Knowledge processing method and related device

Abstract

The invention provides a knowledge processing method and a related device, which can be applied to the field of big data or finance. In the application, after the user updates the target knowledge according to the data updating demand, the target node and the association weight value of the target node can be determined based on the pre-constructed knowledge connection directed graph, and the target node is the node pointed by the starting node corresponding to the target knowledge. The knowledge corresponding to the target node is the knowledge which can be browsed after the target knowledge, so that the possibility that the knowledge corresponding to the target node needs to be modified after the target knowledge is modified is large, and the knowledge corresponding to the target node is output in sequence after the target knowledge is updated; the knowledge associated with the updated knowledge can be provided for the user, so that an updating reference is provided, the user is prevented from missing part of knowledge during updating, and the reliability and accuracy of knowledge updating are improved.

Description

Technical Field

[0001] The present application relates to the field of financial technology, and in particular to a knowledge processing method and related devices. Background Art

[0002] In order to facilitate the management of knowledge, an enterprise knowledge base system is built. The enterprise knowledge base system covers all kinds of required knowledge. During the use of knowledge, it needs to be continuously updated to meet the user's needs for the reliability and accuracy of knowledge.

[0003] Currently, when performing knowledge update operations, users will update knowledge based on business needs and experience. However, in actual applications, it is easy to omit some knowledge that needs to be updated, resulting in low reliability and accuracy of knowledge updates. Summary of the invention

[0004] In view of the above problems, the present application provides a knowledge processing method and related devices to achieve the purpose of avoiding missing updated knowledge by prompting the associated knowledge of the updated knowledge. The specific scheme is as follows:

[0005] The first aspect of the present application provides a knowledge processing method, comprising:

[0006] Acquire target knowledge that has been updated, where the target knowledge is knowledge updated by the user according to data update requirements;

[0007] Obtain a pre-constructed knowledge connection directed graph; in the knowledge connection directed graph, there is a browsing jump relationship between two connected nodes and the number of browsing jumps between the nodes is greater than a preset threshold, and the associated weight value of the node is obtained by updating the initial weight value, and the initial weight value is determined based on the non-browsing jump data of the associated node connected to the node;

[0008] Determine a target node and an associated weight value of the target node from the knowledge connection directed graph; the target node is a node pointed to by a start node, and the start node is a node corresponding to the target knowledge; the importance of the target node is positively correlated with the associated weight value;

[0009] Sorting the target nodes according to the magnitude relationship of the associated weight values ​​to obtain a sorting result;

[0010] According to the sorting result, the knowledge corresponding to the target node is output.

[0011] In a possible implementation, the process of constructing the knowledge connection directed graph includes:

[0012] Get knowledge browsing history;

[0013] Determine the knowledge with browsing jump relationship and the browsing jump times between the knowledge with browsing jump relationship from the knowledge browsing records;

[0014] Filter out the knowledge whose browsing jump times are greater than a preset threshold, and take each of the filtered knowledge as a node;

[0015] Establish connection relationships between nodes based on the browsing jump relationship between nodes;

[0016] Determine an initial weight value of a node, update the initial weight value, and obtain an associated weight value of the node to obtain a knowledge connection directed graph; the initial weight value is determined based on non-browsing jump data of other nodes connected to the node.

[0017] In a possible implementation, determining an initial weight value of a node includes:

[0018] Based on the connection relationship between the nodes, determine each associated node pointed to by the node;

[0019] Acquire non-browsing jump data between the node and the associated node;

[0020] Determining an association value between the node and the associated node from the non-browsing jump data;

[0021] The sum of the associated values ​​is calculated, and the sum is normalized to obtain an initial weight value.

[0022] In a possible implementation, updating the initial weight value to obtain the associated weight value of the node includes:

[0023] The initial weight value of the node is iteratively updated by using the number of associated nodes connected to the node and the initial weight value until an iterative update stop condition is met, thereby obtaining the associated weight value of the node.

[0024] In a possible implementation, outputting the knowledge corresponding to the target node according to the sorting result includes:

[0025] Acquiring the modified content of the target knowledge;

[0026] Determine modification suggestion data of the knowledge corresponding to the target node by using the modification content;

[0027] According to the sorting result, the knowledge corresponding to the target node and the modification suggestion data corresponding to the knowledge are output.

[0028] In a possible implementation, determining modification suggestion data of the knowledge corresponding to the target node by using the modification content includes:

[0029] Performing a keyword extraction operation on the modified content to obtain keywords;

[0030] Locate the keyword from the knowledge corresponding to the target node to obtain a positioning result;

[0031] According to the modification method of the modification content, the modification method of the positioning result is determined to obtain modification suggestion data.

[0032] A second aspect of the present application provides a knowledge processing device, comprising:

[0033] A knowledge acquisition module, used to acquire target knowledge that has been updated, where the target knowledge is the knowledge updated by the user according to data update requirements;

[0034] A directed graph acquisition module is used to acquire a pre-constructed knowledge connection directed graph; in the knowledge connection directed graph, there is a browsing jump relationship between two connected nodes and the number of browsing jumps between the nodes is greater than a preset threshold, and the associated weight value of the node is obtained by updating the initial weight value, and the initial weight value is determined based on the non-browsing jump data of the associated node connected to the node;

[0035] A data determination module is used to determine a target node and an associated weight value of the target node from the knowledge connection directed graph; the target node is the node pointed to by the start node, and the start node is the node corresponding to the target knowledge; the importance of the target node is positively correlated with the associated weight value;

[0036] A sorting module is used to sort the target nodes according to the magnitude relationship of the associated weight values ​​to obtain a sorting result;

[0037] The output module is used to output the knowledge corresponding to the target node according to the sorting result.

[0038] A third aspect of the present application provides a computer program product, including computer-readable instructions, which, when executed on an electronic device, enables the electronic device to implement the above-mentioned knowledge processing method.

[0039] A fourth aspect of the present application provides an electronic device, comprising at least one processor and a memory connected to the processor, wherein:

[0040] The memory is used to store computer programs;

[0041] The processor is used to execute the computer program so that the electronic device can implement the above-mentioned knowledge processing method.

[0042] A fifth aspect of the present application provides a computer storage medium, which carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement the above-mentioned knowledge processing method.

