 6 Schematic diagram of a computer device used for enterprise Q&A recommendation in an embodiment of the present invention. DETAILED DESCRIPTION

[0032] To make the purpose, technical solutions and advantages of the embodiments of the present invention more clear, the embodiments of the present invention are further described in detail below with reference to the accompanying drawings. Here, the exemplary embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0033] The term "and / or" herein simply describes an association relationship, indicating that three relationships can exist. For example, A and / or B can represent the existence of A alone, the simultaneous existence of A and B, and the existence of B alone. In addition, the term "at least one" herein refers to any combination of at least two of any one or more of a plurality of items. For example, "at least one of A, B, and C" can represent any one or more elements selected from the set consisting of A, B, and C.

[0034] In the description of this specification, the terms "include", "including", "have", "contain", etc. are all open terms, which mean including but not limited to. The descriptions with reference to the terms "one embodiment", "a specific embodiment", "some embodiments", "for example", etc. mean that the specific features, structures or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. The order of steps involved in each embodiment is used to schematically illustrate the implementation of the present application, and the order of steps therein is not limited and can be appropriately adjusted as needed.

[0035] The acquisition, storage, use, and processing of data in this application's technical solution comply with relevant national laws and regulations.

[0036] Existing customer service systems display frequently asked questions to customers before connecting to human customer service. Traditional intelligent customer service Q&A systems often rely on a fixed knowledge base, using the same scripts and questions for all users. This knowledge base is also manually updated. Large enterprises have numerous IT systems within them. Therefore, customer service systems serving fixed employees can customize scripts and Q&A based on user positions, levels, departments, and time of employment. This allows intelligent customer service Q&A to resolve employee issues, reducing the number of manual customer service calls and lowering labor costs.

[0037] However, existing Q&A recommendation technology can only be manually maintained by operations staff. Questions are the same for all employees, making it impossible to provide personalized answer recommendations for different employees, and even more difficult to automatically update and optimize the customer service Q&A knowledge base. For large enterprises with numerous and complex IT systems, the inability to personalize Q&A for each employee results in low efficiency in employee query and resolution.

[0038] In order to solve the above problems, the embodiment of the present invention provides an enterprise Q&A recommendation method to improve the efficiency and accuracy of enterprise Q&A recommendations, improve employee satisfaction, and reduce operating costs. Figure 1 , the method may include:

[0039] Step 101: Establish a business node knowledge graph for the enterprise system based on historical business processing characteristics of different business nodes in the enterprise system; the historical business processing characteristics include the following characteristics: business node processing duration, frequency of interface jumps related to the business node, frequency of calling information related to the business node, node jump sequence, and average jump interval duration; the business node knowledge graph is used to characterize the connection relationship between each business node in the enterprise system and the historical business processing characteristics of each business node;

[0040] Step 102: For each business node in the enterprise system, keyword extraction is performed on the historical question and answer records of employees in different positions at the business node to obtain question keywords and answer keywords for each question and answer in the historical question and answer records; and based on the frequency of occurrence of the question keywords and answer keywords, reserved questions and answers corresponding to the different employee positions at the business node are determined;

[0041] Step 103: For each business node in the enterprise system, process extraction is performed on the node operation information of different employees in the business node to determine the operation process information for resolving different processing faults in the business node; the operation process information is one or more node operation behaviors after a historical processing fault occurs in the node operation information;

[0042] Step 104: Establishing an enterprise fault handling solution knowledge base based on the reserved questions and answers associated with different employee positions at each business node and the operation process information for each business node; the enterprise fault handling solution knowledge base includes the reserved questions and answers associated with different employee positions at each business node and the operation process information for each business node;

[0043] Step 105: Detect the current business node where the target employee logs into the enterprise system to perform business processing;

[0044] Step 106: Matching the target business processing feature of the current business node with the business node knowledge graph. If the matching result indicates that the target business processing feature fails to match at least one of the historical business processing features of the current business node in the business node knowledge graph, it is determined that the target employee has a processing failure at the current business node.

[0045] Step 107: When it is determined that the target employee has a fault handling problem at the current business node, the position of the target employee is determined; the reserved questions and answers for the position under the current business node in the enterprise fault handling solution knowledge base and the operation process information of the current business node are recommended to the target employee.

