Method and device for processing enterprise knowledge

Abstract

The present disclosure is about a method and device for processing enterprise knowledge, and relates to the field of data processing technology. The method includes: obtaining enterprise knowledge data, generating a knowledge graph using the enterprise knowledge data; obtaining characteristic information of enterprise users, and generating user portraits of enterprise users based on the characteristic information; the characteristic information includes characteristics associated with the enterprise knowledge data; using the user portrait to obtain the demand data of enterprise users associated with the enterprise knowledge data within a preset time period; inputting the user portrait, demand data and knowledge graph into a pre-trained demand prediction model to obtain the demand prediction results output by the demand prediction model; selecting target enterprise knowledge from the knowledge graph according to the demand prediction results; and pushing the target enterprise knowledge to the terminal device of the enterprise user. This solution can improve the utilization rate of enterprise knowledge.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, and in particular to a method and device for processing enterprise knowledge. Background Art

[0002] In related technologies, enterprises need to manage and apply corporate knowledge. The traditional knowledge pipeline method is to disperse knowledge among different storage media and departments, forming information islands. It is difficult to break down information barriers, and the utilization rate of knowledge is low, so corporate knowledge cannot be fully utilized. Summary of the invention

[0003] In order to overcome the problems existing in the related art, the present disclosure provides a method and device for processing enterprise knowledge.

[0004] According to a first aspect of an embodiment of the present disclosure, a method for processing enterprise knowledge is provided, comprising:

[0005] Acquire enterprise knowledge data, and generate a knowledge graph using the enterprise knowledge data;

[0006] Acquire characteristic information of an enterprise user, and generate a user profile of the enterprise user based on the characteristic information; the characteristic information includes characteristics associated with the enterprise knowledge data;

[0007] Using the enterprise user portrait, obtaining demand data of the enterprise user associated with the enterprise knowledge data within a preset time period;

[0008] Inputting the enterprise user portrait, the demand data and the knowledge graph into a pre-trained demand forecasting model to obtain a demand forecasting result output by the demand forecasting model;

[0009] According to the demand forecast result, selecting target enterprise knowledge from the knowledge graph;

[0010] Pushing the target enterprise knowledge to the terminal device of the enterprise user;

[0011] The demand data includes any one or more of the following items:

[0012] Work scenario data, information browsing data, emotional data, and geographic location data;

[0013] Wherein, after the enterprise user portrait is used to obtain the demand data of the enterprise user associated with the enterprise knowledge data within a preset time period, the method further includes:

[0014] Identify whether there is mutation data in the demand data;

[0015] When it is identified that there is mutation data in the demand data, re-acquiring characteristic information of the enterprise user;

[0016] Updating the user portrait using the reacquired feature information;

[0017] The obtaining of demand data of the enterprise user associated with the enterprise knowledge data within a preset time period by using the enterprise user portrait includes:

[0018] Using the updated enterprise user portrait, obtaining demand data of the enterprise user associated with the enterprise knowledge data within a preset time period;

[0019] The method further includes:

[0020] Inputting the enterprise user portrait, the demand data and the knowledge graph into a pre-trained knowledge flow prediction model to obtain a flow direction prediction result and / or a flow time prediction result output by the knowledge flow prediction model; the flow direction prediction result is a knowledge transmission line;

[0021] Pushing the flow direction prediction result and / or the flow time prediction result to the terminal device of the enterprise user;

[0022] The method further includes:

[0023] The flow direction prediction results are used to construct a knowledge map for tracking the dissemination path and application effect of knowledge.

[0024] According to a second aspect of an embodiment of the present disclosure, there is provided a device for processing enterprise knowledge, including:

[0025] A generating unit, used to obtain enterprise knowledge data and generate a knowledge graph using the enterprise knowledge data;

[0026] A first acquisition unit is used to acquire characteristic information of an enterprise user and generate a user portrait of the enterprise user based on the characteristic information; the characteristic information includes characteristics associated with the enterprise knowledge data;

[0027] A second acquisition unit, configured to acquire demand data of the enterprise user associated with the enterprise knowledge data within a preset time period by using the enterprise user portrait;

[0028] A prediction unit, used to input the enterprise user portrait, the demand data and the knowledge graph into a pre-trained demand prediction model to obtain a demand prediction result output by the demand prediction model;

[0029] A selection unit, configured to select target enterprise knowledge from the knowledge graph according to the demand prediction result;

[0030] A push unit, used to push the target enterprise knowledge to the terminal device of the enterprise user;

[0031] The demand data includes any one or more of the following items:

[0032] Work scenario data, information browsing data, emotional data, and geographic location data;

[0033] The device further comprises:

[0034] An identification unit, used to identify whether there is mutation data in the demand data;

[0035] The third acquisition unit is used to re-acquire the characteristic information of the enterprise user when it is identified that there is mutation data in the demand data;

