Digital employee monitoring method and device, electronic equipment and readable storage medium

Abstract

The invention relates to the technical field of data processing, and provides a digital employee monitoring method and device, electronic equipment and a computer readable storage medium, and the method comprises the steps: obtaining digital employee operation information; performing information splitting processing on the digital employee operation information to obtain multiple pieces of task operation information; comparing the multiple pieces of task operation information with preset historical operation information to obtain operation state information; under the condition that the abnormal operation sub-information is a non-empty set, matching each piece of abnormal operation sub-information with preset fault level division information to obtain fault level information; performing priority division processing on the corresponding abnormal operation sub-information according to the fault level information to obtain processing priority information; and according to the processing priority information, performing optimization adjustment processing on the abnormal task corresponding to the operation abnormal sub-information to obtain an optimization adjustment result. According to the technical scheme, the problem that the operation condition of digital employees cannot be monitored in time can be solved.

Description

Technical Field

[0001] The embodiments of the present application relate to, but are not limited to, the field of data processing, and in particular, to a digital employee monitoring method, device, electronic device, and computer-readable storage medium. Background Art

[0002] With the rapid development of artificial intelligence and automation technology, digital employees (such as intelligent question-answering robots and virtual assistants) have been widely used in various industries, which can greatly improve work efficiency and reduce labor costs. For example, in the consultation process of auto insurance, property damage insurance, liability insurance, credit and guarantee insurance, accident and health insurance, engineering insurance and cargo insurance, people can ask the intelligent question-answering robot about the specific compensation conditions and compensation amounts of the relevant insurance types, which not only brings great convenience to users, but also can well reduce the workload of insurance salesmen. However, digital employees may make mistakes, malfunction or be maliciously exploited in the process of performing tasks. If they are not discovered in time, it will bring a bad user experience to users. Summary of the invention

[0003] The following is a summary of the subject matter described in detail herein. This summary is not intended to limit the scope of the claims.

[0004] In order to solve the problems mentioned in the above background technology, the embodiments of the present application provide a digital employee monitoring method, device, electronic device and computer-readable storage medium, which can solve the problem that the operation status of digital employees cannot be monitored in time.

[0005] In a first aspect, an embodiment of the present application provides a digital employee monitoring method, comprising:

[0006] Get digital employee operation information;

[0007] Performing information splitting processing on the digital employee operation information to obtain multiple task operation information;

[0008] Compare the plurality of task operation information with preset historical operation information to obtain operation status information, wherein the operation status information includes normal operation sub-information and abnormal operation sub-information, and the normal operation sub-information and the abnormal operation sub-information both correspond to the task operation information one by one;

[0009] In the case where the operation abnormality sub-information is a non-empty set, each of the operation abnormality sub-information is matched with the preset fault level classification information to obtain fault level information, wherein the fault level information corresponds to the operation abnormality sub-information one by one;

[0010] Prioritize the corresponding abnormal operation sub-information according to the fault level information to obtain processing priority information;

[0011] The abnormal task corresponding to the abnormal operation sub-information is optimized and adjusted according to the processing priority information to obtain an optimization and adjustment result.

[0012] In a second aspect, an embodiment of the present application further provides a digital employee monitoring device, including:

[0013] An acquisition unit, used for acquiring digital employee operation information;

[0014] A splitting unit, used for performing information splitting processing on the digital employee operation information to obtain a plurality of task operation information;

[0015] A comparison unit, used for comparing the plurality of task operation information with preset historical operation information to obtain operation status information, wherein the operation status information includes normal operation sub-information and abnormal operation sub-information, and the normal operation sub-information and the abnormal operation sub-information both correspond to the task operation information one by one;

[0016] a matching unit, configured to match each of the operation abnormality sub-information with preset fault level classification information to obtain fault level information when the operation abnormality sub-information is a non-empty set, wherein the fault level information corresponds to the operation abnormality sub-information in a one-to-one manner;

[0017] a dividing unit, configured to perform priority division processing on the corresponding operation abnormality sub-information according to the fault level information to obtain processing priority information;

[0018] The adjustment unit is used to optimize and adjust the abnormal task corresponding to the operation abnormality sub-information according to the processing priority information to obtain an optimization adjustment result.

[0019] In a third aspect, an embodiment of the present application further provides an electronic 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 digital employee monitoring method as described in the first aspect above is implemented.

[0020] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are used to execute the digital employee monitoring method as described in the first aspect above.