[0046] In an embodiment of the present invention, a business node knowledge graph of an enterprise system is established based on the historical business processing characteristics of different business nodes of the enterprise system; the historical business processing characteristics include the following characteristics: the duration of the business node processing process, the frequency of interface jumps involving the business node, the frequency of calling information involving the business node, the node jump sequence, and the average duration of the jump interval; the business node knowledge graph is used to characterize the connection relationship between each business node of the enterprise system and the historical business processing characteristics of each business node; for each business node under the enterprise system, the historical question and answer records of employees in different positions of the business node are subjected to keyword extraction to obtain the question keywords and answer keywords of each question and answer in the historical question and answer records; according to the question keywords The frequency of occurrence of words and answer keywords is used to determine the reserved questions and answers corresponding to different employee positions in the business node; for each business node under the enterprise system, the node operation information of different employees under the business node is extracted to determine the operation process information for solving different processing faults under the business node; the operation process information is one or more node operation behaviors after the historical processing fault occurs in the node operation information; according to the reserved questions and answers for different employee positions at each business node, and the operation process information of each business node, an enterprise fault processing solution knowledge base is established; the enterprise fault processing solution knowledge base includes the reserved questions and answers associated with different employee positions under each business node, and the operation process information of each business node; detection target The target employee logs into the enterprise system to perform business processing on the current business node; matches the target business processing characteristics of the current business node with the business node knowledge graph; when the matching result indicates that the target business processing characteristics fail to match at least one characteristic of the historical business processing characteristics of the current business node in the business node knowledge graph, it is determined that the target employee has a processing fault at the current business node; when it is determined that the target employee has a processing fault at the current business node, the position of the target employee is determined; the reserved questions and answers for the position under the current business node in the enterprise fault processing solution knowledge base and the operation process information of the current business node are recommended to the target employee, which is consistent with the technology of providing fixed questions and answers for employees in the enterprise system in the prior art. Compared with the technical solution, by based on the employee's position, when a processing failure occurs in the employee's current processing node, the reserved questions and answers of the position under the current business node in the enterprise's fault processing solution knowledge base and the operation process information of the current business node can be recommended to the employee. The intelligent recommendation of questions and answers can be instructed to the employee, and the operation process of solving the current processing failure can also be provided to the employee. This avoids the problem of recommending fixed questions and answers to different employees under the existing technology, which makes it difficult to recommend personalized questions and answers to employees. It improves the recommendation efficiency and accuracy of the enterprise's questions and answers, and can enable the enterprise customer service system to solve employees' problems to the greatest extent, improve employee satisfaction, and reduce the number of times employees use manual customer service, thereby reducing operating costs.

[0047] During specific implementation, first, a business node knowledge graph of the enterprise system is established based on the historical business processing characteristics of different business nodes of the enterprise system; the historical business processing characteristics include the following characteristics: the duration of the business node processing process, the frequency of interface jumps involving business nodes, the frequency of calling information involving business nodes, the node jump sequence, and the average duration of the jump interval; the business node knowledge graph is used to characterize the connection relationship between each business node of the enterprise system and the historical business processing characteristics of each business node.

[0048] In an embodiment, historical business processing characteristics may include the following characteristics: business node processing process duration, business node-related interface jump frequency, business node-related information call frequency, node jump order, and average jump interval duration; wherein, business node-related interface jump frequency is used to describe the frequency of page jumps involved in the processing operation of the business node; business node-related information call frequency is used to describe the call frequency of calling information in different database data tables involved in the processing operation of the business node; node jump order is used to describe the node jump order of the previous node and the next node containing the business node; average jump interval duration is used to describe the average interval duration of the previous node containing the business node jumping to the business node, and the average interval duration of the business node jumping to the next node.

[0049] In an embodiment, the knowledge graph created can help enterprises train their employees on specific issues, help companies understand issues that employees do not understand, enable the company's customer service system to solve employee problems to the greatest extent possible, improve employee satisfaction, and reduce the number of times employees use manual customer service.

[0050] In one embodiment, the business node knowledge graph is used to characterize the connection relationship between each business node in the enterprise system and the historical business processing characteristics of each business node. It includes the historical business processing characteristics of each business node and the connection relationship between different business nodes. For example, the connection relationship can be represented by a tree-like node network.

[0051] During specific implementation, after establishing a business node knowledge graph of the enterprise system based on the historical business processing characteristics of different business nodes of the enterprise system, for each business node under the enterprise system, keyword extraction is performed on the historical question and answer records of employees in different positions of the business node to obtain the question keywords and answer keywords of each question and answer in the historical question and answer records; based on the frequency of occurrence of the question keywords and answer keywords, the reserved questions and answers corresponding to the different employee positions of the business node are determined.

[0052] In this embodiment, for each business node in the enterprise system, keyword extraction is performed on the historical question and answer records of employees in different positions in the business node to obtain the question keywords and answer keywords of each question and answer in the historical question and answer records, including:

[0053] For each business node in the enterprise system, keywords are extracted from the historical Q&A records of employees in different positions at that business node to determine the question keywords and answer keywords for each employee's position in the historical Q&A records;

[0054] Based on the frequency of occurrence of the question keywords and answer keywords, the reserved questions and answers corresponding to different employee positions in the business node are determined, including:

[0055] Determine the frequency of occurrence of question keywords and answer keywords for each employee position;

[0056] Determine the first weight of the question keyword based on the frequency of occurrence of the question keyword;

[0057] Determine the second weight of the answer keyword based on the occurrence frequency of the answer keyword and the employee's rating;

[0058] The question content corresponding to the question keyword with the first weight exceeding the first threshold is used as the target question content in the reserved question and answer for the employee position;

[0059] The answer keyword with a second weight exceeding a second threshold among the multiple answer keywords corresponding to the target question content is used as the target answer content in the reserved question and answer for the employee position.

[0060] In one embodiment, the employee's historical question and answer records may include: questions asked by employees in different positions to the intelligent customer service system during historical business processing and the answers given by the intelligent customer service system; they may also include: questions asked by employees in different positions to humans (such as managers) during historical business processing and the answers given by humans.