[0036] An updating unit, used to update the user portrait using the re-acquired feature information;

[0037] The second acquisition unit is specifically used for:

[0038] Using the updated enterprise user portrait, the demand data of enterprise users associated with enterprise knowledge data within a preset time period is obtained;

[0039] The device further comprises:

[0040] An output unit, used to input enterprise user portraits, demand data and knowledge graphs into a pre-trained knowledge flow prediction model to obtain a flow direction prediction result and / or a flow time prediction result output by the knowledge flow prediction model; the flow direction prediction result is a knowledge transmission line;

[0041] The push unit is also used to push the flow direction prediction result and / or the flow time prediction result to the terminal device of the enterprise user;

[0042] The device further comprises:

[0043] A construction unit is used to construct a knowledge map using the flow direction prediction result to track the propagation path and application effect of knowledge.

[0044] According to a third aspect of an embodiment of the present disclosure, an electronic device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method described in any one of the first aspects is implemented.

[0045] According to a fourth aspect of an embodiment of the present disclosure, there is provided a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the method according to any one of the first aspects is implemented.

[0046] According to a fifth aspect of an embodiment of the present disclosure, a computer program product is provided, comprising a computer program, wherein the computer program implements the method as described in any one of the first aspects when executed by a processor.

[0047] The technical solution provided by the embodiments of the present disclosure may include the following beneficial effects: by acquiring enterprise knowledge data, generating a knowledge graph using the enterprise knowledge data; acquiring characteristic information of enterprise users, generating user portraits of enterprise users based on the characteristic information; the characteristic information includes characteristics associated with enterprise knowledge data; using user portraits to acquire demand data associated with enterprise knowledge data of enterprise users within a preset time period; inputting user portraits, demand data and knowledge graphs into a pre-trained demand forecasting model to obtain demand forecasting results output by the demand forecasting model; selecting target enterprise knowledge from the knowledge graph based on the demand forecasting results; and pushing target enterprise knowledge to the terminal device of the enterprise user. Based on user portraits, demand data and knowledge graphs, enterprise knowledge that can meet actual needs can be pushed to enterprise users under the premise of considering the correlation between different knowledge, thereby breaking down the information barriers between different storage media or different departments in the enterprise and improving the utilization rate of enterprise knowledge.

[0048] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0050] Figure 1 The present invention is a flowchart of a method for processing enterprise knowledge according to an exemplary embodiment.

[0051] Figure 2 The present invention is a block diagram of a device for processing enterprise knowledge according to an exemplary embodiment.

[0052] Figure 3 The invention is a block diagram showing an apparatus for a method for processing enterprise knowledge according to an exemplary embodiment. DETAILED DESCRIPTION

[0053] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0054] The terms used in the disclosed embodiments are only for the purpose of describing specific embodiments, and are not intended to limit the disclosed embodiments. The singular forms "a", "an" and "the" used in the disclosed embodiments and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings.

[0055] It should be understood that although the terms first, second, third, etc. may be used to describe various information in the disclosed embodiments, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the disclosed embodiments, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein may be interpreted as "at" or "when" or "in response to determination".

[0056] In addition, various forms of processes shown in the embodiments of the present disclosure may be used to reorder, add or delete steps. For example, the steps described in the present application may be performed in parallel, sequentially or in different orders, as long as the desired results of the technical solution disclosed in the present disclosure can be achieved, and this document does not limit this.

[0057] It should be noted that in the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0058] In related technologies, enterprises need to manage and apply corporate knowledge. The traditional knowledge pipeline method is to disperse knowledge among different storage media and departments, forming information islands. It is difficult to break down information barriers, and the utilization rate of knowledge is low, so corporate knowledge cannot be fully utilized.

[0059] In order to solve the above problems, the present disclosure provides a method and device for processing enterprise knowledge, which obtains enterprise knowledge data and generates a knowledge graph using the enterprise knowledge data; obtains characteristic information of enterprise users and generates user portraits of enterprise users based on the characteristic information; the characteristic information includes characteristics associated with enterprise knowledge data; uses user portraits to obtain demand data associated with enterprise knowledge data of enterprise users within a preset time period; inputs user portraits, demand data and knowledge graphs into a pre-trained demand prediction model to obtain demand prediction results output by the demand prediction model; selects target enterprise knowledge from the knowledge graph based on the demand prediction results; and pushes the target enterprise knowledge to the terminal device of the enterprise user. Based on user portraits, demand data and knowledge graphs, enterprise knowledge that can meet actual needs can be pushed to enterprise users under the premise of considering the correlation between different knowledge, thereby breaking the information barriers between different storage media or different departments in the enterprise and improving the utilization rate of enterprise knowledge.