[0021] According to the digital employee monitoring method of the embodiment provided by the present application, at least the following beneficial effects are achieved: in the process of digital employee monitoring, firstly, the digital employee operation information is obtained; then, the digital employee operation information is split and processed to obtain multiple task operation information; then, the multiple task operation information is compared and processed with the preset historical operation information to obtain the operation status information, wherein the operation status information includes normal operation sub-information and abnormal operation sub-information, and both the normal operation sub-information and the abnormal operation sub-information correspond one-to-one to the task operation information; when the abnormal operation sub-information is a non-empty set, each abnormal operation sub-information can be matched with the preset fault level classification information to obtain the fault level information, wherein the fault level information corresponds one-to-one to the abnormal operation sub-information; then, the corresponding abnormal operation sub-information is prioritized according to the fault level information to obtain the processing priority information; finally, the abnormal task corresponding to the abnormal operation sub-information is optimized and adjusted according to the processing priority information to obtain the optimization adjustment result. Through the above technical solution, it is possible to obtain the operation information of digital employees in real time, use the preset historical operation information to determine whether there is any abnormality in the operation information of digital employees, and in the case of abnormality in the operation information of digital employees, the operation abnormality sub-information is also graded and processed. Subsequently, the corresponding abnormal tasks will be optimized and adjusted according to the grade division, so that the abnormal work of digital employees can be discovered in real time, and abnormal tasks can be processed according to priority information, so as to maintain the normal operation of digital employees to the greatest extent, bringing a good user experience to users. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings are used to provide further understanding of the technical solution of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the technical solution of the present application and do not constitute a limitation on the technical solution of the present application.

[0023] Figure 1 This is a schematic diagram of an application environment of a digital employee monitoring method provided by an embodiment of the present application;

[0024] Figure 2 is a flowchart of a digital employee monitoring method provided by an embodiment of the present application;

[0025] Figure 3 yes Figure 2 A schematic flow chart of a specific implementation of step S200;

[0026] Figure 4 yes Figure 2 A schematic flow chart of a specific implementation of step S300;

[0027] Figure 5 yes Figure 2A schematic flow chart of a specific implementation of step S400;

[0028] Figure 6 yes Figure 2 A schematic flow chart of a specific implementation of step S500;

[0029] Figure 7 is a flowchart of a digital employee monitoring method provided by another embodiment of the present application;

[0030] Figure 8 is a flowchart of a digital employee monitoring method provided by another embodiment of the present application;

[0031] Fig. 9 is a schematic diagram of a digital employee monitoring device provided by an embodiment of the present application;

[0032] Fig.10 It is a schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0033] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0034] It should be noted that although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification and claims and the above drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0035] It should be noted that, unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0036] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0037] AI is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. Artificial intelligence is a branch of computer science. Artificial intelligence attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a similar way to human intelligence. Research in this field includes robots, language recognition, image recognition, natural language processing and expert systems. Artificial intelligence can simulate the information process of human consciousness and thinking. Artificial intelligence is also a theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0038] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0039] Artificial intelligence is AI. AI is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0040] The servers involved in artificial intelligence technology can be independent servers or cloud servers that provide basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), as well as big data and artificial intelligence platforms.

[0041] The present application provides a digital employee monitoring method, device, electronic device and computer-readable storage medium. In the process of digital employee monitoring, firstly, digital employee operation information is obtained; then, the digital employee operation information is split and processed to obtain multiple task operation information; then, the multiple task operation information is compared and processed with preset historical operation information to obtain operation status information, wherein the operation status information includes normal operation sub-information and abnormal operation sub-information, and the normal operation sub-information and the abnormal operation sub-information both correspond to the task operation information one-to-one; when the abnormal operation sub-information is a non-empty set, each abnormal operation sub-information can be matched with preset fault level classification information to obtain fault level information, wherein the fault level information corresponds to the abnormal operation sub-information one-to-one; then, the corresponding abnormal operation sub-information is prioritized according to the fault level information to obtain processing priority information; finally, the abnormal task corresponding to the abnormal operation sub-information is optimized and adjusted according to the processing priority information to obtain the optimization adjustment result. Through the above technical solution, it is possible to obtain the operation information of digital employees in real time, use the preset historical operation information to determine whether there is any abnormality in the operation information of digital employees, and in the case of abnormality in the operation information of digital employees, the operation abnormality sub-information is also graded and processed. Subsequently, the corresponding abnormal tasks will be optimized and adjusted according to the grade division, so that the abnormal work of digital employees can be discovered in real time, and abnormal tasks can be processed according to priority information, so as to maintain the normal operation of digital employees to the greatest extent, bringing a good user experience to users.

[0042] The digital employee monitoring method provided in the embodiment of the present application can be applied in the following aspects: Figure 1In the application environment, the digital employee communicates with the server through the network. The server can collect the digital employee operation information of the digital employee through the network, and then split the digital employee operation information to obtain multiple task operation information; then compare the multiple task operation information with the preset historical operation information to obtain the operation status information, wherein the operation status information includes normal operation sub-information and abnormal operation sub-information, and the normal operation sub-information and the abnormal operation sub-information are in one-to-one correspondence with the task operation information; when the abnormal operation sub-information is a non-empty set, each abnormal operation sub-information can be matched with the preset fault level classification information to obtain the fault level information, wherein the fault level information corresponds to the abnormal operation sub-information one-to-one; then the corresponding abnormal operation sub-information is prioritized according to the fault level information to obtain the processing priority information; finally, the abnormal task corresponding to the abnormal operation sub-information is optimized and adjusted according to the processing priority information to obtain the optimization adjustment result. Among them, the digital employee in the embodiment of the present application can be an intelligent question-and-answer robot or a virtual assistant; in the insurance business, users can consult the intelligent question-and-answer robot about insurance product-related knowledge, insurance application process, claims-related knowledge, insurance planning-related knowledge, insurance service-related knowledge, and insurance industry-related knowledge; the virtual assistant in the insurance industry can also recommend personalized insurance plans based on the personal situation provided by the user, and can also provide insurance sales reference examples for insurance agents. In the intelligent medical industry, users can consult the intelligent question-and-answer robot about simple medical knowledge, medical process guidance, and hospital conditions, and the virtual assistant can assist in the identification of medical images, assist in patient information management, and generate medical advice. The server can be configured as an independent physical server, or as a server cluster or distributed system composed of multiple physical servers, or as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements the digital employee monitoring method, but is not limited to the above forms.