[0061] During specific implementation, for each business node under the enterprise system, keyword extraction is performed on the historical question and answer records of employees in different positions at the business node to obtain the question keywords and answer keywords for each question and answer in the historical question and answer records; based on the frequency of occurrence of the question keywords and answer keywords, the reserved questions and answers corresponding to the different employee positions at the business node are determined, and then, for each business node under the enterprise system, process extraction is performed on the node operation information of different employees at the business node to determine the operation process information for solving different processing faults at the business node; the operation process information is one or more node operation behaviors after the historical processing fault occurs in the node operation information.

[0062] In one embodiment, the node operation information of different employees is used to describe the operation records of employees performing business processing under the business node. For example, clicking button B on interface A can jump to interface C.

[0063] In one embodiment, the operation process information is used to describe the employee's operation to solve the processing failure when the corresponding processing failure occurs in the historical operation record. For example, when clicking the B button through the A interface, it is impossible to jump to the C interface. You can click the D interface and then click the C interface on the D interface, thereby solving the processing failure of "when clicking the B button through the A interface, it is impossible to jump to the C interface".

[0064] This embodiment can extract the node operation information of different employees under each business node under the enterprise system, determine the operation process information for solving different processing faults under the business node, automatically obtain the processing methods for solving different processing faults in the historical operations of employees, and form operation process information for subsequent use by employees.

[0065] During specific implementation, for each business node under the enterprise system, the node operation information of different employees under the business node is extracted, and after the operation process information for solving different processing faults under the business node is determined, an enterprise fault processing solution knowledge base is established based on the reserved questions and answers of different employee positions at each business node and the operation process information of each business node; the enterprise fault processing solution knowledge base includes the reserved questions and answers associated with different employee positions at each business node, and the operation process information of each business node.

[0066] In one embodiment, the method further includes: obtaining feedback information of the target employee on the recommended reserved question and answer; the feedback information is used to indicate whether the employee clicks on the recommended reserved question and answer and the question and answer score for the recommended reserved question and answer;

[0067] Update the enterprise fault handling solution knowledge base based on the feedback information

[0068] In one embodiment, updating the enterprise fault handling solution knowledge base based on the feedback information includes:

[0069] Adjusting the first weight of the question keyword and the second weight of the answer keyword according to the feedback information;

[0070] Based on the adjusted first weight and second weight, the reserved questions and answers for different employee positions under different business nodes are re-determined.

[0071] In the above embodiment, it also includes:

[0072] When the feedback information indicates that the employee has not clicked on the recommended reserved question and answer, and / or the question and answer score for the recommended reserved question and answer is lower than a preset value, an alarm message carrying the feedback information is issued.

[0073] In specific implementation, after establishing an enterprise fault handling solution knowledge base based on the reserved questions and answers of different employee positions at each business node and the operation process information of each business node, the current business node where the target employee logs into the enterprise system to perform business processing is detected.

[0074] In specific implementation, after detecting the current business node where the target employee logs into the enterprise system to perform business processing, the target business processing characteristics of the current business node are matched with the business node knowledge graph. When the matching result indicates that the target business processing characteristics fail to match at least one of the historical business processing characteristics of the current business node in the business node knowledge graph, it is determined that the target employee has a processing failure at the current business node.

[0075] In one embodiment, when any of the following features in the target business processing features of the current business node: business node processing time, business node-related interface jump frequency, business node-related information call frequency, node jump sequence, and average jump interval duration, fails to match at least one feature in the historical business processing features of the current business node in the business node knowledge graph, it can be determined that the target employee has a processing failure at the current business node. At this time, a solution to the processing failure can be provided to the employee through subsequent steps.

[0076] During specific implementation, when the target business processing characteristics of the current business node are matched with the business node knowledge graph, and when the matching result indicates that the target business processing characteristics fail to match at least one of the historical business processing characteristics of the current business node in the business node knowledge graph, it is determined that the target employee has a processing fault at the current business node. When it is determined that the target employee has a processing fault at the current business node, the position of the target employee is determined; the reserved questions and answers for the position under the current business node in the enterprise fault processing solution knowledge base and the operation process information of the current business node are recommended to the target employee.

[0077] In the above embodiment, personalized Q&A recommendations for employees are achieved, which avoids the problem of the existing technology of recommending fixed Q&A to different employees and making it difficult to achieve personalized Q&A recommendations for employees, thereby improving the efficiency and accuracy of enterprise Q&A recommendations.

[0078] A specific embodiment is given below to illustrate the specific application of the method of the present invention. In this embodiment, the following steps may be included:

[0079] 1. Collection of user operation records, such as Figure 2 As shown:

[0080] All enterprise applications track employee behavior, collect employee position information, and detect the target business processing characteristics of the current business node when the target employee logs into the enterprise system to perform business processing. The information matching engine then generates the employee's problem.

[0081] For each business node in the enterprise system, keyword extraction is performed on the historical Q&A records of employees in different positions at that business node to obtain the question keywords and answer keywords for each question and answer in the historical Q&A records; based on the frequency of occurrence of the question keywords and answer keywords, reserved questions and answers corresponding to different employee positions at that business node are determined;

[0082] For each business node in the enterprise system, the node operation information of different employees under the business node is extracted to determine the operation process information for solving different processing faults under the business node; the operation process information is one or more node operation behaviors after the occurrence of historical processing faults in the node operation information;

[0083] An enterprise fault handling solution knowledge base is established based on the reserved questions and answers for different employee positions at each business node and the operating procedure information of each business node; the enterprise fault handling solution knowledge base includes the reserved questions and answers associated with different employee positions at each business node and the operating procedure information of each business node.