[0043] By means of the above technical scheme, the present application provides a knowledge processing method and related devices. In the present invention, after the user updates the target knowledge according to the data update requirements, the target node and the associated weight value of the target node can be determined based on the pre-constructed knowledge connection directed graph. The target node is the node pointed to by the start node corresponding to the target knowledge, that is, the knowledge corresponding to the target node is the knowledge that will be browsed after the target knowledge, which further indicates that after modifying the target knowledge, it is more likely that the knowledge corresponding to the target node needs to be modified. After updating the target knowledge, the knowledge corresponding to the target node is output in sequence, which can provide the user with knowledge associated with the updated knowledge, and then provide an update reference, so as to avoid missing some knowledge when the user updates, and improve the reliability and accuracy of knowledge update. In addition, in the present invention, the larger the associated weight value of the target node, the higher the importance. Then, according to the size relationship of the associated weight value, the target nodes are sorted, and the knowledge corresponding to the target node with high importance is ranked first in the sorting result, which can preferably recommend the knowledge with high importance to the user, so that the user can perform the update operation according to the important procedure, and improve the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0045] Figure 1 A schematic diagram of a system architecture provided for this application;

[0046] Figure 2 A schematic diagram of a terminal structure provided for this application;

[0047] Figure 3 A schematic diagram of a server structure provided for this application;

[0048] Figure 4 A flowchart of a knowledge processing method provided for this application;

[0049] Figure 5 A schematic diagram of a knowledge connection directed graph provided for this application;

[0050] Figure 6 A flowchart of a method for generating a knowledge connection directed graph provided in this application;

[0051] Figure 7 A schematic diagram of the structure of a knowledge processing device provided in this application;

[0052] Figure 8 A schematic diagram of the structure of an electronic device provided in this application. DETAILED DESCRIPTION

[0053] The following describes the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. The terms used in the implementation method section of the present application are only used to explain the specific embodiments of the present application, and are not intended to limit the present application.

[0054] The embodiments of the present application are described below in conjunction with the accompanying drawings. Those skilled in the art will appreciate that, with the development of technology and the emergence of new scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0055] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and need not be used to describe a specific order or sequential order. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, which is only to describe the distinction mode adopted by the objects of the same attributes when describing in the embodiments of the present application. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, so that the process, method, system, product or equipment comprising a series of units need not be limited to those units, but may include other units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0056] 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, stored data, displayed data, 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 relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0057] See also Figure 1 , Figure 1 A schematic diagram of a system architecture is shown. The system may include a terminal 100 and a server 200. The server 200 may include one or more servers ( Figure 1 In the example, a server is included, and the server 200 can provide the method provided in the embodiment of the present application for one or more terminals.

[0058] The terminal 100 can receive the target knowledge modified by the user, and then send the target knowledge to the server 200 . The server 200 can obtain a processing result based on the received data, and return the processing result to the terminal 100 .

[0059] It should be understood that in some optional implementations, the terminal 100 can also complete the action of obtaining the processing result based on the received target knowledge by itself without the cooperation of the server, and the embodiments of the present application are not limited thereto.

[0060] Next describe Figure 1 The product form of the mid-terminal 100;

[0061] The terminal 100 in the embodiment of the present application can be a mobile phone, a tablet computer, a wearable device, a vehicle-mounted device, an augmented reality (AR) / virtual reality (VR) device, a laptop computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), etc., and the embodiment of the present application does not impose any limitation on this.

[0062] Figure 2 An optional hardware structure diagram of the terminal 100 is shown.

[0063] refer to Figure 2 As shown, the terminal 100 may include a radio frequency unit 110, a memory 120, an input unit 130, a display unit 140, a camera 150 (optional), an audio circuit 160 (optional), a speaker 161 (optional), a microphone 162 (optional), an earphone jack 163 (optional), a processor 170, an external interface 180, a power supply 190 and other components. Those skilled in the art will appreciate that Figure 2 These are merely examples of terminals or multi-function devices and do not constitute limitations on the terminals or multi-function devices, which may include more or fewer components than those shown in the figures, or combinations of certain components, or different components.

[0064] The input unit 130 can be used to receive input digital or character information, and generate key signal input related to the user settings and function control of the portable multifunctional device. Specifically, the input unit 130 may include a touch screen 131 (optional) and / or other input devices 132. The touch screen 131 can collect the user's touch operations on or near it (such as the user's operation on or near the touch screen using any suitable object such as fingers, joints, stylus, etc.), and drive the corresponding connection device according to a pre-set program. The touch screen can detect the user's touch action on the touch screen, convert the touch action into a touch signal and send it to the processor 170, and can receive and execute the command sent by the processor 170; the touch signal at least includes the touch point coordinate information. The touch screen 131 can provide an input interface and an output interface between the terminal 100 and the user. In addition, the touch screen can be implemented using multiple types such as resistive, capacitive, infrared and surface acoustic wave. In addition to the touch screen 131, the input unit 130 can also include other input devices. Specifically, other input devices 132 may include, but are not limited to, one or more of a physical keyboard, function keys (such as a volume control key, a switch key, etc.), a trackball, a mouse, a joystick, and the like.

[0065] Among them, the input device 132 can receive input data and the like.

[0066] The display unit 140 can be used to display information input by the user or provided to the user, various menus of the terminal 100, interactive interfaces, file displays and / or playback of any multimedia files. In the embodiment of the present application, the display unit 140 can be used to display the interface of knowledge processing, processing results, etc.

[0067] The memory 120 can be used to store instructions and data. The memory 120 can mainly include an instruction storage area and a data storage area. The data storage area can store various data, such as multimedia files, texts, etc.; the instruction storage area can store software units such as operating systems, applications, instructions required for at least one function, or their subsets and extensions. It can also include a non-volatile random access memory; provide the processor 170 with hardware, software and data resources including management of computing and processing equipment, and support control software and applications. It is also used for the storage of multimedia files, and the storage of running programs and applications.

[0068] The processor 170 is the control center of the terminal 100. It uses various interfaces and lines to connect various parts of the entire terminal 100. By running or executing instructions stored in the memory 120 and calling data stored in the memory 120, it executes various functions of the terminal 100 and processes data, thereby controlling the terminal device as a whole. Optionally, the processor 170 may include one or more processing units; preferably, the processor 170 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface and application program, and the modem processor mainly processes wireless communication. It is understandable that the above-mentioned modem processor may not be integrated into the processor 170. In some embodiments, the processor and the memory may be implemented on a single chip, and in some embodiments, they may also be implemented separately on separate chips. The processor 170 may also be used to generate corresponding operation control signals, send them to corresponding components of the computing and processing device, read and process data in the software, especially read and process data and programs in the memory 120, so that each functional module therein performs corresponding functions, thereby controlling the corresponding components to act according to the requirements of the instructions.