[0060] Figure 1 is a flow chart of a method for processing enterprise knowledge according to an exemplary embodiment. Figure 1 As shown, it should be noted that the enterprise knowledge processing method of the embodiment of the present disclosure is applied to the enterprise knowledge processing device. Figure 1 As shown, the method may include the following steps:

[0061] Step 101, obtain enterprise knowledge data, and use the enterprise knowledge data to generate a knowledge graph.

[0062] In some embodiments of the present disclosure, any one or more of the following methods may be used to obtain enterprise knowledge data: using crawler technology to automatically crawl internal data sources or external data sources of the enterprise, using natural language processing technology to clean and parse text, extracting keywords, entities and other information, and obtaining enterprise knowledge data from a pre-built enterprise knowledge base. Among them, tags and classification systems may be used to effectively organize the content in the enterprise knowledge base for easy retrieval and reuse.

[0063] In some embodiments of the present disclosure, the original enterprise knowledge data may be preprocessed to obtain standardized enterprise knowledge data. The enterprise knowledge data may include author, time, source, etc., to facilitate classification and retrieval. The above preprocessing operation may include removing outliers, filling missing values, unifying data formats, etc. from the original enterprise knowledge data to ensure data quality.

[0064] In the disclosed embodiments, a Neo4j graph database may be used to store knowledge nodes and relationships, and a graph architecture may be designed based on previously defined entity and relationship models. Preprocessed data may be imported into the graph database to construct an initial knowledge graph. New data sources may also be monitored and captured in real time to automatically or semi-automatically update the knowledge graph.

[0065] In some embodiments of the present disclosure, an event trigger mechanism can also be designed, such as automatically triggering the update of the knowledge graph when a new document is uploaded or the project status changes. The accuracy and completeness of the graph can also be evaluated regularly, and continuously improved through user feedback and algorithm optimization. Applications such as knowledge search, recommendation systems, and knowledge maps can also be developed based on the graph to promote the circulation and value-added of knowledge.

[0066] In some embodiments of the present disclosure, NLP (Natural Language Processing) technology can be used to parse the acquired unstructured knowledge, automatically extract keywords and summaries, and attach metadata tags to facilitate subsequent retrieval and classification.

[0067] Step 102: Acquire characteristic information of the enterprise user, and generate a user profile of the enterprise user based on the characteristic information.

[0068] The characteristic information includes characteristics associated with the enterprise knowledge data.

[0069] In the disclosed embodiments, the above-mentioned characteristic information may include the user's basic information (such as position, interests), behavioral characteristics (such as frequently visited areas, active time periods), influence and interaction in social networks.

[0070] Step 103, using the enterprise user portrait, obtain the demand data of the enterprise users associated with the enterprise knowledge data within a preset time period.

[0071] It is understandable that, based on the enterprise user portrait, the demand data of the enterprise users associated with the enterprise knowledge data in different time periods can be determined, so that the related enterprise knowledge can be pushed to the users in different time periods.

[0072] In some embodiments of the present disclosure, the demand data includes any one or more of the following items:

[0073] Work scene data, information browsing data, emotional data, and geographic location data.

[0074] In one embodiment, indicators that meet actual needs can be selected to quantify user needs, such as counting users' click rate, dwell time, number of content sharing, etc. on a specific topic.

[0075] In addition, the demand data within the preset time period can be arranged in chronological order to obtain a time series formed by different demand data, and the above demand data can be updated based on the time series, that is, the demand data including the time series can be input into the demand forecasting model to improve the accuracy of the forecast results. The long-term trend and cyclical pattern in the demand data can be identified by using time series analysis; the long-term upward or downward trend of the data can be found through model fitting; short-term interest demand fluctuations can be captured by analyzing residuals or using high-frequency components (such as weekly and monthly changes).

[0076] It should be noted that the above emotion data can be predicted based on the user portrait and relevant data associated with the user emotion.

[0077] For example, by obtaining the user's conversation or context in the chat software, it can be seen that the user may feel stressed and need to complete multiple tasks efficiently. At the same time, the user also needs to seek some relaxing or efficiency-enhancing methods to relieve work pressure. Based on this, relevant content can be pushed to the user.

[0078] In one embodiment, the user portrait and the above-mentioned relevant data associated with the user's emotions can be input into a pre-trained neural network model to obtain the emotion prediction result of the neural network model data.

[0079] In some embodiments of the present disclosure, after step 103, the following steps may also be included:

[0080] Identify whether there is mutation data in the demand data;

[0081] When it is identified that there is mutation data in the demand data, the characteristic information of the enterprise user is re-acquired;

[0082] Update the user profile using the retrieved feature information;

[0083] Step 103 may specifically include: using the updated enterprise user portrait to obtain demand data of the enterprise users associated with the enterprise knowledge data within a preset time period.