[0084] For example, we can collect information about employees' to-do items and anomalies, including missed workdays and unreimbursed travel. A recent use case involves collecting information about the systems employees access before entering customer service, such as clocking in and out of the office (OA), to recommend related issues. If a user accessed the OA system before entering customer service, it's likely they have an issue with it, so we recommend OA-related issues and solutions.

[0085] 2. Enterprise Q&A generation process:

[0086] Record employees' latest IT systems and operations;

[0087] Obtain and collect employee position information and detect the target business processing characteristics of the current business node where the target employee logs into the enterprise system to perform business processing;

[0088] The collected information is input into the question and answer matching engine, and the questions and answers provided to employees this time are matched based on the collected information.

[0089] Information collector: Provides a tracking interface to which all enterprise application access and key operations must be connected, thereby generating enterprise IT system access records and operation trajectories for each employee.

[0090] Question and answer matching engine: Generates tags based on employees' IT system access records and operation traces as well as employee information, especially department and position information, and selects multiple questions and answers from the knowledge base based on tags and matching rules.

[0091] Specifically, the matching rules are divided into four categories: user operation track, user position, user organization, and user tag. Their priorities can be set in the system; the weights of tags can also be set in the system settings to optimize and adjust the answers.

[0092] 3. You can build and update the knowledge base according to the following steps: Figure 3 and Figure 4 As shown:

[0093] An enterprise fault handling solution knowledge base is established based on the reserved questions and answers for different employee positions at each business node and the operating procedure information of each business node; the enterprise fault handling solution knowledge base includes the reserved questions and answers associated with different employee positions at each business node and the operating procedure information of each business node.

[0094] If the currently provided questions and answers do not solve the employee's problem, the questions raised by the employee using manual customer service will be recorded and the above database can be updated through manual matching.

[0095] The information obtained in the above three steps is input into the knowledge base engine, and the current knowledge base is updated according to the selected update rules.

[0096] The sources of knowledge base updates can include: 1. Human maintenance; 2. Question and answer collection from other enterprise systems; 3. Keyword extraction from answer records in enterprise systems; and 4. Feedback and ratings from employees. The frequency and weight of these four types of updates can be manually set to achieve database creation and updates.

[0097] In this specific embodiment, each employee's Q&A is personalized using information from both the employee and the enterprise's IT systems. This allows the customer service system to maximize the resolution of employee issues, improving efficiency and employee satisfaction. This also reduces the number of times employees use manual customer service, thereby reducing operational costs. Furthermore, each employee's response to a customer service Q&A question can be used to update and optimize the knowledge base in real time, making the customer service Q&A system more intelligent with use. Furthermore, the usage of each enterprise's IT systems can be collected and monitored in real time to further optimize the enterprise's IT systems.

[0098] Of course, it is understandable that the above detailed process may have other variations, and all relevant variations should fall within the scope of protection of the present invention.

[0099] In an embodiment of the present invention, a business node knowledge graph of an enterprise system is established based on the historical business processing characteristics of different business nodes of the enterprise system; the historical business processing characteristics include the following characteristics: the duration of the business node processing process, the frequency of interface jumps involving the business node, the frequency of calling information involving the business node, the node jump sequence, and the average duration of the jump interval; the business node knowledge graph is used to characterize the connection relationship between each business node of the enterprise system and the historical business processing characteristics of each business node; for each business node under the enterprise system, the historical question and answer records of employees in different positions of the business node are subjected to keyword extraction to obtain the question keywords and answer keywords of each question and answer in the historical question and answer records; according to the question keywords The frequency of occurrence of words and answer keywords is used to determine the reserved questions and answers corresponding to different employee positions in the business node; for each business node under the enterprise system, the node operation information of different employees under the business node is extracted to determine the operation process information for solving different processing faults under the business node; the operation process information is one or more node operation behaviors after the historical processing fault occurs in the node operation information; according to the reserved questions and answers for different employee positions at each business node, and the operation process information of each business node, an enterprise fault processing solution knowledge base is established; the enterprise fault processing solution knowledge base includes the reserved questions and answers associated with different employee positions under each business node, and the operation process information of each business node; detection target The target employee logs into the enterprise system to perform business processing on the current business node; matches the target business processing characteristics of the current business node with the business node knowledge graph; when the matching result indicates that the target business processing characteristics fail to match at least one characteristic of the historical business processing characteristics of the current business node in the business node knowledge graph, it is determined that the target employee has a processing fault at the current business node; when it is determined that the target employee has a processing fault at the current business node, the position of the target employee is determined; the reserved questions and answers for the position under the current business node in the enterprise fault processing solution knowledge base and the operation process information of the current business node are recommended to the target employee, which is consistent with the technology of providing fixed questions and answers for employees in the enterprise system in the prior art. Compared with the technical solution, by based on the employee's position, when a processing failure occurs in the employee's current processing node, the reserved questions and answers of the position under the current business node in the enterprise's fault processing solution knowledge base and the operation process information of the current business node can be recommended to the employee. The intelligent recommendation of questions and answers can be instructed to the employee, and the operation process of solving the current processing failure can also be provided to the employee. This avoids the problem of recommending fixed questions and answers to different employees under the existing technology, which makes it difficult to recommend personalized questions and answers to employees. It improves the recommendation efficiency and accuracy of the enterprise's questions and answers, and can enable the enterprise customer service system to solve employees' problems to the greatest extent, improve employee satisfaction, and reduce the number of times employees use manual customer service, thereby reducing operating costs.