[0043] It should be noted that in each specific implementation of the present application, when it comes to the need to perform relevant processing based on data related to user identity or characteristics such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first, and the collection, use, and processing of these data will comply with relevant laws, regulations, and standards. In addition, when the embodiment of the present application needs to obtain the user's sensitive personal information, the user's separate permission or consent will be obtained through a pop-up window or by jumping to a confirmation page. After clearly obtaining the user's separate permission or consent, the necessary user-related data for the normal operation of the embodiment of the present application will be obtained.

[0044] The embodiments of the present application are further described below in conjunction with the accompanying drawings.

[0045] like Figure 2 As shown, Figure 2 : is a flow chart of a digital employee monitoring method provided by an embodiment of the present application, and the digital employee monitoring method comprises the following steps:

[0046] Step S100: Acquire digital employee operation information.

[0047] In the digital employee monitoring method provided in the embodiment of the present application, the digital employee can be an intelligent question-and-answer robot or a virtual assistant; in the insurance industry, users can consult the intelligent question-and-answer robot about insurance-related knowledge, for example, they can consult the intelligent question-and-answer robot about "what are the insurance conditions for purchasing accident insurance" and "what materials need to be submitted for online insurance." In the intelligent medical industry, users can consult the intelligent question-and-answer robot about simple medical knowledge, medical process guidance, and hospital conditions, etc., while the virtual assistant can assist in the recognition of medical images, assist in patient information management, and generate medical advice, etc. Digital employee operation information is the information generated during the operation of digital employees.

[0048] Exemplarily, the digital employee is an intelligent question-and-answer robot; the intelligent question-and-answer robot may include a user interface, a natural language processing module, a question-and-answer engine, and a knowledge base, etc.; in the insurance industry, when a user asks the intelligent question-and-answer robot "under what circumstances can a health insurance claim be applied for", the intelligent question-and-answer robot can receive the user's voice signal through the user interface, and then the natural language processing module in the intelligent question-and-answer robot can parse the received voice signal to obtain parsed information, and then the question-and-answer engine in the intelligent question-and-answer robot can extract key information from the parsed information, and then match the key information with the pre-stored data in the knowledge base in the intelligent question-and-answer robot, and finally generate voice feedback results. In the process of generating voice feedback results, the intelligent question-and-answer robot will generate relevant operation information. For another example, in the smart medical industry, when a user asks the intelligent question-and-answer robot "What is the hospital medical treatment process like", the intelligent question-and-answer robot can receive the user's voice signal through the user interface, and then the natural language processing module can parse the received voice signal to obtain parsed information, and then the question-and-answer engine can extract key information from the parsed information, and then match the key information with the pre-stored data in the knowledge base, and finally generate voice feedback results; in this process, the intelligent question-and-answer robot will generate operation information, which is the digital employee operation information referred to in the embodiments of the present application.

[0049] It is worth noting that the server in the embodiment of the present application can collect the operating information of the digital employee through the network, that is, obtain the operating information of the digital employee; in the embodiment of the present application, the operating information generated in the digital employee can be collected in real time, and then the digital employee operating information can be obtained in real time, and then the operating status of the digital employee can be well monitored in real time, and the fault problems generated during the operation of the digital employee can be discovered in time.

[0050] Step S200: splitting the digital employee operation information to obtain multiple task operation information.

[0051] In some embodiments of the present application, the digital employee operation information is first obtained, and then the digital employee operation information is split and processed to obtain multiple task operation information; it is worth noting that the digital employee can execute multiple event tasks at the same time, and each event task will correspond to a task operation information. Therefore, the obtained digital employee operation information is split and processed to obtain multiple task operation information, and each task operation information will correspond to an event task. The digital employee operation information is split and processed to prepare for the subsequent detection and comparison of the operation information.

[0052] For example, in the insurance industry, for a virtual assistant in the insurance industry, when a user simultaneously asks the virtual assistant about the types of auto insurance and how to claim health insurance online, two task operation information will be generated in the virtual assistant, one task operation information related to the types of auto insurance, and one task operation information related to health insurance reimbursement. Therefore, by splitting the digital employee operation information obtained from the virtual assistant, one task operation information related to the types of auto insurance and one task operation information related to health insurance reimbursement can be obtained. For another example, for a medical virtual assistant, it is possible to simultaneously identify medical images and assist in patient information management. Therefore, the digital employee operation information obtained in the process of collecting operation information for the medical virtual assistant can include two task operation information, one task operation information related to the identification of medical images, and the other task operation information related to patient information management.