[0084] It is understandable that there are usually mutation data in demand data. The existence of mutation data may be caused by some special conditions of the user. Therefore, when it is identified that there is mutation data in the demand data, the characteristic information of the enterprise user is re-acquired to determine whether there is an emergency situation for the enterprise user, and the user portrait is updated using the re-acquired characteristic information. In this way, the demand data associated with the enterprise knowledge data of the enterprise user within the preset time period is obtained according to the updated enterprise user portrait, so as to make timely adjustments to the promoted enterprise knowledge and improve the rationality of the push.

[0085] In one embodiment, statistical methods or machine learning algorithms may be used to identify anomalies in the data (ie, the mutation data mentioned above), which may be signals of sudden changes in user interest requirements.

[0086] As a possible example, the requirement data may include any one or more of the following items:

[0087] User behavior data: records of knowledge items that users have browsed, searched, read, shared, or created in the past, which can reflect users' interests, needs, preferences, and activity levels;

[0088] Knowledge content features: including keyword extraction, topic tags, document type, length, etc. of text content, used to understand and quantify the value and relevance of knowledge;

[0089] Social network data: social graphs within an organization, such as who collaborates with whom frequently and information sharing patterns among team members, which can reveal social network effects of knowledge flow;

[0090] Time series data: timestamps of when knowledge items are accessed and updated, as well as temporal patterns of user activity, to capture temporal dependencies;

[0091] Contextual information: Such as geographic location, department information, job role, etc. This information can help the model better understand the context of knowledge needs.

[0092] Step 104, input the enterprise user portrait, demand data and knowledge graph into the pre-trained demand forecasting model to obtain the demand forecasting result output by the demand forecasting model.

[0093] In one embodiment, the demand model can be pre-trained using the user's historical demand data, historical enterprise knowledge push information, and time series formed by different historical demand data, so that the demand prediction model can predict target enterprise knowledge that meets the needs of enterprise users.

[0094] As an example of a possible implementation, each content item (document, video, course, etc.) in the knowledge graph can be labeled with multi-dimensional labels, including subject, difficulty, applicable population, etc., so as to improve the matching accuracy of the demand prediction model. Natural language processing technology can be used to automatically extract content summaries and keywords to assist manual review and labeling.

[0095] As an example, the above demand forecasting model can adopt graph neural network GNN, which can capture the complex associations and knowledge propagation patterns between nodes (such as employees or knowledge points), so that the knowledge graph can be more effectively used to output demand forecasting results.

[0096] In one embodiment, context-related knowledge recommendations can be provided based on factors such as the user's current work scenario, task requirements, and emotional state, for example:

[0097] Work scenario analysis: The user is in the quality center, and her main responsibilities involve process management, quality control, and daily administrative assistance. She is currently at the end of the work week, and an important project is about to enter the review stage, which means she needs to pay attention to the integrity of the project documents, the compliance of the process, and possible potential risk points; Task requirement analysis: prepare weekly reports, review project documents, arrange meetings for next week, and plan personal learning and growth; Emotional judgment: Judging from the conversation or context, the user may feel stressed and need to complete multiple tasks efficiently, and also seek some relaxing or efficiency-enhancing methods to relieve work pressure;

[0098] Recommended context-related knowledge: Project review knowledge package: Recommend a project review checklist, including necessary documents, common problem troubleshooting, quality standard quick reference table, etc., to help her review project documents efficiently and ensure that nothing is missed. Provide a "Project Risk Management Manual" covering emergency response strategies in case of emergency; Guide to writing efficient weekly reports: Based on the tool for summarizing the work content of a week, automatically generate a draft of a weekly report, including the schedule completed this week, a summary of to-do items, and a review of important chat records, reducing the burden of manual writing. Share an article on "How to write an efficient weekly report" to guide how to extract key points and present results, so that the weekly report is both detailed and concise; Time management and stress relief skills: Recommend an e-book or short article on time management, such as "The Pomodoro Technique", to teach how to use time efficiently and improve work efficiency. Share a short meditation audio or deep breathing exercise to help her relax quickly and adjust her emotional state during intense work; Personal growth resources: Based on the needs for process compliance and learning growth mentioned earlier, recommend an online course, such as "Quality Management and Six Sigma Methods", to promote her professional growth. It is recommended to join relevant professional development communities or subscribe to industry newsletters to keep up with the latest quality management trends;

[0099] Implementation and feedback: Remind the user that the above recommendations are customized based on the current work and emotional state, and can be flexibly adjusted according to actual conditions. Encourage her to provide feedback on the effect after use so as to further optimize the recommended content.