[0100] The present invention also provides a device for recommending enterprise Q&A, as described in the following embodiments. Since the principle of solving the problem of the device is similar to that of the enterprise Q&A recommendation method, the implementation of the device can refer to the implementation of the enterprise Q&A recommendation method, and the repeated parts will not be repeated.

[0101] The embodiment of the present invention also provides an enterprise question and answer recommendation device to improve the efficiency and accuracy of enterprise question and answer recommendations, improve employee satisfaction, and reduce operating costs. Figure 5 As shown, the device includes:

[0102] The business node knowledge graph establishment module 501 is used to establish a business node knowledge graph for the enterprise system based on the historical business processing characteristics of different business nodes in the enterprise system. The historical business processing characteristics include the following characteristics: business node processing duration, frequency of interface jumps related to the business node, frequency of calling information related to the business node, node jump sequence, and average jump interval duration. The business node knowledge graph is used to represent the connection relationship between each business node in the enterprise system and the historical business processing characteristics of each business node.

[0103] The reserved question and answer determination module 502 is configured to perform keyword extraction on the historical question and answer records of employees at different positions in each business node of the enterprise system to obtain question keywords and answer keywords for each question and answer in the historical question and answer records; and determine the reserved questions and answers corresponding to the different employee positions at the business node based on the frequency of occurrence of the question keywords and answer keywords.

[0104] The operation process information determination module 503 is used to extract the node operation information of different employees at each business node in the enterprise system and determine the operation process information for solving different processing faults at the business node; the operation process information is one or more node operation behaviors after the occurrence of historical processing faults in the node operation information;

[0105] An enterprise fault handling solution knowledge base establishment module 504 is configured to establish an enterprise fault handling solution knowledge base based on the reserved questions and answers associated with different employee positions at each business node and the operational process information for each business node. The enterprise fault handling solution knowledge base includes the reserved questions and answers associated with different employee positions at each business node and the operational process information for each business node.

[0106] The current business node detection module 505 is used to detect the current business node at which the target employee logs into the enterprise system to perform business processing;

[0107] An information matching module 506 is configured to match the target business processing feature of the current business node with the business node knowledge graph, and determine that a processing failure has occurred at the current business node for the target employee when a matching result indicates that the target business processing feature fails to match at least one of the historical business processing features of the current business node in the business node knowledge graph.

[0108] Information recommendation module 507 is used to determine the target employee's position when it is determined that the target employee has a problem handling problem at the current business node. It then recommends to the target employee the reserved questions and answers for that position at the current business node in the enterprise's problem handling solution knowledge base, as well as the operational process information for the current business node.

[0109] In one embodiment, a question-answer determination module is reserved, specifically configured to:

[0110] For each business node in the enterprise system, keywords are extracted from the historical Q&A records of employees in different positions at that business node to determine the question keywords and answer keywords for each employee's position in the historical Q&A records;

[0111] Determine the frequency of occurrence of question keywords and answer keywords for each employee position;

[0112] Determine the first weight of the question keyword based on the frequency of occurrence of the question keyword;

[0113] Determine the second weight of the answer keyword based on the occurrence frequency of the answer keyword and the employee's rating;

[0114] The question content corresponding to the question keyword with the first weight exceeding the first threshold is used as the target question content in the reserved Q&A for the employee position;

[0115] The answer keyword with a second weight exceeding a second threshold among the multiple answer keywords corresponding to the target question content is used as the target answer content in the reserved question and answer for the employee position.

[0116] In one embodiment, it further includes:

[0117] Enterprise troubleshooting solution knowledge base update module, used for:

[0118] Obtaining feedback information from the target employee on the recommended reserved question and answer; the feedback information is used to indicate whether the employee clicks on the recommended reserved question and answer and the question and answer score for the recommended reserved question and answer;

[0119] The enterprise fault handling solution knowledge base is updated according to the feedback information.

[0120] In one embodiment, the enterprise fault handling solution knowledge base update module is specifically configured to:

[0121] Adjusting the first weight of the question keyword and the second weight of the answer keyword according to the feedback information;

[0122] Based on the adjusted first weight and second weight, the reserved questions and answers for different employee positions under different business nodes are re-determined.

[0123] In one embodiment, it further includes:

[0124] Alarm module, used for:

[0125] When the feedback information indicates that the employee has not clicked on the recommended reserved question and answer, and / or the question and answer score for the recommended reserved question and answer is lower than a preset value, an alarm message carrying the feedback information is issued.