[0069] Among them, the memory 120 can be used to store software codes related to the knowledge processing method, the processor 170 can execute the steps of the knowledge processing method, and can also schedule other units (such as the above-mentioned input unit 130 and display unit 140) to realize corresponding functions.

[0070] The radio frequency unit 110 (optional) can be used for receiving and sending information or receiving and sending signals during a call, for example, after receiving the downlink information of the base station, it is sent to the processor 170 for processing; in addition, the designed uplink data is sent to the base station. Generally, the RF circuit includes but is not limited to an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier (Low Noise Amplifier, LNA), a duplexer, etc. In addition, the radio frequency unit 110 can also communicate with network devices and other devices through wireless communication. The wireless communication can use any communication standard or protocol, including but not limited to Global System of Mobile communication (Global System of Mobile communication, GSM), General Packet Radio Service (General Packet Radio Service, GPRS), Code Division Multiple Access (Code Division Multiple Access, CDMA), Wideband Code Division Multiple Access (Wideband Code Division Multiple Access, WCDMA), Long Term Evolution (Long Term Evolution, LTE), email, Short Messaging Service (SMS), etc.

[0071] In this embodiment of the present application, the RF unit 110 can send data to the server 200 and receive processing results sent by the server 200.

[0072] It should be understood that the radio frequency unit 110 is optional and can be replaced by other communication interfaces, such as a network port.

[0073] The terminal 100 also includes a power supply 190 (such as a battery) for supplying power to various components. Preferably, the power supply can be logically connected to the processor 170 through a power management system, so that the power management system can manage functions such as charging, discharging, and power consumption.

[0074] The terminal 100 further includes an external interface 180 , which may be a standard Micro USB interface or a multi-pin connector, and may be used to connect the terminal 100 to communicate with other devices, or to connect a charger to charge the terminal 100 .

[0075] Although not shown, the terminal 100 may also include a flashlight, a wireless fidelity (WiFi) module, a Bluetooth module, sensors with different functions, etc., which are not described in detail here. Some or all of the methods described below may be applied in the following embodiments. Figure 2 In the terminal 100 shown.

[0076] Next describe Figure 1 The product form of the server 200;

[0077] Figure 3 A schematic diagram of the structure of a server 200 is provided, such as Figure 3 As shown, the server 200 includes a bus 201, a processor 202, a communication interface 203, and a memory 204. The processor 202, the memory 204, and the communication interface 203 communicate with each other via the bus 201.

[0078] The bus 201 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 3 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0079] The processor 202 may be any one or more of a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0080] The memory 204 may include a volatile memory, such as a random access memory (RAM). The memory 204 may also include a non-volatile memory, such as a read-only memory (ROM), a flash memory, a hard drive (HDD), or a solid state drive (SSD).

[0081] The memory 204 may be used to store software codes related to the knowledge processing method, the processor 202 may execute the steps of the knowledge processing method of the chip, and may also schedule other units to implement corresponding functions.

[0082] It should be understood that the above-mentioned terminal 100 and server 200 can be centralized or distributed devices, and the processors in the above-mentioned terminal 100 and server 200 (such as processor 170 and processor 202) can be hardware circuits (such as application specific integrated circuit (ASIC), field-programmable gate array (FPGA), general-purpose processor, digital signal processor (DSP), microprocessor or microcontroller, etc.), or a combination of these hardware circuits. For example, the processor can be a hardware system with an instruction execution function, such as a CPU, DSP, etc., or a hardware system without an instruction execution function, such as an ASIC, FPGA, etc., or a combination of the above-mentioned hardware systems without an instruction execution function and hardware systems with an instruction execution function.

[0083] In order to facilitate the management of knowledge, an enterprise knowledge base system is built. The enterprise knowledge base system covers all kinds of required knowledge. The knowledge in the enterprise knowledge base system has problems such as outdated content and insufficient update frequency. This outdated knowledge may mislead users or fail to meet their needs. Therefore, artificial knowledge needs to be continuously updated during use to meet users' needs for the reliability and accuracy of knowledge.

[0084] Currently, when performing knowledge update operations, users, such as knowledge maintenance personnel, will update knowledge based on business needs and subjective experience. However, in actual applications, there are users who only update part of the knowledge, but some knowledge is omitted, resulting in this part of the knowledge not being updated, making the reliability and accuracy of knowledge update low.

[0085] Therefore, in order to improve the accuracy, reliability and comprehensiveness of knowledge updating, in the present invention, after the user updates part of the knowledge, such as at least one piece of knowledge, the knowledge associated with the updated knowledge will be determined, and the determined knowledge will be recommended to the user, so that the user can perform subsequent knowledge updating operations based on the recommendation results to avoid omissions in knowledge updating. In addition, in the present invention, when recommending knowledge, the corresponding modification method will also be recommended, so that the user can have a certain reference basis when updating knowledge, which can improve the updating efficiency compared to the method of determining how to update by self-analysis.

[0086] On the basis of the above content, the present application provides a knowledge processing method and related devices. In the present invention, after the user updates the target knowledge according to the data update requirements, the target node and the associated weight value of the target node can be determined based on the pre-constructed knowledge connection directed graph. The target node is the node pointed to by the start node corresponding to the target knowledge, that is, the knowledge corresponding to the target node is the knowledge that will be browsed after the target knowledge, which further indicates that after modifying the target knowledge, it is more likely that the knowledge corresponding to the target node needs to be modified. After updating the target knowledge, the knowledge corresponding to the target node is output in sequence, which can provide the user with knowledge associated with the updated knowledge, and then provide an update reference, so as to avoid missing some knowledge when the user updates, and improve the reliability and accuracy of knowledge update. In addition, in the present invention, the larger the associated weight value of the target node, the higher the importance. Then, according to the size relationship of the associated weight value, the target nodes are sorted, and the knowledge corresponding to the target node with high importance is ranked first in the sorting result, which can preferably recommend the knowledge with high importance to the user, so that the user can perform the update operation according to the important program, and improve the user experience.

[0087] It should be noted that the knowledge processing method and related devices provided by the present invention can be used in the field of big data or finance. The above is only an example and does not limit the application field of the knowledge processing method and related devices provided by the present invention.

