Operation knowledge accompanying method, device, equipment, medium and product

Abstract

The invention relates to an operation knowledge accompanying method and device, equipment, a medium and a product. The method comprises the steps of obtaining an operation behavior of a user; performing matching positioning processing on the operation behavior, and determining a target business scene corresponding to the operation behavior; target knowledge data corresponding to the target business scene is inquired from a pre-stored knowledge graph, operation guidance and associated knowledge links are generated based on the target knowledge data, and the knowledge graph is obtained by conducting classified conversion processing on the multi-source business data. By adopting the method, the knowledge accompanying efficiency can be improved.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence technology, and in particular to a method, apparatus, device, medium, and product for operating knowledge. Background Technology

[0002] Bank branches serve as crucial touchpoints connecting banks and customers, involving a vast amount of business processes, product information, regulations, and policies. To improve knowledge management and counter operation levels at bank branches, it is necessary to achieve efficient extraction of banking knowledge and information and to ensure that counter operation knowledge is readily available.

[0003] In traditional technology, on-the-go operational knowledge involves assigning specialists to regularly visit bank branches and conduct one-on-one interviews with senior tellers and branch managers to record business experience, operational skills, and other knowledge. This knowledge is then compiled into paper manuals or simple documents and archived in the relevant section of the internal system. Teller staff can then access relevant knowledge about business processes by consulting the paper manuals or the relevant sections of the bank's internal system.

[0004] However, current operational knowledge-based methods suffer from low efficiency in knowledge acquisition. Summary of the Invention

[0005] Therefore, it is necessary to provide an operational knowledge-following method, apparatus, equipment, medium, and product that can improve the efficiency of knowledge-following in response to the above-mentioned technical problems.

[0006] Firstly, this application provides an operational knowledge-accompanying method, including:

[0007] Obtain user actions;

[0008] Perform matching and location processing on the operation behavior to determine the target business scenario corresponding to the operation behavior;

[0009] The system queries the target knowledge data corresponding to the target business scenario from the pre-stored knowledge graph, and generates operation guidance and related knowledge links based on the target knowledge data. The knowledge graph is obtained by classifying and transforming multi-source business data.

[0010] In one embodiment, the method further includes:

[0011] Acquire multi-source business data, which includes business system data, counter communication data, and historical document data;

[0012] The data is classified and filtered using a pre-defined data classification model to obtain knowledge data with category labels.

[0013] Based on category labels, a mapping relationship is established between knowledge data and various business scenarios, and a knowledge graph is generated based on the mapping relationship and knowledge data.

[0014] In one embodiment, the knowledge graph includes multiple relationships;

[0015] Based on category labels, a mapping relationship is established between knowledge data and various business scenarios, and a knowledge graph is generated based on the mapping relationship and knowledge data, including:

[0016] Match category labels with entity categories in each business scenario;

[0017] For each successfully matched category label and at least one business scenario, establish the association between the knowledge data corresponding to the category label and each business scenario.

[0018] In one embodiment, a preset data classification model is used to classify and filter multi-source business data to obtain knowledge data with category labels, including:

[0019] Using a data classification model, semantic analysis and clustering are performed on multi-source business data to obtain the category labels corresponding to each multi-source business data.

[0020] The accuracy of multi-source business data in each category of labels is verified by using preset standard constraints, and the verification results corresponding to each multi-source business data are obtained.

[0021] The multi-source business data that have consistent verification results are deduplicated and merged to obtain knowledge data with category labels.

[0022] In one embodiment, generating a knowledge graph based on mapping relationships and knowledge data includes:

[0023] Obtain policy update data and user feedback data;

[0024] Knowledge graphs are generated using policy update data, user feedback data, and knowledge data.

[0025] In one embodiment, generating operation instructions based on knowledge data includes:

[0026] Obtain the user's historical operation data;

[0027] Based on historical operational data, construct user capability profiles;

[0028] Based on capability profiles and knowledge data, operational guidelines are generated.

[0029] Secondly, this application also provides an operational knowledge-accompanying device, comprising:

[0030] The data acquisition module is used to acquire the operational behavior of teller users;

[0031] The scene location module is used to match and locate operational behaviors to determine the target business scene corresponding to the operational behavior.