[0126] An embodiment of the present invention provides an embodiment of a computer device for implementing all or part of the above-mentioned enterprise question-and-answer recommendation method. The computer device specifically includes the following contents:

[0127] A processor, a memory, a communications interface, and a bus; wherein the processor, memory, and communications interface communicate with each other via the bus; the communications interface is used to implement information transmission between related devices; the computer device can be a desktop computer, a tablet computer, a mobile terminal, etc., but this embodiment is not limited thereto. In this embodiment, the computer device can be implemented with reference to the embodiment for implementing the enterprise Q&A recommendation method and the embodiment for implementing the enterprise Q&A recommendation device, the contents of which are incorporated herein and repeated parts are not repeated.

[0128] Figure 6 1 is a schematic block diagram of the system structure of the computer device 1000 according to an embodiment of the present application. Figure 6 As shown, the computer device 1000 may include a central processor 1001 and a memory 1002; the memory 1002 is coupled to the central processor 1001. Figure 6 is exemplary; other types of structures may also be used to supplement or replace this structure to implement telecommunication functions or other functions.

[0129] In one embodiment, the enterprise Q&A recommendation function may be integrated into the central processing unit 1001. The central processing unit 1001 may be configured to perform the following control:

[0130] Establish a business node knowledge graph for the enterprise system based on the historical business processing characteristics of different business nodes in the enterprise system; the historical business processing characteristics include the following characteristics: business node processing duration, frequency of interface jumps related to the business node, frequency of information call related to the business node, node jump sequence, and average jump interval duration; the business node knowledge graph is used to characterize the connection relationship between each business node in the enterprise system and the historical business processing characteristics of each business node;

[0131] For each business node in the enterprise system, keyword extraction is performed on the historical Q&A records of employees in different positions at that business node to obtain the question keywords and answer keywords for each question and answer in the historical Q&A records; based on the frequency of occurrence of the question keywords and answer keywords, reserved questions and answers corresponding to different employee positions at that business node are determined;

[0132] For each business node in the enterprise system, the node operation information of different employees under the business node is extracted to determine the operation process information for solving different processing faults under the business node; the operation process information is one or more node operation behaviors after the occurrence of historical processing faults in the node operation information;

[0133] Establishing an enterprise fault handling solution knowledge base based on the reserved questions and answers associated with different employee positions at each business node and the operational process information of each business node; the enterprise fault handling solution knowledge base includes the reserved questions and answers associated with different employee positions at each business node and the operational process information of each business node;

[0134] Detect the current business node where the target employee logs into the enterprise system to process business;

[0135] Matching the target business processing feature of the current business node with the business node knowledge graph; if the matching result indicates that the target business processing feature fails to match at least one of the historical business processing features of the current business node in the business node knowledge graph, determining that the target employee has a processing failure at the current business node;

[0136] When it is determined that the target employee has a problem handling at the current business node, the position of the target employee is determined; the reserved questions and answers for the position under the current business node in the enterprise fault handling solution knowledge base and the operation process information of the current business node are recommended to the target employee.

[0137] In another embodiment, the enterprise Q&A recommendation device can be configured separately from the central processor 1001. For example, the enterprise Q&A recommendation device can be configured as a chip connected to the central processor 1001, and the enterprise Q&A recommendation function can be realized through the control of the central processor.

[0138] like Figure 6 As shown, the computer device 1000 may further include: a communication module 1003, an input unit 1004, an audio processor 1005, a display 1006, and a power supply 1007. It is worth noting that the computer device 1000 does not necessarily have to include Figure 6 In addition, the computer device 1000 may also include all components shown in Figure 6 For components not shown, reference may be made to the prior art.

[0139] like Figure 6 As shown, the central processing unit 1001 is sometimes also referred to as a controller or an operation control unit, and may include a microprocessor or other processor device and / or logic device. The central processing unit 1001 receives inputs and controls the operations of various components of the computer device 1000 .

[0140] Memory 1002 can be, for example, one or more of a cache, flash memory, hard drive, removable media, volatile memory, non-volatile memory, or other suitable devices. It can store the aforementioned failure-related information and a program that executes the relevant information. The CPU 1001 can execute the program stored in memory 1002 to implement information storage or processing.

[0141] Input unit 1004 provides input to CPU 1001. Input unit 1004 may be, for example, a keypad or touch input device. Power supply 1007 is used to provide power to computer device 1000. Display 1006 is used to display objects such as images and text. This display may be, for example, an LCD display, but is not limited thereto.

[0142] The memory 1002 may be a solid-state memory, such as a read-only memory (ROM), random access memory (RAM), or SIM card. Alternatively, it may be a memory that retains information even when power is off, can be selectively erased, and is provided with more data. Examples of such memory are sometimes referred to as EPROMs. The memory 1002 may also be some other type of device. The memory 1002 includes a buffer memory 1021 (sometimes referred to as a buffer). The memory 1002 may include an application / function storage unit 1022 for storing application programs and function programs or processes used by the central processing unit 1001 to execute the operations of the computer device 1000.

[0143] The memory 1002 may also include a data storage unit 1023 for storing data, such as contacts, digital data, pictures, sounds, and / or any other data used by the computer device. The driver storage unit 1024 of the memory 1002 may include various driver programs for the computer device for communication functions and / or for executing other functions of the computer device (such as messaging applications, address book applications, etc.).