[0053] like Figure 3 As shown, in step S200, the digital employee operation information is split and processed to obtain multiple task operation information, which may include the following steps:

[0054] Step S210, determining task tag information from the digital employee operation information;

[0055] Step S220 , performing task division processing on the digital employee operation information according to the task tag information to obtain a plurality of task operation information.

[0056] For steps S210 to S220, in the process of splitting the digital employee operation information to obtain multiple task operation information, the task marking information is determined from the digital employee operation information; then, the digital employee operation information can be task-divided according to the task marking information to obtain multiple task operation information, and then each task operation information can be detected and processed separately to determine whether each task operation information is normal.

[0057] For example, in the insurance business, when the digital employee is an intelligent question-and-answer robot, when the user asks the intelligent question-and-answer robot "What materials are needed to purchase health insurance", corresponding digital employee operation information will be generated, and the digital employee operation information will be marked as "01"; and when the user asks the intelligent question-and-answer robot "What is the process of car insurance reimbursement", corresponding digital employee operation information will be generated, and the digital employee operation information will be marked as "02"; after obtaining the digital employee operation information from the intelligent question-and-answer robot, the task operation information related to health insurance purchase and the task operation information related to car insurance reimbursement can be split from the digital employee information according to the task marking information "01" and "02". For another example, for a medical virtual assistant, digital employee operation information will be generated in the process of managing the patient's personal information, marked as "01", and "01" is the task marking information in the embodiment of the present application; at the same time, the medical virtual assistant will also generate other digital employee operation information in the process of generating medical advice, marked as "02", and "02" is the task marking information in the embodiment of the present application; after subsequently obtaining the digital employee operation information from the medical virtual assistant, it is possible to split the digital employee information into a task operation information related to the patient information and a task operation information related to generating medical advice based on the task marking information "01" and "02".

[0058] Step S300: Compare the multiple task operation information with the preset historical operation information to obtain operation status information, wherein the operation status information includes normal operation sub-information and abnormal operation sub-information, and the normal operation sub-information and the abnormal operation sub-information both correspond to the task operation information one by one.

[0059] In some embodiments of the present application, after splitting and obtaining multiple task operation information, each task operation information can be compared with the preset historical operation information to obtain the operation status information corresponding to each task operation information; wherein the operation status information includes normal operation sub-information and abnormal operation sub-information, the normal operation sub-information indicates that the corresponding task operation information is in a normal state, and the abnormal operation sub-information indicates that the corresponding task operation information is in an abnormal state. Through the above technical solution, the task operation information can be monitored and processed simply and quickly.

[0060] It is worth noting that the historical operation information is the task operation information generated during the normal operation of the previous digital employee. The subsequent task operation information is compared with the previous normal task operation information. When the two are consistent, the normal operation sub-information will be obtained, and when the two are inconsistent, the abnormal operation sub-information will be obtained. For example, in the insurance industry, the digital employee is an intelligent question-and-answer robot. When the user asks the intelligent question-and-answer robot "What types of corporate insurance are included", the intelligent question-and-answer robot will generate corresponding task operation information, and then the obtained task operation information can be compared with the pre-set historical operation information; when the task operation information is the same as the historical operation information, the normal operation sub-information can be obtained; when the task operation information is different from the historical operation information, the abnormal operation sub-information can be obtained. Among them, the historical operation information is the normal operation information generated by the previous consultation "What types of corporate insurance are included".

[0061] like Figure 4 As shown, in step S300, the historical operation information includes historical operation standard information, and the operation status information is obtained by comparing the multiple task operation information with the preset historical operation information, which may include the following steps:

[0062] Step S310, comparing each task operation information with historical operation standard information;

[0063] Step S320, when the task running information is consistent with the historical running standard information, obtaining normal running sub-information;

[0064] Step S330, when the task running information is inconsistent with the historical running standard information, the running abnormality sub-information is obtained.

[0065] For steps S310 to S330, the historical operation information includes the historical operation standard information. In the process of comparing the multiple task operation information with the preset historical operation information, each task operation information is first compared with the historical operation standard information; when the task operation information is consistent with the historical operation standard information, normal operation sub-information will be obtained; when the task operation information is inconsistent with the historical operation standard information, abnormal operation sub-information will be obtained. Through the above technical solution, the normal operation sub-information and abnormal operation sub-information can be obtained by simply and quickly performing the comparison process, thereby accelerating the recognition efficiency of the task operation information, making the efficiency of the entire digital employee monitoring more efficient.

[0066] Step S400: when the operation abnormality sub-information is a non-empty set, each operation abnormality sub-information is matched with the preset fault level classification information to obtain fault level information, wherein the fault level information corresponds to the operation abnormality sub-information one by one.

[0067] In some embodiments of the present application, after comparing multiple task operation information with preset historical operation information to obtain operation status information, when the operation exception sub-information is a non-empty set, each operation exception sub-information can be matched with the preset fault level classification information, and then the corresponding fault level information can be obtained, wherein the fault level information corresponds to the operation exception sub-information one-to-one; the operation exception sub-information is matched with the fault level classification information to prepare for the subsequent priority classification of the operation exception sub-information.