[0032] The accompanying guidance module is used to query the target knowledge data corresponding to the target business scenario from the pre-stored knowledge graph, and generate operation guidance and related knowledge links based on the target knowledge data. The knowledge graph is obtained by classifying and transforming multi-source business data.

[0033] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the operation knowledge-following method as described in the first aspect.

[0034] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the operation knowledge-accompanying method as described in the first aspect.

[0035] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the operation knowledge-accompanying method as described in the first aspect.

[0036] The aforementioned operational knowledge-accompanying methods, devices, equipment, media, and products identify target business scenarios through user operational behavior and query target knowledge data corresponding to the target business scenario from a knowledge graph. The knowledge graph in this embodiment is obtained by classifying and transforming multi-source business data, which can improve knowledge completeness and extraction efficiency. Based on the target knowledge data corresponding to the target business scenario, operation guidance and related knowledge links are generated, which can realize timely knowledge retrieval and effectively improve the efficiency of knowledge accompanying. Attached Figure Description

[0037] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0038] Figure 1 This is a flowchart illustrating the operation knowledge-following method in one embodiment;

[0039] Figure 2 This is a flowchart illustrating the steps involved in generating a knowledge graph in one embodiment.

[0040] Figure 3This is a flowchart illustrating the operation knowledge-following method in another embodiment;

[0041] Figure 4 This is a structural block diagram of the operation knowledge-accompanying device in one embodiment;

[0042] Figure 5 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0043] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0044] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0045] In this embodiment, the "Operational Knowledge Accompanying Method" supports dual-terminal use on bank branch counter computers and user tablets. The floating window on the user tablet can be synchronized with the counter system via Bluetooth. At the same time, it supports the "offline download" function, allowing users to download knowledge packages for high-frequency services in advance, such as "Guidelines for Monthly Centralized Salary Payment Services". Even when the network is unstable, users can still use the "Operational Knowledge Accompanying Method" to obtain operation guidelines and related knowledge links.

[0046] In one embodiment, such as Figure 1 As shown, an operational knowledge-based method is provided. This embodiment illustrates the application of this method to a terminal. It is understood that this method can also be applied to a server, and further to a system including both a terminal and a server, and is implemented through interaction between the terminal and the server. In this embodiment, the method includes steps 102 to 106. Wherein:

[0047] Step 102: Obtain the user's actions.

[0048] Among them, the user's operation behavior can be captured in real time by the counter transaction system connected to the server, that is, the operation behavior of the counter transaction system tellers.

[0049] For example, the actions may include, but are not limited to, users clicking the "Cross-border Remittance" transaction entry or entering their customer account in the counter transaction system.

[0050] Step 104: Perform matching and location processing on the operation behavior to determine the target business scenario corresponding to the operation behavior.

[0051] Among them, matching and positioning processing refers to analyzing the acquired operation behavior to obtain system interface elements, operation steps and system interface elements, retrieving relevant information from the knowledge graph, and locating the corresponding business scenario based on the retrieval results.

[0052] Step 106: Query the target knowledge data corresponding to the target business scenario from the pre-stored knowledge graph, and generate operation guidance and related knowledge links based on the target knowledge data.

[0053] The knowledge graph is obtained by classifying and transforming multi-source business data. During the query process, the hierarchical category labels in the knowledge graph are used as index keys to locate the corresponding standard business process backbone. The standard business process backbone can include the standard operation step sequence after verification and deduplication, the list of required materials, and the corresponding interface screenshots for each step, forming the basic framework of the accompanying guidance.

[0054] Operation instructions can be displayed on the interactive interface of the over-the-counter transaction system via a pop-up window. The instructions within the pop-up window can be presented in a "steps + screenshot" format, as in the "personal cross-border remittance" business scenario. The operation instructions may include the following items:

[0055] S1: Enter the recipient's name (Note: It must be exactly the same as the name on the overseas account to avoid spelling errors);

[0056] S2: Select the remittance currency (find the corresponding currency in the drop-down menu, such as "USD - US Dollar");

[0057] S3: Enter the remittance amount (must be within the annual foreign exchange quota, ≤ USD 50,000 per person per year).