[0144] The communication module 1003 is a transmitter / receiver 1003 that sends and receives signals via the antenna 1008. The communication module (transmitter / receiver) 1003 is coupled to the central processor 1001 to provide input signals and receive output signals, which may be the same as the case of a conventional mobile communication terminal.

[0145] Based on different communication technologies, multiple communication modules 1003 can be provided in the same computer device, such as a cellular network module, a Bluetooth module, and / or a wireless local area network module. The communication module (transmitter / receiver) 1003 is also coupled to a speaker 1009 and a microphone 1010 via an audio processor 1005 to provide audio output via the speaker 1009 and receive audio input from the microphone 1010, thereby implementing common telecommunication functions. The audio processor 1005 may include any suitable buffer, decoder, amplifier, etc. Furthermore, the audio processor 1005 is coupled to the central processing unit 1001, enabling local recording via the microphone 1010 and playback of stored audio via the speaker 1009.

[0146] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned enterprise question and answer recommendation method is implemented.

[0147] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the above-mentioned enterprise question and answer recommendation method.

[0148] In an embodiment of the present invention, a business node knowledge graph of an enterprise system is established based on the historical business processing characteristics of different business nodes of the enterprise system; the historical business processing characteristics include the following characteristics: the duration of the business node processing process, the frequency of interface jumps involving the business node, the frequency of calling information involving the business node, the node jump sequence, and the average duration of the jump interval; the business node knowledge graph is used to characterize the connection relationship between each business node of the enterprise system and the historical business processing characteristics of each business node; for each business node under the enterprise system, the historical question and answer records of employees in different positions of the business node are subjected to keyword extraction to obtain the question keywords and answer keywords of each question and answer in the historical question and answer records; according to the question keywords The frequency of occurrence of words and answer keywords is used to determine the reserved questions and answers corresponding to different employee positions in the business node; for each business node under the enterprise system, the node operation information of different employees under the business node is extracted to determine the operation process information for solving different processing faults under the business node; the operation process information is one or more node operation behaviors after the historical processing fault occurs in the node operation information; according to the reserved questions and answers for different employee positions at each business node, and the operation process information of each business node, an enterprise fault processing solution knowledge base is established; the enterprise fault processing solution knowledge base includes the reserved questions and answers associated with different employee positions under each business node, and the operation process information of each business node; detection target The target employee logs into the enterprise system to perform business processing on the current business node; matches the target business processing characteristics of the current business node with the business node knowledge graph; when the matching result indicates that the target business processing characteristics fail to match at least one characteristic of the historical business processing characteristics of the current business node in the business node knowledge graph, it is determined that the target employee has a processing fault at the current business node; when it is determined that the target employee has a processing fault at the current business node, the position of the target employee is determined; the reserved questions and answers for the position under the current business node in the enterprise fault processing solution knowledge base and the operation process information of the current business node are recommended to the target employee, which is consistent with the technology of providing fixed questions and answers for employees in the enterprise system in the prior art. Compared with the technical solution, by based on the employee's position, when a processing failure occurs in the employee's current processing node, the reserved questions and answers of the position under the current business node in the enterprise's fault processing solution knowledge base and the operation process information of the current business node can be recommended to the employee. The intelligent recommendation of questions and answers can be instructed to the employee, and the operation process of solving the current processing failure can also be provided to the employee. This avoids the problem of recommending fixed questions and answers to different employees under the existing technology, which makes it difficult to recommend personalized questions and answers to employees. It improves the recommendation efficiency and accuracy of the enterprise's questions and answers, and can enable the enterprise customer service system to solve employees' problems to the greatest extent, improve employee satisfaction, and reduce the number of times employees use manual customer service, thereby reducing operating costs.

[0149] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0150] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0151] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0152] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0153] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for recommending enterprise questions and answers, characterized in that: include: Establish a business node knowledge graph for the enterprise system based on the historical business processing characteristics of different business nodes in the enterprise system; the historical business processing characteristics include the following characteristics: business node processing time, frequency of interface jumps related to business nodes, frequency of calling information related to business nodes, node jump order, and average jump interval duration; The business node knowledge graph is used to characterize the connection relationship between each business node in the enterprise system and the historical business processing characteristics of each business node; For each business node in the enterprise system, keyword extraction is performed on the historical question and answer records of employees in different positions in the business node to obtain the question keywords and answer keywords of each question and answer in the historical question and answer records; Determine reserved questions and answers corresponding to different employee positions at the business node based on the frequency of occurrence of the question keywords and answer keywords; For each business node in the enterprise system, process extraction is performed on the node operation information of different employees under the business node to determine the operational process information for solving different processing faults under the business node; The operation process information is one or more node operation behaviors after a historical processing failure occurs in the node operation information; Establish an enterprise fault handling solution knowledge base based on the reserved questions and answers for different employee positions at each business node and the operational process information of each business node; The enterprise fault handling solution knowledge base includes reserved questions and answers associated with different employee positions under each business node, and the operation process information of each business node; Detect the current business node where the target employee logs into the enterprise system to process business; Matching the target business processing feature of the current business node with the business node knowledge graph; if the matching result indicates that the target business processing feature fails to match at least one of the historical business processing features of the current business node in the business node knowledge graph, determining that the target employee has a processing failure at the current business node; When it is determined that the target employee has a processing failure at the current business node, determine the position of the target employee; The reserved questions and answers for the position under the current business node in the enterprise's fault handling solution knowledge base and the operation process information of the current business node are recommended to the target employee.