[0068] It is worth noting that the abnormal operation sub-information is a non-empty set, that is, by comparing multiple task operation information with preset historical operation information, the abnormal operation sub-information can be obtained, that is, the obtained digital employee operation information has abnormal conditions. Exemplarily, when the digital employee is an intelligent assistant, when the agent usually uses the intelligent assistant to query various recommended plans for purchasing insurance, the corresponding task operation information will be generated, and the task operation information will be compared with the historical operation information. When the two are different, the corresponding abnormal operation sub-information will be generated, and the abnormal operation sub-information at this time is a non-empty set.

[0069] like Figure 5 As shown, in step S400, the fault level classification information includes fault information and level information corresponding to the fault information. When the operation abnormality sub-information is a non-empty set, each operation abnormality sub-information is matched with the preset fault level classification information to obtain the fault level information, which may include the following steps:

[0070] Step S410, when the operation abnormality sub-information is a non-empty set, matching the operation abnormality sub-information with the fault information to obtain target fault information;

[0071] Step S420: Determine the level information corresponding to the target fault information as the fault level information.

[0072] For steps S410 to S420, when the operation abnormality sub-information is a non-empty set, in the process of matching each operation abnormality sub-information with the preset fault level classification information to obtain the fault level information, the operation abnormality sub-information can be matched with the fault information first, and then the target fault information can be determined; then the level information corresponding to the target fault information is determined as the corresponding fault level information, in preparation for the subsequent priority classification.

[0073] For example, in the insurance industry, the digital employee is an intelligent question-and-answer robot. When a user asks the intelligent question-and-answer robot "What is the reimbursement process for auto insurance" and "How to buy auto insurance more reasonably", the intelligent question-and-answer robot will generate corresponding task operation information after receiving these two questions; after comparing and processing the two task operation information, operation abnormality sub-information is obtained, proving that abnormal situations occurred in the process of processing these two answer events; the preset fault level classification information includes "abnormality in consulting on auto insurance reimbursement process", and the corresponding level information is "level one"; "abnormality in consulting on how to buy auto insurance", and the corresponding level information is "level two"; among them, "abnormality in consulting on auto insurance reimbursement process" and "abnormality in consulting on how to buy auto insurance" are fault information, and "level one" and "level two" are level information. Therefore, the operation abnormality sub-information generated by the detection of the two question-and-answer events will be matched with the preset fault level classification information, and it can be determined that the level information corresponding to the operation task of "What is the reimbursement process of auto insurance" is "level one"; the level information corresponding to the operation task of "How to buy auto insurance more reasonably" is "level two", and the priority classification can be performed according to the level information corresponding to the operation task. For another example, for the intelligent question-and-answer robot in the medical industry, when the user asks the intelligent question-and-answer robot "What is the process of seeing a doctor" and "What methods can be used to exercise in daily life", the intelligent question-and-answer robot can generate corresponding task operation information after receiving these two questions; after comparing the two task operation information, both get the operation abnormality sub-information, proving that abnormal situations occurred in the process of processing these two answer events; the preset fault level classification information includes "abnormal consultation and medical process", the corresponding level information is "level one"; "abnormal consultation and physical exercise", the corresponding level information is "level two"; among them, "abnormal consultation and medical process" and "abnormal consultation and physical exercise" are fault information, and "level one" and "level two" are level information. Therefore, the operation abnormality sub-information generated by the detection of the two question and answer events will be matched with the preset fault level classification information, so that it can be determined that the level information corresponding to the operation task of "What is the process of medical treatment" is "level one"; the level information corresponding to the operation task of "What are the ways to exercise in daily life" is "level two". Subsequently, priority classification can be carried out according to the level information corresponding to the operation task.

[0074] Step S500: Prioritize the corresponding abnormal operation sub-information according to the fault level information to obtain processing priority information.

[0075] In some embodiments of the present application, when the fault level information corresponding to each operation abnormality sub-information is determined, the corresponding operation abnormality sub-information can be prioritized according to the fault level information to obtain processing priority information, and then the corresponding abnormal tasks can be processed in sequence according to the determined processing priority information; among them, the abnormal task with the highest priority will be optimized and adjusted first, so that the digital employee can maintain normal operation to the greatest extent.

[0076] For example, in the insurance industry, the digital employee is an insurance virtual assistant. When a user uses the insurance virtual assistant to perform "medical invoice upload during health insurance reimbursement" and "accident insurance type consultation", abnormal situations occur in the process of handling these two event tasks. Therefore, two operation abnormality sub-information are obtained; after matching and processing these two operation abnormality sub-information with the preset fault level classification information, the level information corresponding to "medical invoice upload" is "level one", and the level information corresponding to "insurance type consultation" is "level two". Subsequently, the operation abnormality sub-information is prioritized and processed, and "medical invoice upload" can be listed as high priority, and "insurance type consultation" can be listed as low priority. Subsequently, "medical invoice upload" will be optimized and adjusted first, and then "insurance type consultation" will be optimized and adjusted. For another example, for a medical virtual assistant, it is processing "medical image recognition" and "medical consultation guidance" at the same time, and abnormal situations occur in the process of processing these two event tasks. Therefore, two operation abnormality sub-information are obtained; after matching and processing these two operation abnormality sub-information with the preset fault level classification information, the level information corresponding to "medical image recognition" is "level one", and the level information corresponding to "medical consultation guidance" is "level two". Subsequently, the operation abnormality sub-information is prioritized and processed, and "medical image recognition" can be listed as a high priority and "medical consultation guidance" can be listed as a low priority. Subsequently, "medical image recognition" will be optimized and adjusted first, and then "medical consultation guidance" will be optimized and adjusted.