[0100] In another embodiment, context information such as geographic location and time may be used to make recommendations more tailored to the actual needs of the user, for example:

[0101] Scene setting: The geographical location is XX City, the city where XX Company is located. Time: 15:41 on October 11, 2024, Friday, close to the end of get off work. User status: The user is preparing a weekly report, feeling a little nervous, and thinking about how to relax in the evening;

[0102] Dinner recommendation: Considering that it is getting close to the end of the get off work day, the user may want to find a place to eat near the company. Recommended content: Call the geolocation service to identify highly rated restaurants near the user's current location, especially those suitable for quick meals and relaxed environments. For example, XX vegetarian restaurant is only a 5-minute walk from the company and is known for its healthy light meals and fast service, which is very suitable for weekday dinners;

[0103] Traffic travel suggestions: Suppose the user plans to attend an industry exchange meeting on the other side of the city on the weekend. Recommended content: Use the real-time traffic information API to analyze the current traffic conditions and expected weekend traffic flow, and recommend the best travel method. For example, it is recommended to use Metro Line 3 to transfer to Line 2 to the destination after the Friday evening rush hour (after 18:30) to avoid congested sections and save travel time;

[0104] Weekend activity suggestions: Considering that users may want to relax after a busy week. Recommended content: Combined with the current weather forecast in the city (assuming it is a sunny and warm weekend), recommend outdoor concerts in the city, where you can enjoy the natural scenery and experience the artistic atmosphere to help you relax. At the same time, check the remaining tickets through the ticketing platform and provide a convenient ticket purchase link;

[0105] Weekly report auxiliary tool: The user is writing a weekly report and needs to improve efficiency. Recommended content: In view of the current work scenario, it is recommended to use a tool to summarize the work content of the week, automatically summarize the key work data and events of the week, and quickly generate a draft of the weekly report. In addition, an efficient document editing tool is recommended, such as cloud-based collaborative office software, so that users can continue to edit and improve the weekly report on the subway on their way home. Implementation and feedback;

[0106] When providing the above recommendations, send them to her via messaging software or email to ensure the timeliness and accessibility of the information. At the same time, attach a brief reason for the recommendation and an operation guide so that the user can quickly understand and adopt the suggestions. Encourage users to give feedback based on their personal experience so that future recommendations can be more accurate and personalized.

[0107] Step 105: Select target enterprise knowledge from the knowledge graph based on the demand forecast results.

[0108] In some embodiments of the present disclosure, the target enterprise knowledge may include enterprise knowledge personalized for the user, and may also include popular knowledge related to the user, that is, knowledge information that can be predicted to become a hot topic and is of high importance to the user's current work.

[0109] Step 106: Push the target enterprise knowledge to the terminal device of the enterprise user.

[0110] In one embodiment, the demand forecast result may be the type of knowledge that needs to be pushed to the user, and may also include the amount of data.

[0111] In some embodiments of the present disclosure, after step 106, the method may further include the following steps:

[0112] Inputting enterprise user portraits, demand data and knowledge graphs into a pre-trained knowledge flow prediction model to obtain a flow direction prediction result and / or a flow time prediction result output by the knowledge flow prediction model;

[0113] The flow direction prediction results and / or flow time prediction results are pushed to the terminal devices of the enterprise users.

[0114] It should be noted that the above flow direction prediction result can be a knowledge transmission line, that is, the predicted objects to which the knowledge will be pushed, and the above flow time prediction result can be the time required to transmit the knowledge to the target object.

[0115] In one embodiment, the knowledge flow prediction model can be obtained by training a long short-term memory network (LSTM, Long Short-Term Memory).

[0116] In one embodiment, the flow direction prediction results can also be used to construct a knowledge map to track the knowledge propagation path and application effect and evaluate the value-added effect of knowledge.

[0117] In some embodiments of the present disclosure, after step 106, the method may further include the following steps:

[0118] Sending inquiry information to the terminal device; the inquiry information is used to display on the terminal device whether the enterprise user is satisfied with the target enterprise knowledge;

[0119] Receiving reply information sent by the enterprise user through the terminal device; the reply information is the reply information to the inquiry information;

[0120] Adjust the parameters of the demand forecasting model based on the response information.

[0121] It is understandable that in order to enable the pushed enterprise knowledge to meet the actual needs of users, inquiry information can be sent to the terminal devices used by enterprise users to obtain user feedback on the target enterprise knowledge and make timely adjustments to the prediction model based on the feedback.

[0122] In some embodiments of the present disclosure, the method may further include:

[0123] Evaluate the enterprise knowledge data according to the preset multiple evaluation indicators to obtain the evaluation indicator values ​​corresponding to the multiple evaluation indicators;

[0124] The evaluation index values ​​corresponding to the multiple evaluation indicators are fused to obtain the contribution evaluation index value.

[0125] In one embodiment, the evaluation indicator may include feedback from users on the pushed enterprise knowledge.

[0126] In one embodiment, preset weight values ​​of each of the multiple evaluation indicators may be obtained, and the multiple evaluation indicator values ​​may be weighted and summed according to the weight values ​​to obtain the contribution evaluation indicator value.

[0127] In some embodiments, the contribution evaluation index value can be used to evaluate enterprise knowledge providers, thereby playing a role in encouraging enterprise knowledge providers. It can also be used to assign priorities to enterprise knowledge. For example, the value of enterprise knowledge can be evaluated by the contribution evaluation index value. The higher the value of enterprise knowledge, the higher the priority it can be pushed.