2. The method according to claim 1, wherein For each business node in the enterprise system, keyword extraction is performed on the historical question and answer records of employees in different positions in the business node to obtain the question keywords and answer keywords of each question and answer in the historical question and answer records, including: For each business node in the enterprise system, keywords are extracted from the historical Q&A records of employees in different positions at that business node to determine the question keywords and answer keywords for each employee's position in the historical Q&A records; Based on the frequency of occurrence of the question keywords and answer keywords, the reserved questions and answers corresponding to different employee positions in the business node are determined, including: Determine the frequency of occurrence of question keywords and answer keywords for each employee position; Determine the first weight of the question keyword based on the frequency of occurrence of the question keyword; Determine the second weight of the answer keyword based on the occurrence frequency of the answer keyword and the employee's rating; The question content corresponding to the question keyword with the first weight exceeding the first threshold is used as the target question content in the reserved question and answer for the employee position; The answer keyword with a second weight exceeding a second threshold among the multiple answer keywords corresponding to the target question content is used as the target answer content in the reserved question and answer for the employee position.

3. The method according to claim 2, wherein Also includes: Obtain feedback from target employees on the recommended reserved questions and answers; The feedback information is used to indicate whether the employee clicks on the recommended reserved question and answer and the question and answer score for the recommended reserved question and answer; The enterprise fault handling solution knowledge base is updated according to the feedback information.

4. The method according to claim 3, wherein The enterprise fault handling solution knowledge base is updated based on the feedback information, including: Adjusting the first weight of the question keyword and the second weight of the answer keyword according to the feedback information; Based on the adjusted first weight and second weight, the reserved questions and answers for different employee positions under different business nodes are re-determined.

5. The method according to claim 4, wherein Also includes: When the feedback information indicates that the employee has not clicked on the recommended reserved question and answer, and / or the question and answer score for the recommended reserved question and answer is lower than a preset value, an alarm message carrying the feedback information is issued.

6. An enterprise question and answer recommendation device, characterized in that: include: A business node knowledge graph building module is used to build a business node knowledge graph for the enterprise system based on the historical business processing characteristics of different business nodes in the enterprise system; the historical business processing characteristics include the following characteristics: business node processing time, frequency of interface jumps related to business nodes, frequency of calling information related to business nodes, node jump order, and average jump interval duration; The business node knowledge graph is used to characterize the connection relationship between each business node in the enterprise system and the historical business processing characteristics of each business node; The reserved question and answer determination module is used to extract keywords from the historical question and answer records of employees in different positions at each business node in the enterprise system, and obtain the question keywords and answer keywords of each question and answer in the historical question and answer records; Determine reserved questions and answers corresponding to different employee positions at the business node based on the frequencies of occurrence of the question keywords and answer keywords; The operation process information determination module is used to extract the node operation information of different employees under each business node in the enterprise system and determine the operation process information for solving different processing faults under the business node; The operation process information is one or more node operation behaviors after a historical processing failure occurs in the node operation information; An enterprise fault handling solution knowledge base establishment module is used to establish an enterprise fault handling solution knowledge base based on the reserved questions and answers of different employee positions at each business node and the operation process information of each business node; The enterprise fault handling solution knowledge base includes reserved questions and answers associated with different employee positions under each business node, and the operation process information of each business node; The current business node detection module is used to detect the current business node where the target employee logs into the enterprise system to process business; an information matching module, configured to perform information matching on the target business processing feature of the current business node and the business node knowledge graph, and determine that a processing failure has occurred on the target employee at the current business node when a matching result indicates that the target business processing feature fails to match at least one of the historical business processing features of the current business node in the business node knowledge graph; An information recommendation module is used to determine the position of a target employee when it is determined that the target employee has a processing failure at the current business node; The reserved questions and answers for the position under the current business node in the enterprise's fault handling solution knowledge base and the operation process information of the current business node are recommended to the target employee.

7. The device according to claim 6, characterized in that The reserved question and answer determination module is specifically used for: For each business node in the enterprise system, keywords are extracted from the historical Q&A records of employees in different positions at that business node to determine the question keywords and answer keywords for each employee's position in the historical Q&A records; Determine the frequency of occurrence of question keywords and answer keywords for each employee position; Determine the first weight of the question keyword based on the frequency of occurrence of the question keyword; Determine the second weight of the answer keyword based on the occurrence frequency of the answer keyword and the employee's rating; The question content corresponding to the question keyword with the first weight exceeding the first threshold is used as the target question content in the reserved Q&A for the employee position; The answer keyword with a second weight exceeding a second threshold among the multiple answer keywords corresponding to the target question content is used as the target answer content in the reserved question and answer for the employee position.

8. The device according to claim 7, wherein Also includes: Enterprise troubleshooting solution knowledge base update module, used for: Obtain feedback from target employees on the recommended reserved questions and answers; The feedback information is used to indicate whether the employee clicks on the recommended reserved question and answer and the question and answer score for the recommended reserved question and answer; The enterprise fault handling solution knowledge base is updated according to the feedback information.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 5 is implemented.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

11. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images