[0058] Each step is completed, and the progress of the operation guide is updated in real time. The floating box automatically updates the next step of the guide, and complete steps are marked with a "green checkmark" and error-prone points are marked with a "red reminder".

[0059] In some embodiments, knowledge graph technology can also be used to traverse the associated nodes in the knowledge graph, using the step corresponding to the current operation as an anchor point, and the tacit knowledge data retrieved can also be used as target knowledge data. For example, when the user's operation reaches the specific step node of "entering the purpose of remittance", if it is detected that this node has a strong correlation with the "compliance risk warning" node in the knowledge graph, a pop-up window or highlight mark related to "compliance risk warning" will be generated in the front-end floating box, displaying experiential compliance advice or prohibited items.

[0060] In some embodiments, for high-risk or error-prone steps, a "Precautions" pop-up window automatically appears in the floating box. For example, when entering the purpose of remittance, the pop-up window prompts, "You cannot select illegal purposes such as 'investment' or 'property purchase'. We recommend selecting compliant options such as 'tourism' or 'study abroad'." If the user's operation deviates from the guidance, such as selecting an illegal remittance purpose, the floating box immediately flashes and prompts, "Operational risk, please change the purpose and continue."

[0061] Among them, the related knowledge links can be linked to the "View Full Document" button set at the bottom of the floating box. Users can directly jump to the corresponding official operation manual after clicking it, such as "Operational Specifications for Personal Cross-border Remittance Business"; it can also push relevant policy document links, such as "The Latest Regulations of the State Administration of Foreign Exchange on Personal Foreign Exchange Management", so that users can quickly access authoritative information.

[0062] For example, based on the current business scenario, such as when processing "cross-border remittances," related knowledge links can also be displayed at the edge of the floating box. These related knowledge links can include "Frequently Asked Questions," such as "How should I fill in the form if the customer does not have an overseas account address?" and "Solution Links," which can be clicked to view detailed answers and "Customer Communication Scripts," such as "When explaining foreign exchange quota restrictions to customers, you can say, 'According to national regulations, individuals can process cross-border remittances of no more than US$50,000 per year. Your remittance amount is within the quota and can be processed normally.'"

[0063] In the above-mentioned knowledge-based operation method, the target business scenario is identified through the user's operation behavior, and the target knowledge data corresponding to the target business scenario is queried from the knowledge graph. The knowledge graph in this embodiment is obtained by classifying and transforming multi-source business data, which can improve the completeness of knowledge and extraction efficiency. Based on the target knowledge data corresponding to the target business scenario, operation guidance and related knowledge links are generated, which can realize timely knowledge access and effectively improve the efficiency of knowledge-based operation.

[0064] In one exemplary embodiment, generating operation guidance based on knowledge data includes: obtaining the user's historical operation data; constructing the user's capability profile based on the historical operation data; and generating operation guidance based on the capability profile and knowledge data.

[0065] For example, a user's historical operation data may include business processing accuracy, error types, and training records.

[0066] In some embodiments, a capability profile can be built based on the user's usage time. For users whose usage time is less than or equal to a preset duration, more detailed operation guidance can be generated, such as text and animated demonstrations for each step, and links to basic knowledge points can be pushed, such as a "Foreign Exchange Currency Code Comparison Table". For users whose usage time is greater than the preset duration, simplified operation guidance can be generated, with a focus on pushing advanced knowledge such as risk prevention and special scenario handling, such as "Identifying Risk Points in Cross-border Remittances".

[0067] In this embodiment of the application, by constructing a user capability profile to generate adapted operation guidance, it is possible to meet the needs of different scenarios and improve the flexibility and reliability of the operation knowledge-accompanying method.

[0068] In one exemplary embodiment, based on Figure 1 The illustrated embodiments, such as Figure 2 As shown, the provided method also includes:

[0069] Step 202: Obtain multi-source business data.

[0070] Among them, multi-source business data includes business system data, counter communication data, and historical document data.