[0128] As an example, the above-mentioned evaluation indicators may include the knowledge output of enterprise employees (such as the number of uploaded documents, the number of published blogs, etc.), knowledge influence (such as the number of times the content is viewed, downloaded, and cited), knowledge innovation (such as novelty evaluation, expert review score), and knowledge application effect (such as quantitative indicators such as project success rate and cost savings after the enterprise knowledge is adopted).

[0129] In some embodiments of the present disclosure, knowledge review and refinement can also be performed: after the project is completed, the knowledge review process is automatically started to refine the lessons learned and form a case library, for example:

[0130] Standardize the review process and design a review template: Develop a standardized review template, including project overview, goal review, execution process, performance analysis, problem summary, experience extraction and other sections; Process automation: Develop a workflow automation tool to automatically trigger the review task after the project is completed, designate a person in charge, and clearly specify the submission deadline;

[0131] Knowledge verification and review, peer review: design an online review process, invite domain experts or project members to review the refined knowledge points to ensure the accuracy and practicality of the content; machine-assisted verification: use machine learning models to conduct preliminary verification of the consistency and logic of the content to reduce manual burden;

[0132] Knowledge dissemination and application, knowledge base integration: Integrate verified knowledge points into the enterprise knowledge base and store them by subject, project type and other dimensions; Intelligent recommendation: Combine user behavior analysis and machine learning algorithms to intelligently recommend relevant review knowledge to employees, accelerating the absorption and application of knowledge;

[0133] Feedback and iteration, effect evaluation: Establish a tracking mechanism for the effect of knowledge application, such as evaluating the influence of knowledge review through indicators such as employee surveys and project success rates; Continuous optimization: Based on the evaluation results and user feedback, continuously optimize the review template, refinement process and recommendation algorithm to form a closed loop of knowledge management.

[0134] According to the method for processing enterprise knowledge proposed in the embodiment of the present disclosure, the enterprise knowledge data is obtained, and a knowledge graph is generated using the enterprise knowledge data; characteristic information of enterprise users is obtained, and user portraits of enterprise users are generated based on the characteristic information; the characteristic information includes characteristics associated with the enterprise knowledge data; the demand data of enterprise users associated with the enterprise knowledge data within a preset time period is obtained using the user portrait; the user portrait, demand data and knowledge graph are input into a pre-trained demand prediction model to obtain the demand prediction results output by the demand prediction model; according to the demand prediction results, target enterprise knowledge is selected from the knowledge graph; and the target enterprise knowledge is pushed to the terminal device of the enterprise user. Based on user portraits, demand data and knowledge graphs, enterprise knowledge that can meet actual needs can be pushed to enterprise users under the premise of considering the correlation between different knowledge, thereby breaking the information barriers between different storage media or different departments in the enterprise and improving the utilization rate of enterprise knowledge.

[0135] Figure 2 FIG. 1 is a block diagram of a device for processing enterprise knowledge according to an exemplary embodiment. Figure 2 The device includes a generating unit 201, a first acquiring unit 202, a second acquiring unit 203, a predicting unit 204, a selecting unit 205 and a pushing unit 206.

[0136] The generating unit 201 is used to obtain enterprise knowledge data and generate a knowledge graph using the enterprise knowledge data;

[0137] A first acquisition unit 202 is used to acquire characteristic information of enterprise users and generate a user profile of the enterprise users based on the characteristic information; the characteristic information includes characteristics associated with enterprise knowledge data;

[0138] The second acquisition unit 203 is used to acquire demand data of enterprise users associated with enterprise knowledge data within a preset time period by using enterprise user portraits;

[0139] The prediction unit 204 is used to input the enterprise user portrait, demand data and knowledge graph into the pre-trained demand prediction model to obtain the demand prediction result output by the demand prediction model;

[0140] A selection unit 205 is used to select target enterprise knowledge from the knowledge graph according to the demand prediction result;

[0141] The push unit 206 is used to push the target enterprise knowledge to the terminal device of the enterprise user.

[0142] In some embodiments of the present disclosure, the demand data includes any one or more of the following items:

[0143] Work scene data, information browsing data, emotional data, and geographic location data.

[0144] In some embodiments of the present disclosure, the device may further include:

[0145] An identification unit, used to identify whether there is mutation data in the demand data;

[0146] The third acquisition unit is used to re-acquire the characteristic information of the enterprise user when it is identified that there is mutation data in the demand data;

[0147] An updating unit, used to update the user portrait using the re-acquired feature information;

[0148] The second acquisition unit 203 can be specifically used for:

[0149] Fourth, the updated enterprise user portrait is used to obtain the demand data of the enterprise users associated with the enterprise knowledge data within a preset time period.