[0088] In order to solve the above problems, an embodiment of the present application provides a knowledge processing method. The executor of the knowledge processing method in the present invention can be the above-mentioned terminal 100 or server 200. The terminal 100 can obtain the target knowledge modified by the user and perform knowledge recommendation operations according to the target knowledge, or the server 200 can obtain the target knowledge modified by the user and perform knowledge recommendation operations according to the target knowledge. Alternatively, the terminal 100 obtains the target knowledge modified by the user and sends the target knowledge to the server 200, and the server 200 performs knowledge recommendation operations according to the target knowledge.

[0089] The knowledge processing method of the embodiment of the present application is described in detail below with reference to the accompanying drawings. Figure 4 , Figure 4 A flow chart of a knowledge processing method provided in an embodiment of the present application is as follows: Figure 4 As shown, a knowledge processing method provided in an embodiment of the present application may include:

[0090] S11. Acquire the target knowledge that has been updated.

[0091] In actual applications, users, such as knowledge maintenance personnel, will update knowledge according to experience after receiving business needs, such as data update needs. After the user has updated at least one piece of knowledge or completed the knowledge update operation, the present invention can perform knowledge recommendation operations based on the knowledge updated by the user to avoid the user missing out on updating some knowledge.

[0092] In this embodiment, the target knowledge is the knowledge updated by the user according to the data update requirements; the number of target knowledge can be one or more, depending on the actual configuration. The present invention can perform knowledge association analysis and knowledge recommendation operations after the user updates one piece of knowledge, or stop the knowledge update operation after the user completes the update, such as when the user only updates one piece of knowledge, or stop the knowledge update operation after the user completes multiple pieces of knowledge, and then perform knowledge association analysis and knowledge recommendation operations.

[0093] The target knowledge can be a knowledge document or a web page, which is not limited in this embodiment. When the user updates the target knowledge, the user's modification operation can be recorded, and the modification content of the target knowledge can be recorded. The modification content can be, for example, changing "credit card interest rate increase" to "credit card interest rate reduction" and changing "bank card processing fee" to "bank card processing free of charge".

[0094] S12. Obtain a pre-built knowledge connection directed graph.

[0095] Among them, in the knowledge connection directed graph, there is a browsing jump relationship between two connected nodes and the number of browsing jumps between the nodes is greater than a preset threshold.

[0096] In practical applications, the knowledge connection directed graph can refer to Figure 5 As shown, Figure 5 In the database, there are three nodes, namely A, B and C. A points to B and C, and B points to A and C. Each node represents a piece of knowledge (also called a knowledge document). For example, node A represents knowledge A, and node B represents knowledge B. Then the knowledge base is represented as a directed graph, which represents the actual browsing jump relationship between documents. Only documents with browsing jump relationship are the focus of users.

[0097] A points to B (A→B) means that there is a browsing jump relationship from A to B, that is, the user browses knowledge B after browsing knowledge A.

[0098] In practical applications, in order to avoid the problem of a large scale of the knowledge connection directed graph caused by building a connection relationship between two nodes when there are only a small number of browsing jumps, the number of browsing jumps between knowledge is limited in the embodiment of the present invention. When the number of browsing jumps is large, such as greater than a preset threshold, it means that the browsing jump frequency between the two knowledge is high and the association relationship is stable, and the connection relationship between the two knowledge is built. If it is not greater than the preset threshold, it means that the browsing jump frequency between the two knowledge is low. In order to reduce the scale of the knowledge connection directed graph, the association relationship is unstable, and the connection relationship between the two knowledge will not be built.

[0099] like Figure 5 As shown, the number of browsing jumps from knowledge A to knowledge B is 100, which is greater than the preset threshold value 50, so a connection relationship of node A→B is constructed; the number of browsing jumps from knowledge C to knowledge A is 10, which is less than the preset threshold value 50, so a connection relationship of node C→A is not constructed.

[0100] against Figure 5 Each node in the network has its own associated weight value, which refers to the degree of association between the node and other nodes. The larger the associated weight value, the more important the node is.

[0101] In this embodiment, the associated weight value of the node is obtained by updating the initial weight value, which is the initial value when the weight value is iteratively updated, and the initial weight value is set based on the non-browsing jump data of the associated node connected to the node. Non-browsing jump data refers to data corresponding to non-browsing jump relationships other than browsing jump relationships, such as hyperlink jumps or embedded relationships between documents, reference relationships in standard documents, recommendation relationships of recommendation systems, directory hierarchical relationships of documents, etc.

[0102] S13. Determine a target node and an associated weight value of the target node from the knowledge connection directed graph.

[0103] After the target knowledge is determined, the starting node corresponding to the target knowledge is determined from the knowledge connection directed graph.

[0104] Then, the starting node is taken as the starting point, and the node pointed to by the starting node is found, which is the target node. That is, in this embodiment, the starting node is the node corresponding to the target knowledge; the target node is the node pointed to by the starting node.

[0105] From the above step S12, it can be seen that each target node has a corresponding association weight value. The larger the association weight value, the more important the node is, that is, the importance of the target node is positively correlated with the association weight value. In this embodiment, the association weight value of the target node is directly obtained to perform subsequent operations.

[0106] S14, sorting the target nodes according to the magnitude relationship of the associated weight values ​​to obtain a sorting result;

[0107] In this step, since the larger the association weight value is, the more important the node is, the target nodes should be sorted in descending order of the association weight values. The nodes at the front of the list have a high degree of importance, which means that when the data is updated, the priority to be updated is high and the update is required as soon as possible. Therefore, in this embodiment, the target nodes are sorted according to the size relationship of the association weight values ​​to obtain a sorting result.

[0108] S15. According to the sorting result, output the knowledge corresponding to the target node.

[0109] In this embodiment, after obtaining the sorting results, the knowledge corresponding to each target node is determined and the knowledge is output in sequence. After obtaining the output results, the user can analyze whether the knowledge in the output results needs to be updated. If it needs to be updated, the update operation is directly performed. The update operation can be, for example, revising the content, supplementing new relevant information, deleting outdated or erroneous content, etc.

[0110] If no update is needed, skip it and continue to analyze whether the next knowledge needs to be updated.

[0111] It should be noted that if there is only one target knowledge in this embodiment, a sorting result is obtained according to the above steps, and the knowledge is output according to the sorting result.