[0071] For example, business system data can be collected in real time by connecting to the bank's core business systems, such as counter transaction systems or customer management systems, to collect user operation logs and business processing data, such as business type, customer needs, and processing results. This allows for the automatic identification of knowledge requirements corresponding to high-frequency business and error-prone steps. Counter communication data can be collected by configuring voice capture devices at branch counters to record conversations between tellers and customers, as well as business exchanges between tellers. Natural language processing technology can then convert the speech into text and extract key information, such as "communication scripts when a customer refuses to purchase wealth management products" or "key points for verifying large cash deposits and withdrawals." Historical document data can be processed using document parsing tools to extract structured knowledge such as business processes, precautions, and common problems from existing paper manuals, meeting minutes, and scanned electronic versions of handwritten notes from veteran tellers. This generates a business knowledge tag library, which can include tiered knowledge tags such as credit card activation - operation steps or corporate account opening - document review.

[0072] Step 204: Use a preset data classification model to classify and filter multi-source business data to obtain knowledge data with category labels.

[0073] In one possible implementation, step 204 may further include: performing semantic analysis and clustering on multi-source business data using a data classification model to obtain category labels corresponding to each multi-source business data; using preset normative constraints to verify the accuracy of multi-source business data in each scenario category label to obtain verification results corresponding to each multi-source business data; and performing deduplication and merging processing on multi-source business data with consistent verification results to obtain knowledge data with category labels.

[0074] For example, category labels may include "counter operations", "customer service", "policy and regulations", and "risk prevention and control". Each category label may be further subdivided into second-level sub-labels, such as "counter operations - transfer business" and "counter operations - loss reporting business".

[0075] Accuracy verification refers to using a pre-defined knowledge audit model to compare regulatory constraints with diverse business data, identify and mark conflicting content, and then send it to business experts for review to ensure the accuracy of the knowledge. Regulatory constraints can be generated based on official bank policy documents and a business specification library.

[0076] Deduplication and merging refers to merging similar knowledge, such as "operational differences in transfers through different channels," to avoid redundancy.

[0077] Step 206: Based on category labels, establish a mapping relationship between knowledge data and various business scenarios, and generate a knowledge graph based on the mapping relationship and knowledge data.

[0078] In one possible implementation, the knowledge graph includes multiple relationships; step 206 may further include: matching category labels with entity categories in each business scenario; for successfully matched category labels and at least one business scenario, constructing the relationship between the knowledge data corresponding to the category label and each business scenario.

[0079] Each business scenario can include a predefined standard business process backbone from the business initiation node, key operation nodes to the business completion node. Each node includes corresponding system interface elements, possible user operation sequences, expected data input and output, and possible abnormal situations. For example, the "personal cross-border remittance" business scenario model will clearly define multiple nodes such as "remittance application initiation", "recipient information entry", "remittance amount and purpose selection", and "risk warning and confirmation", and each node is associated with specific system identifiers, database field names, and backend interface call information.

[0080] In some embodiments, the large amount of valuable but difficult-to-standardize tacit knowledge acquired during the data collection phase, such as experienced tellers' skills in identifying counterfeit documents and their techniques for handling specific customer emotions, can be transformed into explicit knowledge consisting of "operational guidelines + risk warnings." For example, the operation guidelines section might state, "When verifying ID documents, pay close attention to the similarity between the photo and the applicant (≥85%) and the document's validity period (must be within the validity period)," while the risk warning section might state, "If in doubt, call the identity verification system for secondary verification." Then, through entity extraction and relation extraction techniques, this transformed explicit knowledge is mapped and mounted onto the backbone of an existing standard business process knowledge graph, creating a strong association with specific business scenarios. Thus, when querying knowledge data corresponding to a target business scenario, the retrieved explicit knowledge can be used as the target knowledge data based on these associations.

[0081] In this embodiment of the application, a knowledge graph is constructed through association relationships, which can transform implicit knowledge that originally relied on personal experience into identifiable and triggerable explicit knowledge, thereby effectively improving the utilization efficiency of bank branch knowledge and the comprehensiveness of the operational knowledge-accompanying method.

[0082] In one possible implementation, generating a knowledge graph based on mapping relationships and knowledge data includes: acquiring policy update data and user feedback data; and generating a knowledge graph using the policy update data, user feedback data, and knowledge data.