[0077] like Figure 6 As shown, in step S500, the corresponding abnormal operation sub-information is prioritized according to the fault level information to obtain processing priority information, which may include the following steps:

[0078] Step S510, performing priority sorting processing on each operation abnormality sub-information according to the fault level information of each operation abnormality sub-information;

[0079] Step S520: determining the processing priority information according to each of the operation abnormality sub-information after the priority sorting processing.

[0080] For steps S510 to S520, in the process of prioritizing the corresponding operation exception sub-information according to the fault level information to obtain the processing priority information, first, each operation exception sub-information is prioritized according to the fault level information of each operation exception sub-information; then, the corresponding processing priority information is determined according to each operation exception sub-information after the priority sorting, so that each abnormal task can be subsequently sorted and processed according to the processing priority information.

[0081] It is worth noting that when the priority information represents that the operation exception sub-information has the highest priority, the exception task corresponding to the exception sub-information will be optimized and adjusted first, so as to maintain the normal operation of the digital employee to the greatest extent.

[0082] Step S600: Optimizing and adjusting the abnormal task corresponding to the abnormal operation sub-information according to the processing priority information to obtain an optimization and adjustment result.

[0083] In some embodiments of the present application, after obtaining the processing priority information, the abnormal tasks corresponding to the running abnormal sub-information can be prioritized and adjusted according to the processing priority information, so that the corresponding optimization adjustment results can be obtained; through the above technical scheme, the abnormal tasks with the highest priority can be prioritized and adjusted, and then the relatively lower abnormal tasks can be processed. Through such a setting, the normal functions of digital employees can be well maintained.

[0084] like Figure 7 As shown, after step S600, the following steps may be included:

[0085] Step S710, feeding back the optimization adjustment result to a preset digital employee monitoring terminal;

[0086] Step S720: Based on the digital employee monitoring terminal, the historical operation information is updated according to the optimization adjustment result.

[0087] For steps S710 to S720, after optimizing and adjusting the abnormal tasks corresponding to the operation abnormality sub-information according to the processing priority information to obtain the optimization adjustment results, the optimization adjustment results can be fed back to the preset digital employee monitoring terminal; then based on the digital employee monitoring terminal, the historical operation information can be updated according to the optimization adjustment results to prepare the digital employees for subsequent task processing, and can also greatly improve the accuracy of subsequent task execution judgments.

[0088] It is worth noting that the digital employee monitoring terminal can be a mobile phone, a tablet, and a computer, which is not limited here. For example, in the insurance industry, the digital employee is an insurance virtual assistant, and the digital employee monitoring terminal is a virtual assistant monitoring terminal. After the optimization and adjustment results are fed back to the virtual assistant monitoring terminal, the virtual assistant maintenance personnel can view and process the operation of the insurance virtual assistant through the virtual assistant monitoring terminal.

[0089] like Figure 8 As shown, after step S600, the following steps may also be included:

[0090] Step S810, feeding back the digital employee operation information and operation status information to a preset digital employee monitoring terminal;

[0091] Step S820: transferring the digital employee operation information and operation status information to a preset non-volatile memory based on the digital employee monitoring terminal.

[0092] For steps S810 to S820, after optimizing and adjusting the abnormal tasks corresponding to the operation abnormal sub-information according to the processing priority information to obtain the optimization adjustment results, the digital employee operation information and operation status information can be fed back to the preset digital employee monitoring terminal; then, based on the digital employee monitoring terminal, the digital employee operation information and operation status information are transferred to the preset non-volatile memory, and then the historical data processing process log can be viewed and processed through the non-volatile memory.

[0093] It is worth noting that non-volatile memory is a type of memory that retains data after power is removed. Unlike volatile memory, non-volatile memory does not require continuous power to retain data. The main types of non-volatile memory include read-only memory, flash memory, phase change memory, magnetoresistive random access memory, resistive random access memory, and ferroelectric memory.

[0094] In addition, if Fig. 9 As shown, an embodiment of the present application further provides a digital employee monitoring device 10, comprising:

[0095] The acquisition unit 100 is used to acquire the digital employee operation information;

[0096] The splitting unit 200 is used to split the digital employee operation information to obtain multiple task operation information;

[0097] The comparison unit 300 is used to compare the multiple task operation information with the preset historical operation information to obtain the operation status information, wherein the operation status information includes normal operation sub-information and abnormal operation sub-information, and the normal operation sub-information and the abnormal operation sub-information both correspond to the task operation information one by one;

[0098] The matching unit 400 is used to match each of the operation abnormality sub-information with the preset fault level classification information to obtain the fault level information when the operation abnormality sub-information is a non-empty set, wherein the fault level information corresponds to the operation abnormality sub-information one by one;

[0099] A division unit 500 is used to perform priority division processing on corresponding operation abnormality sub-information according to the fault level information to obtain processing priority information;

[0100] The adjustment unit 600 is used to optimize and adjust the abnormal task corresponding to the abnormal operation sub-information according to the processing priority information to obtain an optimized adjustment result.