[0112] If there are multiple target knowledge, a ranking result can be obtained according to the above steps for each target knowledge, and the corresponding knowledge can be output according to the ranking result. Since the content updated by the user is similar when the knowledge is updated, there may be repeated knowledge in different ranking results when there are multiple target knowledge. The user can update the repeated knowledge once according to the needs.

[0113] In this embodiment, after the user updates the target knowledge according to the data update requirements, the target node and the associated weight value of the target node can be determined based on the pre-constructed knowledge connection directed graph. The target node is the node pointed to by the starting node corresponding to the target knowledge, that is, the knowledge corresponding to the target node is the knowledge that will be browsed after the target knowledge, which further indicates that after modifying the target knowledge, it is more likely that the knowledge corresponding to the target node needs to be modified. After updating the target knowledge, the knowledge corresponding to the target node is output in sequence, which can provide the user with knowledge associated with the updated knowledge, and then provide an update reference, so as to avoid missing some knowledge when the user updates, and improve the reliability and accuracy of knowledge update. In addition, in the present invention, the larger the associated weight value of the target node, the higher the importance. Then, according to the size relationship of the associated weight value, the target nodes are sorted, and the knowledge corresponding to the target node with high importance is ranked first in the sorting result. It can preferably recommend knowledge with high importance to the user, so that the user can perform update operations according to important procedures. By giving priority to important documents, the quality and accuracy of the entire knowledge base can be improved, and the user experience can be improved.

[0114] The above embodiment mentions the knowledge connection directed graph. Now, the construction process of the knowledge connection directed graph is introduced. Figure 6 , which may include:

[0115] S21. Obtain knowledge browsing records.

[0116] In specific implementation, the enterprise knowledge base system includes various knowledge, and users can access this knowledge. In the knowledge, hyperlink jumps or embedding between documents can be set. When users access the knowledge, they can access other knowledge through hyperlinks or embedding.

[0117] Alternatively, in knowledge, other knowledge is set by reference in a specification document, and other knowledge is accessed through the reference.

[0118] Alternatively, when accessing certain knowledge, the interface displaying the knowledge may be configured with a recommendation function of a recommendation system, which may recommend knowledge related to the currently accessed knowledge. When the user accesses the current knowledge, the user may access another knowledge through the recommendation function.

[0119] Alternatively, when accessing a certain piece of knowledge, other knowledge at the same directory level as the document containing the knowledge may be displayed, and the user may access the other knowledge by clicking on the other knowledge.

[0120] Or, when a user accesses a piece of knowledge, he wants to view another piece of knowledge. He searches for another piece of knowledge through functions such as search, and then jumps to another piece of knowledge. In addition, the knowledge jump method can be configured according to the actual scenario.

[0121] Regardless of the method adopted by the user to perform knowledge jump, the knowledge browsing record can be recorded, and the knowledge browsing record includes the browsing jump of various knowledge, such as A→B→C→D, etc.

[0122] In practical applications, knowledge browsing records can be obtained within a certain period of time, such as once every quarter, half a year, or year, and a knowledge connection directed graph is generated based on the knowledge browsing records. Subsequently, the knowledge connection directed graph needs to be monitored and updated regularly, such as updating the knowledge connection directed graph once every quarter or half a year to ensure that the knowledge connection directed graph is coordinated with other entries in the existing knowledge base and maintain the overall knowledge quality.

[0123] In addition, the knowledge browsing record includes the browsing records of all users. For the same user, if he jumps from knowledge A to knowledge B, and then jumps from knowledge A to knowledge B again, it is considered that the number of jumps from knowledge A to knowledge B is twice, that is, each jump is counted once.

[0124] S22: Determine the knowledge having a browsing jump relationship and the number of browsing jumps between the knowledge having a browsing jump relationship from the knowledge browsing records.

[0125] Specifically, after obtaining the knowledge browsing record, since it is necessary to analyze the jumps between different knowledge, it is necessary to determine the knowledge with browsing jump relationship. In this embodiment, the knowledge with browsing jump relationship is generally a group, and there are two knowledge in a group. If the arrangement order of two knowledge in a group is different, they are considered to be different groups. For example, taking A→B→C, A→C, B→A, C→A as examples, the knowledge with browsing jump relationship is A→B, B→C, A→C, B→A, C→A.

[0126] After obtaining the knowledge with browsing jump relationship, according to the above discussion, in order to avoid the problem of large scale of the knowledge connection directed graph, it is necessary to limit the number of browsing jumps and pre-configure a preset threshold. Therefore, it is necessary to count the number of browsing jumps between two pieces of knowledge to determine the size relationship with the preset threshold.

[0127] S23, filter out the knowledge with browsing jump times greater than a preset threshold, and take each of the filtered knowledge as a node.

[0128] Specifically, for the above-mentioned A→B, B→C, A→C, B→A, and C→A, the number of browsing jumps is counted respectively, and the knowledge with the number of browsing jumps greater than the preset threshold is screened out. For example, if the number of browsing jumps of A→B, B→C, A→C, and B→A is greater than the preset threshold, and the number of browsing jumps of C→A is not greater than the preset threshold, then C→A is eliminated, and only A→B, B→C, A→C, and B→A are retained to screen out knowledge. The screened out knowledge is A, B, and C, and then A, B, and C are respectively taken as a node.

[0129] S24. Establish connection relationships between nodes based on the browsing jump relationship between nodes.

[0130] Specifically, the browsing jump relationship between nodes is A→B, B→C, A→C, B→A. Taking A→B as an example, an arrow from A to B needs to be drawn to represent the jump from A to B. The connection relationship between nodes can be as follows: Figure 5 shown.

[0131] S25. Determine the initial weight value of the node, and update the initial weight value to obtain the associated weight value of the node to obtain a knowledge connection directed graph.

[0132] Among them, after obtaining the nodes and the connection relationship between the nodes, it is also necessary to determine the associated weight value of the node, so as to finally obtain the knowledge connection directed graph.

[0133] The association weight value is determined based on an initial weight value, and the initial weight value is determined based on non-browsing jump data of other nodes connected to the node.

[0134] In a possible implementation, determining the initial weight value of the node may include:

[0135] 1) Based on the connection relationship between nodes, determine each associated node to which the node points.

[0136] Specifically, Figure 5 Take node A in as an example, filter out the nodes executed by node A, Figure 5 In the example, A points to B and C, so B and C are associated nodes.