[0083] Policy update data can be obtained in real time by connecting to official platforms such as the People's Bank of China and the State Financial Regulatory Commission, using public opinion monitoring algorithms to capture policy updates, such as interest rate adjustments and new foreign exchange control regulations. User feedback data can be collected through the "Knowledge Correction / Supplement" button on the interactive interface. If users find omissions or errors while using the knowledge, they can submit user feedback data in real time. By summarizing and analyzing user feedback data, high-frequency feedback points are identified, such as "a step in a certain business operation is missing," and the knowledge graph is updated accordingly to ensure continuous optimization of knowledge.

[0084] In some embodiments, the method further includes monitoring the functional iteration data of various operating systems in bank branches, such as changes in the position of operation buttons, the addition of verification steps, and triggering the knowledge update process.

[0085] In some embodiments, the method further includes: updating the normative constraints using policy update information and user feedback information to obtain updated normative constraints; the updated normative constraints are used to verify the accuracy of multi-source business data in each category label to obtain the verification result corresponding to each multi-source business data.

[0086] In this embodiment, a knowledge graph is constructed based on diverse business data, and policy and business changes are monitored in real time to dynamically update the knowledge graph, which ensures the timeliness of the operational knowledge-accompanying method.

[0087] In one embodiment, such as Figure 3 As shown, an operational knowledge-accompanying method is provided, which includes the following steps 301 to 310. Wherein:

[0088] Step 301: Obtain multi-source business data, which includes business system data, counter communication data, and historical document data.

[0089] Step 302: Use a data classification model to perform semantic analysis and clustering on the multi-source business data to obtain the category labels corresponding to each multi-source business data.

[0090] Step 303: Use preset standard constraints to verify the accuracy of multi-source business data in each category label, and obtain the verification results corresponding to each multi-source business data.

[0091] Step 304: Perform deduplication and merging on the multi-source business data that have consistent verification results to obtain knowledge data with category labels.

[0092] Step 305: Based on category labels, establish a mapping relationship between knowledge data and various business scenarios, and generate a knowledge graph based on the mapping relationship and knowledge data.

[0093] In one embodiment, the knowledge graph includes multiple relationships; category tags are matched with entity categories in each business scenario; for a successfully matched category tag and at least one business scenario, the relationship between the knowledge data corresponding to the category tag and each business scenario is constructed.

[0094] In one embodiment, the method further includes acquiring policy update data and user feedback data; and generating a knowledge graph using the policy update data, user feedback data, and knowledge data.

[0095] Step 306: Obtain the user's operation behavior and historical operation data.

[0096] Step 307: Perform matching and location processing on the operation behavior to determine the target business scenario corresponding to the operation behavior.

[0097] Step 308: Construct a user capability profile based on historical operation data.

[0098] Step 309: Query the target knowledge data corresponding to the target business scenario from the pre-stored knowledge graph.

[0099] Knowledge graphs are obtained by classifying and transforming multi-source business data.

[0100] Step 310: Based on the capability profile and target knowledge data, generate operation guidelines and related knowledge links.

[0101] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0102] Based on the same inventive concept, this application also provides an operation knowledge-following device for implementing the operation knowledge-following method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more operation knowledge-following device embodiments provided below can be found in the limitations of the operation knowledge-following method described above, and will not be repeated here.

[0103] In one exemplary embodiment, such as Figure 4 As shown, an operational knowledge-accompanying device is provided, including: a data acquisition module 402, a scene positioning module 404, and an accompanying guidance module 406, wherein:

[0104] Data acquisition module 402 is used to acquire the operational behavior of teller users;

[0105] The scene positioning module 404 is used to match and locate the operation behavior to determine the target business scene corresponding to the operation behavior.

[0106] The accompanying guidance module 406 is used to query the target knowledge data corresponding to the target business scenario from the pre-stored knowledge graph, and generate operation guidance and related knowledge links based on the target knowledge data. The knowledge graph is obtained by classifying and transforming multi-source business data.