[0150] In some embodiments of the present disclosure, the device may further include:

[0151] An output unit, used to input enterprise user portraits, demand data and knowledge graphs into a pre-trained knowledge flow prediction model to obtain a flow direction prediction result and / or a flow time prediction result output by the knowledge flow prediction model;

[0152] The push unit is also used to push the flow direction prediction results and / or flow time prediction results to the terminal device of the enterprise user.

[0153] In some embodiments of the present disclosure, the device may further include:

[0154] The inquiry unit is used to send inquiry information to the terminal device; the inquiry information is used to display on the terminal device whether the enterprise user is satisfied with the target enterprise knowledge;

[0155] A receiving unit, used to receive reply information sent by the enterprise user through the terminal device; the reply information is reply information to the inquiry information;

[0156] A parameter adjustment unit is used to adjust the parameters of the demand forecasting model based on the reply information.

[0157] In some embodiments of the present disclosure, the device may further include:

[0158] An evaluation unit, used to evaluate the enterprise knowledge data according to a plurality of preset evaluation indicators, and obtain evaluation indicator values ​​corresponding to each of the plurality of evaluation indicators;

[0159] The fusion unit is used to fuse the evaluation index values ​​corresponding to the multiple evaluation indicators to obtain the contribution evaluation index value.

[0160] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0161] According to the enterprise knowledge processing device proposed in the embodiment of the present disclosure, the enterprise knowledge data is obtained, and a knowledge graph is generated using the enterprise knowledge data; characteristic information of enterprise users is obtained, and user portraits of enterprise users are generated based on the characteristic information; the characteristic information includes characteristics associated with the enterprise knowledge data; the demand data of enterprise users associated with the enterprise knowledge data within a preset time period is obtained using the user portrait; the user portrait, demand data and knowledge graph are input into a pre-trained demand prediction model to obtain the demand prediction results output by the demand prediction model; according to the demand prediction results, target enterprise knowledge is selected from the knowledge graph; and the target enterprise knowledge is pushed to the terminal device of the enterprise user. Based on user portraits, demand data and knowledge graphs, enterprise knowledge that can meet actual needs can be pushed to enterprise users under the premise of considering the correlation between different knowledge, thereby breaking the information barriers between different storage media or different departments in the enterprise and improving the utilization rate of enterprise knowledge.

[0162] Figure 3 300 is a block diagram of an apparatus for a method according to an exemplary embodiment. For example, the apparatus 300 may be an electronic device, such as a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0163] Reference Figure 3 , the device 300 may include one or more of the following components: a processing component 302 , a memory 304 , a power component 306 , a multimedia component 308 , an audio component 310 , an input / output (I / O) interface 312 , a sensor component 314 , and a communication component 316 .

[0164] The processing component 302 generally controls the overall operation of the device 300, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 302 may include one or more processors 320 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 302 may include one or more modules to facilitate the interaction between the processing component 302 and other components. For example, the processing component 302 may include a multimedia module to facilitate the interaction between the multimedia component 308 and the processing component 302.

[0165] The memory 304 is configured to store various types of data to support operations on the device 300. Examples of such data include instructions for any application or method operating on the device 300, contact data, phone book data, messages, pictures, videos, etc. The memory 304 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0166] The power component 306 provides power to the various components of the device 300. The power component 306 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device 300.

[0167] The multimedia component 308 includes a screen that provides an output interface between the device 300 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 308 includes a front camera and / or a rear camera. When the device 300 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0168] The audio component 310 is configured to output and / or input audio signals. For example, the audio component 310 includes a microphone (MIC), and when the device 300 is in an operation mode, such as a call mode, a recording mode, and a speech recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 304 or sent via the communication component 316. In some embodiments, the audio component 310 also includes a speaker for outputting audio signals.

[0169] I / O interface 312 provides an interface between processing component 302 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: home button, volume button, start button, and lock button.

[0170] The sensor assembly 314 includes one or more sensors for providing various aspects of status assessment for the device 300. For example, the sensor assembly 314 can detect the open / closed state of the device 300, the relative positioning of components, such as the display and keypad of the device 300, the sensor assembly 314 can also detect the position change of the device 300 or a component of the device 300, the presence or absence of user contact with the device 300, the orientation or acceleration / deceleration of the device 300, and the temperature change of the device 300. The sensor assembly 314 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 314 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 314 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0171] The communication component 316 is configured to facilitate wired or wireless communication between the device 300 and other devices. The device 300 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 316 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 316 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0172] In an exemplary embodiment, the apparatus 300 may be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above methods.

[0173] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 304 including instructions, and the instructions can be executed by a processor 320 of the device 300 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0174] In an exemplary embodiment, a computer program product is also provided, comprising a computer program, which implements the above method when executed by the processor 320 of the device 300 .

[0175] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are to be considered exemplary only, and the true scope and spirit of the present invention are indicated by the following claims.