[0137] 2) Acquire non-browsing jump data between the node and the associated node.

[0138] According to the above discussion, the non-browsing jump data between the node and the associated node can be as follows:

[0139] Hyperlink jumps or embedded relationships between documents, reference relationships in standard documents, recommendation relationships in recommendation systems, directory hierarchical relationships where documents are located, etc. These data can be stored in the database and directly obtained from the database.

[0140] 3) Determine the association value between the node and the associated node from the non-browsing jump data.

[0141] For different relationships in non-browsing data, corresponding association values ​​can be configured. The association value can be the number of out-links. Regardless of the association value or the number of out-links, both represent the non-browsing jump association relationship between two nodes. Different non-browsing jump association relationships represent different degrees of association between nodes. Therefore, different association values ​​can be set for different non-browsing jump association relationships. Specifically, different association values ​​can be assigned based on expert experience. For example, if there is a hyperlink from knowledge A to knowledge B, the association value from A to B is 1; if the recommendation system recommends B to A, the association value from A to B is recorded as 2; if A and B belong to the same parent directory in the system directory, the association value from A to B is recorded as 3, etc.

[0142] 4) Calculate the sum of the associated values, normalize the sum, and obtain an initial weight value.

[0143] In practical applications, for two pieces of knowledge with a browsing jump relationship, there may be multiple non-browsing jump association relationships between the two pieces of knowledge. Therefore, it is necessary to sum the association values ​​of various non-browsing jump association relationships, and then perform a normalization operation, and use the normalized value as the initial weight value.

[0144] In this embodiment, the problem of large data calculation caused by excessively large values ​​can be avoided by normalization operation. In addition, when determining the initial weight value, multiple non-browsing jump associations are considered, and the association between the two pieces of knowledge is fully analyzed, avoiding the arbitrariness of initializing the initial weight value of each node with equal importance, so that the accuracy of the determined initial weight value is higher.

[0145] After obtaining the initial weight value, it is necessary to iteratively update the initial weight value to obtain the associated weight value of the node.

[0146] More specifically, the initial weight value of the node is iteratively updated using the number of associated nodes connected to the node and the initial weight value until an iterative update stop condition is met, thereby obtaining the associated weight value of the node.

[0147] In this embodiment, in order to fully consider the association relationship between nodes, the PageRank algorithm is introduced to perform weight value update operation. PageRank can be used to evaluate the importance or ranking of a web page in the search results. PageRank is a link analysis algorithm that measures the importance of a web page in the entire network by assigning numerical weights to the hyperlink structure between web pages. In the present invention, it is used in the knowledge weight update scenario to analyze the importance of each piece of knowledge. The above initial weight value is the initial PR (PageRank score, PR for short) value of the PageRank algorithm.

[0148] In the specific implementation, the PageRank algorithm is applied to the constructed knowledge connection directed graph. In each iteration, each node will obtain a PR value score according to the initial weight value and the number of associated nodes connected to it. When the number of iterations reaches a certain target, or the difference between the PR values ​​calculated twice is less than the threshold (the convergence condition is reached), the calculation is stopped. Each node corresponds to a PR value, which is the final associated weight value. The larger the associated weight value, the more important the knowledge is.

[0149] In this embodiment, the PageRank algorithm is applied to determine the association weight value of knowledge, so that the association weight value with high accuracy can be determined, and then subsequent knowledge recommendation operations are performed based on the association weight value.

[0150] In the above embodiment, when outputting the knowledge corresponding to the target node according to the sorting result, modification suggestion data of the knowledge can also be output to provide modification suggestions for users to update the knowledge. Specifically, outputting the knowledge corresponding to the target node according to the sorting result includes:

[0151] 1) Obtain the modified content of the target knowledge.

[0152] Specifically, when the user updates the target knowledge, the user's modification operations can be recorded, and the modification content of the target knowledge can be recorded. The modification content can be, for example, changing "credit card interest rate increase" to "credit card interest rate reduction" and changing "bank card processing fees" to "bank card processing free of charge."

[0153] 2) Using the modification content, determine modification suggestion data of the knowledge corresponding to the target node.

[0154] Specifically, the knowledge corresponding to the determined target node is the knowledge associated with the target knowledge modified by the user. For example, if the target knowledge is "credit card interest rate reduction", the knowledge corresponding to the target node may be "how credit card interest rates change". Therefore, the modification contents of the two are similar. Based on the modification content of the target knowledge, the modification content of the knowledge corresponding to the target node can be determined, which is the modification suggestion data.

[0155] In specific implementation, there are multiple ways to determine the modification suggestion data, which are introduced below:

[0156] 1. Implement it using a model.

[0157] Training data can be pre-configured, such as knowledge sample 1, knowledge sample 2 associated with knowledge sample 1, modified content of knowledge sample 1, and modified content of knowledge sample 2, and input into a model, such as a neural network model or a machine learning model for training. The association between the two knowledge samples and the association between the two modified contents are learned within the model. After the model training is completed and the model is put online for use, the target knowledge, the modified content of the target knowledge, and the knowledge corresponding to the target node are input into the model, and the model can output modification suggestion data of the knowledge corresponding to the target node.

[0158] 2. Use keyword positioning to achieve it.

[0159] In specific implementation, firstly, a keyword extraction operation is performed on the modified content to obtain keywords.

[0160] When performing a keyword extraction operation, the modified content is segmented, and then keywords are extracted from the segmentation results.

[0161] For example, if a user modifies "credit card interest rate rises" to "credit card interest rate falls", the keywords obtained after word segmentation are "credit card", "interest rate", "fall", and "rise". Since "fall" and "rise" have a wide range, the keywords selected are "credit card" and "interest rate".

[0162] Then, the keyword is located from the knowledge corresponding to the target node to obtain a location result.

[0163] Specifically, the user also needs to modify the knowledge related to the credit card interest rate in the knowledge corresponding to the target node. Therefore, the user can search for the words "credit card" and "interest rate" in the knowledge corresponding to the target node to query the positioning results.

[0164] Finally, according to the modification method of the modification content, the modification method of the positioning result is determined to obtain modification suggestion data.

[0165] For example, in the knowledge corresponding to the target node, after locating "credit card", the sentence containing the word "credit card" can be analyzed, and semantic analysis can be performed on the sentence to determine whether it is related to the credit card interest rate. If so, a modification suggestion data can be given as "credit card interest rate reduction". If it is not related to the credit card interest rate, such as related to credit card processing, the positioning result here can be skipped.