[0101] It should be noted that in the process of digital employee monitoring, the digital employee operation information is first obtained; then the digital employee operation information is split and processed to obtain multiple task operation information; then the multiple task operation information is compared with the preset historical operation information to obtain the operation status information, wherein the operation status information includes normal operation sub-information and abnormal operation sub-information, and the normal operation sub-information and the abnormal operation sub-information both correspond one-to-one to the task operation information; when the abnormal operation sub-information is a non-empty set, each abnormal operation sub-information can be matched with the preset fault level classification information to obtain the fault level information, wherein the fault level information corresponds one-to-one to the abnormal operation sub-information; then the corresponding abnormal operation sub-information is prioritized according to the fault level information to obtain the processing priority information; finally, the abnormal task corresponding to the abnormal operation sub-information is optimized and adjusted according to the processing priority information to obtain the optimization adjustment result. Through the above technical solution, it is possible to obtain the operation information of digital employees in real time, use the preset historical operation information to determine whether there is any abnormality in the operation information of digital employees, and in the case of abnormality in the operation information of digital employees, the operation abnormality sub-information is also graded and processed. Subsequently, the corresponding abnormal tasks will be optimized and adjusted according to the grade division, so that the abnormal work of digital employees can be discovered in real time, and abnormal tasks can be processed according to priority information, so as to maintain the normal operation of digital employees to the greatest extent, bringing a good user experience to users.

[0102] The specific implementation of the digital employee monitoring device 10 is substantially the same as the specific implementation of the digital employee monitoring method described above, and will not be described in detail herein.

[0103] In addition, if Fig.10 As shown, an embodiment of the present application further provides an electronic device 700 , which includes: a memory 720 , a processor 710 , and a computer program stored in the memory 720 and executable on the processor 710 .

[0104] The processor 710 and the memory 720 may be connected via a bus or in other ways.

[0105] The non-transitory software programs and instructions required to implement the digital employee monitoring methods of the above embodiments are stored in the memory 720 , and when executed by the processor 710 , the digital employee monitoring methods of the above embodiments are executed.

[0106] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0107] In addition, an embodiment of the present application further provides a computer-readable storage medium, which stores computer-executable instructions, and the computer-executable instructions are executed by a processor 710 or a controller, for example, by a processor 710 in the above-mentioned device embodiment, so that the above-mentioned processor 710 can execute the digital employee monitoring method in the above-mentioned embodiment.

[0108] The above embodiments may be used in combination, and modules with the same name in different embodiments may be the same or different.

[0109] The above describes specific embodiments of the present application, and other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily have to be performed in the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0110] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and computer-readable storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0111] The apparatus, device, computer-readable storage medium and method provided in the embodiments of the present application correspond to each other. Therefore, the apparatus, device and non-volatile computer storage medium also have similar beneficial technical effects as the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the corresponding apparatus, device and computer storage medium will not be repeated here.

[0112] In the 1990s, improvements to a technology could be clearly distinguished as hardware improvements (for example, improvements to the circuit structure of diodes, transistors, switches, etc.) or software improvements (improvements to the method flow). However, with the development of technology, many improvements to the method flow today can be regarded as direct improvements to the hardware circuit structure. Designers almost always obtain the corresponding hardware circuit structure by programming the improved method flow into the hardware circuit. Therefore, it cannot be said that an improvement in a method flow cannot be implemented using a hardware entity module. For example, a programmable logic device (PLD) (such as a field programmable gate array (FPGA)) is such an integrated circuit whose logical function is determined by the user's programming of the device. Designers can "integrate" a digital system on a PLD by programming it themselves, without having to ask a chip manufacturer to design and produce a dedicated integrated circuit chip. Moreover, nowadays, instead of manually making integrated circuit chips, this kind of programming is mostly implemented by "logic compiler" software, which is similar to the software compiler used when developing and writing programs, and the original code before compilation must also be written in a specific programming language, which is called hardware description language (HDL). There is not only one HDL, but many kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, RHDL (Ruby Hardware Description Language), etc. The most commonly used ones are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art should also know that it is only necessary to program the method flow slightly in the above-mentioned hardware description languages ​​and program it into the integrated circuit, and then it is easy to obtain the hardware circuit that implements the logic method flow.

[0113] The controller can be implemented in any appropriate manner, for example, the controller can take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (such as software or firmware) that can be executed by the (micro)processor, a logic gate, a switch, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the control logic of the memory. Those skilled in the art also know that in addition to implementing the controller in a purely computer-readable program code manner, the controller can be implemented in the form of a logic gate, a switch, an application-specific integrated circuit, a programmable logic controller, and an embedded microcontroller by logically programming the method steps. Therefore, this controller can be considered as a hardware component, and the devices included therein for implementing various functions can also be regarded as structures within the hardware component. Or even, the devices for implementing various functions can be regarded as both software modules for implementing the method and structures within the hardware component.