[0176] It should be understood that the present invention is not limited to the exact construction that has been described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A method for processing enterprise knowledge, characterized in that: include: Acquire enterprise knowledge data, and generate a knowledge graph using the enterprise knowledge data; Acquire characteristic information of an enterprise user, and generate a user profile of the enterprise user based on the characteristic information; The characteristic information includes characteristics associated with the enterprise knowledge data; Using the enterprise user portrait, obtaining demand data of the enterprise user associated with the enterprise knowledge data within a preset time period; Inputting the enterprise user portrait, the demand data and the knowledge graph into a pre-trained demand forecasting model to obtain a demand forecasting result output by the demand forecasting model; According to the demand forecast result, selecting target enterprise knowledge from the knowledge graph; Pushing the target enterprise knowledge to the terminal device of the enterprise user; The demand data includes any one or more of the following items: Work scenario data, information browsing data, emotional data, and geographic location data; Wherein, after the enterprise user portrait is used to obtain the demand data of the enterprise user associated with the enterprise knowledge data within a preset time period, the method further includes: Identify whether there is mutation data in the demand data; When it is identified that there is mutation data in the demand data, re-acquiring characteristic information of the enterprise user; Updating the user portrait using the reacquired feature information; The obtaining of demand data of the enterprise user associated with the enterprise knowledge data within a preset time period by using the enterprise user portrait includes: Using the updated enterprise user portrait, obtaining demand data of the enterprise user associated with the enterprise knowledge data within a preset time period; The method further includes: Inputting the enterprise user portrait, the demand data and the knowledge graph into a pre-trained knowledge flow prediction model to obtain a flow direction prediction result and / or a flow time prediction result output by the knowledge flow prediction model; the flow direction prediction result is a knowledge transmission line; Pushing the flow direction prediction result and / or the flow time prediction result to the terminal device of the enterprise user; The method further includes: The flow direction prediction results are used to construct a knowledge map for tracking the dissemination path and application effect of knowledge.

2. The method for processing enterprise knowledge according to claim 1, characterized in that: After pushing the target enterprise knowledge to the terminal device of the enterprise user, the method further includes: Sending inquiry information to the terminal device; the inquiry information is used to display on the terminal device whether the enterprise user is satisfied with the target enterprise knowledge; receiving a reply message sent by the enterprise user through the terminal device; the reply message is a reply message to the inquiry message; The demand forecasting model is adjusted based on the response information.

3. The method for processing enterprise knowledge according to claim 1, characterized in that: Also includes: Evaluate the enterprise knowledge data according to a plurality of preset evaluation indicators to obtain evaluation indicator values ​​corresponding to each of the plurality of evaluation indicators; The evaluation index values ​​corresponding to the multiple evaluation indexes are fused to obtain a contribution evaluation index value.

4. A device for processing enterprise knowledge, characterized in that: include: A generating unit, used to obtain enterprise knowledge data and generate a knowledge graph using the enterprise knowledge data; A first acquisition unit, configured to acquire characteristic information of an enterprise user, and generate a user profile of the enterprise user based on the characteristic information; The characteristic information includes characteristics associated with the enterprise knowledge data; A second acquisition unit, configured to acquire demand data of the enterprise user associated with the enterprise knowledge data within a preset time period by using the enterprise user portrait; A prediction unit, used to input the enterprise user portrait, the demand data and the knowledge graph into a pre-trained demand prediction model to obtain a demand prediction result output by the demand prediction model; A selection unit, configured to select target enterprise knowledge from the knowledge graph according to the demand prediction result; A push unit, used to push the target enterprise knowledge to the terminal device of the enterprise user; The demand data includes any one or more of the following items: Work scenario data, information browsing data, emotional data, and geographic location data; The device further comprises: An identification unit, used to identify whether there is mutation data in the demand data; The third acquisition unit is used to re-acquire the characteristic information of the enterprise user when it is identified that there is mutation data in the demand data; An updating unit, used to update the user portrait using the re-acquired feature information; The second acquisition unit is specifically used for: Using the updated enterprise user portrait, the demand data of enterprise users associated with enterprise knowledge data within a preset time period is obtained; The device further comprises: An output unit, used to input enterprise user portraits, demand data and knowledge graphs into a pre-trained knowledge flow prediction model to obtain a flow direction prediction result and / or a flow time prediction result output by the knowledge flow prediction model; the flow direction prediction result is a knowledge transmission line; The push unit is also used to push the flow direction prediction result and / or the flow time prediction result to the terminal device of the enterprise user; The device further comprises: A construction unit is used to construct a knowledge map using the flow direction prediction result to track the propagation path and application effect of knowledge.

5. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method according to any one of claims 1 to 3 is implemented.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 3 is implemented.

7. A computer program product, comprising a computer program, characterized in that The computer program implements the method according to any one of claims 1 to 3 when executed by a processor.

Images