[0166] The same process is performed for the located "interest rate". If it is related to the credit card interest rate, the modification suggestion data can be given as "credit card interest rate reduction". If it is not related to the credit card interest rate, such as related to the loan interest rate, the positioning result here is skipped.

[0167] For all positioning results, the modification suggestion data are processed in the above manner until all positioning results are processed to obtain complete modification suggestion data corresponding to the knowledge. The modification suggestion data can be displayed in the knowledge in the form of annotations.

[0168] 3) According to the sorting result, the knowledge corresponding to the target node and the modification suggestion data corresponding to the knowledge are output.

[0169] Specifically, when outputting knowledge, knowledge with a higher ranking result and modification suggestion data are output first, and knowledge with a lower ranking result and modification suggestion data are output later.

[0170] In this embodiment, when updating knowledge, modification suggestions for the knowledge are given, which enables the user to quickly locate the modification area and improve the modification and update efficiency.

[0171] As can be seen from the above, the present invention measures the relevance and importance of knowledge between each document in the knowledge base system based on PageRank. After the knowledge maintainer updates a knowledge document, the system automatically recommends other knowledge documents related to the knowledge document and sorts them by importance. The knowledge maintainer can determine whether to update the recommended knowledge document based on the importance of the knowledge document recommended by the system. In addition, when recommending knowledge, modification suggestions will be given to shorten the user's update time and improve efficiency.

[0172] The above introduces a knowledge processing method provided by an embodiment of the present application, and the following will introduce a device for executing the above knowledge processing method.

[0173] See also Figure 7 , Figure 7 This is a schematic diagram of the structure of a knowledge processing device provided in an embodiment of the present application. Figure 7 As shown, the knowledge processing device comprises:

[0174] The knowledge acquisition module 11 is used to acquire target knowledge that has been updated, where the target knowledge is the knowledge updated by the user according to the data update requirements;

[0175] A directed graph acquisition module 12 is used to acquire a pre-constructed knowledge connection directed graph; in the knowledge connection directed graph, there is a browsing jump relationship between two connected nodes and the number of browsing jumps between the nodes is greater than a preset threshold, and the associated weight value of the node is obtained by updating the initial weight value, and the initial weight value is determined based on the non-browsing jump data of the associated node connected to the node;

[0176] The data determination module 13 is used to determine the target node and the associated weight value of the target node from the knowledge connection directed graph; the target node is the node pointed to by the start node, and the start node is the node corresponding to the target knowledge; the importance of the target node is positively correlated with the associated weight value;

[0177] A sorting module 14 is used to sort the target nodes according to the magnitude relationship of the associated weight values ​​to obtain a sorting result;

[0178] The output module 15 is used to output the knowledge corresponding to the target node according to the sorting result.

[0179] In a possible implementation, a directed graph construction module is further included, and the directed graph construction module includes:

[0180] The record acquisition submodule is used to acquire knowledge browsing records;

[0181] A data determination submodule, used to determine knowledge with a browsing jump relationship and the number of browsing jumps between the knowledge with a browsing jump relationship from the knowledge browsing records;

[0182] A screening submodule is used to screen out knowledge with a browsing jump count greater than a preset threshold, and each screened knowledge is used as a node;

[0183] The relationship establishment submodule is used to establish the connection relationship between nodes based on the browsing jump relationship between nodes;

[0184] The graph generation submodule is used to determine the initial weight value of the node, update the initial weight value, and obtain the associated weight value of the node to obtain a knowledge connection directed graph; the initial weight value is determined based on the non-browsing jump data of other nodes connected to the node.

[0185] In a possible implementation, the graph generation submodule includes:

[0186] A node determination unit, used to determine each associated node pointed to by the node based on the connection relationship between the nodes;

[0187] A data acquisition unit, used for acquiring non-browsing jump data between the node and the associated node;

[0188] an association value determining unit, configured to determine an association value between the node and the associated node from the non-browsing jump data;

[0189] The weight determination unit is used to calculate the sum of the associated values, normalize the sum, and obtain an initial weight value.

[0190] In a possible implementation, the graph generation submodule includes:

[0191] The weight updating unit is used to iteratively update the initial weight value of the node by using the number of associated nodes connected to the node and the initial weight value until the iterative update stopping condition is met, thereby obtaining the associated weight value of the node.

[0192] In a possible implementation, the output module 15 includes:

[0193] A modified content acquisition submodule, used to acquire the modified content of the target knowledge;

[0194] A suggestion determination submodule, used to determine modification suggestion data of the knowledge corresponding to the target node using the modification content;

[0195] The data output submodule is used to output the knowledge corresponding to the target node and the modification suggestion data corresponding to the knowledge according to the sorting result.

[0196] In a possible implementation, it is suggested to determine that the submodules include:

[0197] A keyword extraction unit, used to perform a keyword extraction operation on the modified content to obtain keywords;

[0198] A keyword locating unit, used to locate the keyword from the knowledge corresponding to the target node to obtain a locating result;

[0199] The modification determination unit is used to determine the modification method of the positioning result according to the modification method of the modification content, and obtain modification suggestion data.

[0200] In this embodiment, after the user updates the target knowledge according to the data update requirements, the target node and the associated weight value of the target node can be determined based on the pre-constructed knowledge connection directed graph. The target node is the node pointed to by the starting node corresponding to the target knowledge, that is, the knowledge corresponding to the target node is the knowledge that will be browsed after the target knowledge, which further indicates that after modifying the target knowledge, it is more likely that the knowledge corresponding to the target node needs to be modified. After updating the target knowledge, the knowledge corresponding to the target node is output in sequence, which can provide the user with knowledge associated with the updated knowledge, and then provide an update reference, so as to avoid missing some knowledge when the user updates, and improve the reliability and accuracy of knowledge update. In addition, in the present invention, the larger the associated weight value of the target node, the higher the importance. Then, according to the size relationship of the associated weight value, the target nodes are sorted, and the knowledge corresponding to the target node with high importance is ranked first in the sorting result. It can preferably recommend knowledge with high importance to the user, so that the user can perform update operations according to important procedures, thereby improving the user experience.

[0201] It should be noted that the working process of each module, sub-module and unit in this embodiment, please refer to the above corresponding description, and will not be repeated here.