[0107] In one embodiment, the device further includes a graph construction module for acquiring multi-source business data, including business system data, counter communication data, and historical document data; classifying and filtering the multi-source business data using a preset data classification model to obtain knowledge data with category labels; establishing a mapping relationship between the knowledge data and various business scenarios based on the category labels; and generating a knowledge graph based on the mapping relationship and the knowledge data.

[0108] In one embodiment, the knowledge graph includes multiple relationships; the graph construction module is also used to match category labels with entity categories in each business scenario; for a successfully matched category label and at least one business scenario, the association between the knowledge data corresponding to the category label and each business scenario is constructed.

[0109] In one embodiment, the graph construction module is further configured to perform semantic analysis and clustering on multi-source business data using a data classification model to obtain category labels corresponding to each multi-source business data; to perform accuracy verification on the multi-source business data in each category label using preset normative constraints to obtain the verification result corresponding to each multi-source business data; and to perform deduplication and merging processing on the multi-source business data whose verification results are consistent to obtain knowledge data with category labels.

[0110] In one embodiment, the graph construction module is also used to acquire policy update data and user feedback data; and to generate a knowledge graph using the policy update data, user feedback data, and knowledge data.

[0111] In one embodiment, the accompanying guidance module 406 is further configured to acquire the user's historical operation data; construct the user's capability profile based on the historical operation data; and generate operation guidance based on the capability profile and target knowledge data.

[0112] The various modules in the aforementioned knowledge-accompanying device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0113] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 5As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements an operational knowledge-based method. The display unit is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0114] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0115] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0116] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0117] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0118] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0119] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0120] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0121] The above embodiments are merely illustrative of several implementation methods of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for accompaniing operational knowledge, characterized in that, The method includes: Obtain user actions; The operation behavior is matched and located to determine the target business scenario corresponding to the operation behavior; The target knowledge data corresponding to the target business scenario is queried from the pre-stored knowledge graph, and operation guidance and related knowledge links are generated based on the target knowledge data. The knowledge graph is obtained by classifying and transforming multi-source business data.

2. The method according to claim 1, characterized in that, The method further includes: Acquire the multi-source business data, which includes business system data, counter communication data, and historical document data; The multi-source business data is classified and filtered using a preset data classification model to obtain knowledge data with category labels; Based on the category labels, a mapping relationship is established between the knowledge data and various business scenarios, and the knowledge graph is generated according to the mapping relationship and the knowledge data.

3. The method according to claim 2, characterized in that, The knowledge graph includes multiple relationships; The step of establishing a mapping relationship between the knowledge data and various business scenarios based on the category tags, and generating the knowledge graph based on the mapping relationship and the knowledge data, includes: The category labels are matched with the entity categories in each of the business scenarios. For each successfully matched category label and at least one business scenario, an association is established between the knowledge data corresponding to the category label and each business scenario.

4. The method according to claim 2, characterized in that, The process of classifying and filtering the multi-source business data using a preset data classification model to obtain knowledge data with category labels includes: The data classification model is used to perform semantic analysis and clustering on the multi-source business data to obtain the category labels corresponding to each of the multi-source business data. The accuracy of the multi-source business data in each category label is verified using preset standard constraints, and the verification results corresponding to each multi-source business data are obtained. The multi-source business data that have consistent verification results are deduplicated and merged to obtain the knowledge data with category labels.

5. The method according to claim 4, characterized in that, The step of generating the knowledge graph based on the mapping relationship and the knowledge data includes: Obtain policy update data and user feedback data; The knowledge graph is generated using the policy update data, the user feedback data, and the knowledge data.

6. The method according to any one of claims 1-5, characterized in that, The operation guide generated based on the knowledge data includes: Obtain the user's historical operation data; Based on the historical operation data, construct the user's capability profile; The operation guide is generated based on the capability profile and the target knowledge data.

7. A device for accompanying operational knowledge, characterized in that, The device includes: The data acquisition module is used to acquire user actions. The scene positioning module is used to match and locate the operation behavior to determine the target business scene corresponding to the operation behavior. The accompanying guidance module is used to query the target knowledge data corresponding to the target business scenario from the pre-stored knowledge graph, and generate operation guidance and related knowledge links based on the target knowledge data. The knowledge graph is obtained by classifying and transforming multi-source business data.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images