[0114] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0115] For the convenience of description, the above devices are described in terms of functions and are divided into various units. Of course, when implementing the embodiments of the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0116] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the embodiments of the present application may adopt the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the embodiments of the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0117] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, 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 generate 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 flowchart and / or block diagram. 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.

[0118] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0119] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0120] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0121] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0122] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0123] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0124] In the embodiments of the present application, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. Among them, A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c can be represented by: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, c can be single or multiple.

[0125] Embodiments of the present application may be described in the general context of computer executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. Embodiments of the present application may also be practiced in distributed computing environments, where tasks are performed by remote processing devices connected via a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0126] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0127] The above is only the embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A digital employee monitoring method, characterized in that: include: Get digital employee operation information; Performing information splitting processing on the digital employee operation information to obtain multiple task operation information; Compare the plurality of task operation information with preset historical operation information to obtain operation status information, wherein the operation status information includes normal operation sub-information and abnormal operation sub-information, and the normal operation sub-information and the abnormal operation sub-information both correspond to the task operation information one by one; In the case where the operation abnormality sub-information is a non-empty set, each of the operation abnormality sub-information is matched with the preset fault level classification information to obtain fault level information, wherein the fault level information corresponds to the operation abnormality sub-information one by one; Prioritize the corresponding abnormal operation sub-information according to the fault level information to obtain processing priority information; The abnormal task corresponding to the abnormal operation sub-information is optimized and adjusted according to the processing priority information to obtain an optimization and adjustment result.

2. The digital employee monitoring method according to claim 1, characterized in that: The digital employee operation information is split and processed to obtain a plurality of task operation information, including: determining task tag information from the digital employee operation information; The digital employee operation information is task-divided according to the task tag information to obtain a plurality of task operation information.

3. The digital employee monitoring method according to claim 1, characterized in that: The historical operation information includes historical operation standard information, and the operation status information is obtained by comparing the plurality of task operation information with the preset historical operation information, including: Compare each of the task operation information with the historical operation standard information; When the task running information is consistent with the historical running standard information, obtaining the normal running sub-information; When the task running information is inconsistent with the historical running standard information, the running abnormality sub-information is obtained.

4. The digital employee monitoring method according to claim 1, characterized in that: The fault level classification information includes fault information and level information corresponding to the fault information. When the operation abnormality sub-information is a non-empty set, each operation abnormality sub-information is matched with the preset fault level classification information to obtain the fault level information, including: When the operation abnormality sub-information is a non-empty set, matching the operation abnormality sub-information with the fault information to obtain target fault information; The level information corresponding to the target fault information is determined as the fault level information.

5. The digital employee monitoring method according to claim 1, characterized in that: The step of performing priority classification processing on the corresponding abnormal operation sub-information according to the fault level information to obtain processing priority information includes: According to the fault level information of each of the operation abnormality sub-information, priority sorting is performed on each of the operation abnormality sub-information; The processing priority information is determined according to each of the operation abnormality sub-information after priority sorting.

6. The digital employee monitoring method according to claim 1, characterized in that: After optimizing and adjusting the abnormal task corresponding to the abnormal operation sub-information according to the processing priority information and obtaining the optimization and adjustment result, the method further includes: Feeding back the optimization adjustment results to a preset digital employee monitoring terminal; Based on the digital employee monitoring terminal, the historical operation information is updated according to the optimization adjustment result.

7. The digital employee monitoring method according to claim 1, characterized in that: After optimizing and adjusting the abnormal task corresponding to the abnormal operation sub-information according to the processing priority information and obtaining the optimization and adjustment result, the method further includes: Feedback the digital employee operation information and the operation status information to a preset digital employee monitoring terminal; Based on the digital employee monitoring terminal, the digital employee operation information and the operation status information are transferred to a preset non-volatile memory.

8. A digital employee monitoring device, characterized in that: include: An acquisition unit, used for acquiring digital employee operation information; A splitting unit, used for performing information splitting processing on the digital employee operation information to obtain a plurality of task operation information; A comparison unit, used for comparing the plurality of task operation information with preset historical operation information to obtain operation status information, wherein the operation status information includes normal operation sub-information and abnormal operation sub-information, and the normal operation sub-information and the abnormal operation sub-information both correspond to the task operation information one by one; a matching unit, configured to match each of the operation abnormality sub-information with preset fault level classification information to obtain fault level information when the operation abnormality sub-information is a non-empty set, wherein the fault level information corresponds to the operation abnormality sub-information in a one-to-one manner; a dividing unit, configured to perform priority division processing on the corresponding operation abnormality sub-information according to the fault level information to obtain processing priority information; The adjustment unit is used to optimize and adjust the abnormal task corresponding to the operation abnormality sub-information according to the processing priority information to obtain an optimization adjustment result.

9. An electronic device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the digital employee monitoring method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing computer-executable instructions, characterized in that: The computer executable instructions are used to execute the digital employee monitoring method according to any one of claims 1 to 7.

Images