[0202] The present application also provides an electronic device in an embodiment. Figure 8 As shown, it shows a schematic diagram of the structure of an electronic device suitable for implementing the embodiments of the present application. The electronic device in the embodiments of the present application may include but is not limited to fixed terminals such as mobile phones, notebook computers, PDAs (personal digital assistants), PADs (tablet computers), desktop computers, etc. Figure 8 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0203] like Figure 8 As shown, the electronic device may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 to a random access memory (RAM) 603 to implement the above-mentioned knowledge processing method. When the electronic device is powered on, various programs and data required for the operation of the electronic device are also stored in the RAM 603. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0204] Typically, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a memory card, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. Although Figure 8 An electronic device having various devices is shown, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0205] An embodiment of the present application also provides a computer program product, including computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements any knowledge processing method provided in the embodiment of the present application.

[0206] A computer-readable storage medium is also provided in an embodiment of the present application. The storage medium carries one or more computer programs. When one or more computer programs are executed by an electronic device, the electronic device can implement any knowledge processing method provided in the embodiment of the present application.

[0207] It should also be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the drawings of the device embodiments provided by the present application, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines.

[0208] Through the description of the above implementation mode, the technicians in the field can clearly understand that the present application can be implemented by means of software plus necessary general hardware, and of course, it can also be implemented by special hardware including special integrated circuits, special CPUs, special memories, special components, etc. In general, all functions completed by computer programs can be easily implemented by corresponding hardware, and the specific hardware structure used to implement the same function can also be various, such as analog circuits, digital circuits or special circuits. However, for the present application, software program implementation is a better implementation mode in more cases. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a readable storage medium, such as a computer floppy disk, a U disk, a mobile hard disk, a ROM, a RAM, a disk or an optical disk, etc., including a number of instructions to enable a computer device (which can be a personal computer, a training device, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0209] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product.

[0210] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, a computer, a training device, or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, training device, or data center. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a training device, a data center, etc. that includes one or more available media integrations. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.

Claims

1. A knowledge processing method, characterized in that: include: Acquire target knowledge that has been updated, where the target knowledge is knowledge updated by the user according to data update requirements; Get pre-built directed graphs of knowledge connections; In the knowledge connection directed graph, there is a browsing jump relationship between two connected nodes and the number of browsing jumps between the nodes is greater than a preset threshold, and the associated weight value of the node is obtained by updating the initial weight value, and the initial weight value is determined based on the non-browsing jump data of the associated node connected to the node; Determine a target node and an associated weight value of the target node from the knowledge connection directed graph; the target node is the node pointed to by the start node, and the start node is the node corresponding to the target knowledge; The importance of the target node is positively correlated with the associated weight value; Sorting the target nodes according to the magnitude relationship of the associated weight values ​​to obtain a sorting result; According to the sorting result, the knowledge corresponding to the target node is output.

2. The knowledge processing method according to claim 1, characterized in that: The construction process of the knowledge connection directed graph includes: Get knowledge browsing history; Determine the knowledge with browsing jump relationship and the browsing jump times between the knowledge with browsing jump relationship from the knowledge browsing records; Filter out the knowledge whose browsing jump times are greater than a preset threshold, and take each of the filtered knowledge as a node; Establish connection relationships between nodes based on the browsing jump relationship between nodes; Determine an initial weight value of a node, update the initial weight value, and obtain an associated weight value of the node to obtain a knowledge connection directed graph; the initial weight value is determined based on non-browsing jump data of other nodes connected to the node.

3. The knowledge processing method according to claim 2, characterized in that: Determine the initial weight value of the node, including: Based on the connection relationship between the nodes, determine each associated node pointed to by the node; Acquire non-browsing jump data between the node and the associated node; Determining an association value between the node and the associated node from the non-browsing jump data; The sum of the associated values ​​is calculated, and the sum is normalized to obtain an initial weight value.

4. The knowledge processing method according to claim 2, characterized in that: The initial weight value is updated to obtain the associated weight value of the node, including: The initial weight value of the node is iteratively updated by using the number of associated nodes connected to the node and the initial weight value until an iterative update stop condition is met, thereby obtaining the associated weight value of the node.

5. The knowledge processing method according to claim 1, characterized in that: According to the sorting results, the knowledge corresponding to the target node is output, including: Acquiring the modified content of the target knowledge; Determine modification suggestion data of the knowledge corresponding to the target node by using the modification content; According to the sorting result, the knowledge corresponding to the target node and the modification suggestion data corresponding to the knowledge are output.

6. The knowledge processing method according to claim 5, characterized in that: Determining modification suggestion data of the knowledge corresponding to the target node by using the modification content includes: Performing a keyword extraction operation on the modified content to obtain keywords; Locate the keyword from the knowledge corresponding to the target node to obtain a positioning result; According to the modification method of the modification content, the modification method of the positioning result is determined to obtain modification suggestion data.

7. A knowledge processing device, characterized in that: include: A knowledge acquisition module, used to acquire target knowledge that has been updated, where the target knowledge is the knowledge updated by the user according to data update requirements; A directed graph acquisition module is used to acquire a pre-built knowledge connection directed graph; In the knowledge connection directed graph, there is a browsing jump relationship between two connected nodes and the number of browsing jumps between the nodes is greater than a preset threshold, and the associated weight value of the node is obtained by updating the initial weight value, and the initial weight value is determined based on the non-browsing jump data of the associated node connected to the node; A data determination module, used to determine a target node and an associated weight value of the target node from the knowledge connection directed graph; the target node is the node pointed to by the start node, and the start node is the node corresponding to the target knowledge; The importance of the target node is positively correlated with the associated weight value; A sorting module is used to sort the target nodes according to the magnitude relationship of the associated weight values ​​to obtain a sorting result; The output module is used to output the knowledge corresponding to the target node according to the sorting result.

8. A computer program product, characterized in that It comprises computer-readable instructions, and when the computer-readable instructions are executed on an electronic device, the electronic device implements the knowledge processing method as claimed in any one of claims 1 to 6.

9. An electronic device, characterized in that: The method comprises at least one processor and a memory connected to the processor, wherein: The memory is used to store computer programs; The processor is used to execute the computer program so that the electronic device can implement the knowledge processing method as described in any one of claims 1 to 6.

10. A computer storage medium, characterized in that: The storage medium carries one or more computer programs, and when the one or more computer programs are executed by an electronic device, the electronic device can implement the knowledge processing method as described in any one of claims 1 to 6.

Images