CN112954025A

CN112954025A - Information pushing method, device, equipment and medium based on layered knowledge graph

Info

Publication number: CN112954025A
Application number: CN202110127423.XA
Authority: CN
Inventors: 李明琦
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2021-01-29
Filing date: 2021-01-29
Publication date: 2021-06-11
Anticipated expiration: 2041-01-29
Also published as: CN112954025B

Abstract

The present disclosure provides a method, an apparatus, a device, a medium, and a computer program product for pushing information, which relate to the technical field of artificial intelligence, and in particular, to the technical field of knowledge graph, intelligent recommendation, and natural language processing. The implementation scheme is as follows: acquiring a retrieval request from user side equipment; extracting the attention point of the user from the retrieval information in the retrieval request; determining target knowledge corresponding to the layered knowledge map and the user attention point based on the attention point of the user and a pre-constructed layered knowledge map, wherein the layered knowledge map comprises a technical field knowledge map and a non-technical field knowledge map; and pushing the target knowledge to the user equipment as target content.

Description

Information pushing method, device, equipment and medium based on layered knowledge graph

Technical Field

The present disclosure relates to the field of artificial intelligence, and more particularly to the field of knowledge-graph, intelligent recommendation, and natural language processing. In particular, the present disclosure provides a hierarchical knowledge graph-based information pushing method, apparatus, electronic device, computer-readable storage medium, and computer program product.

Background

Artificial intelligence is the subject of research that makes computers simulate some human mental processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.), both at the hardware level and at the software level. The artificial intelligence hardware technology generally comprises technologies such as a sensor, a special artificial intelligence chip, cloud computing, distributed storage, big data processing and the like, and the artificial intelligence software technology mainly comprises a computer vision technology, a voice recognition technology, a natural language processing technology, machine learning/deep learning, a big data processing technology, a knowledge graph spectrum technology and the like.

In a large-scale organization or company, due to the fact that the size of the organization or company is large, business is close to business, staff flow is large, and cross-department communication and cooperation are more. Meanwhile, the staff needs to face a large number of office scenes such as transaction and process processing, communication, cooperation, knowledge information acquisition and the like. This results in that staff needs to spend a lot of effort in finding solutions and people in daily work, resulting in low office efficiency. With the development and popularization of knowledge maps and natural language processing technologies, intelligent office based on enterprise knowledge management is increasingly emphasized, and becomes a key path for improving the office efficiency of enterprises.

Disclosure of Invention

The present disclosure provides a method, an apparatus, an electronic device, a computer-readable storage medium, and a computer program product for pushing information based on a hierarchical knowledge graph.

According to an aspect of the present disclosure, there is provided a computer-implemented hierarchical knowledge-graph-based information pushing method, including: acquiring a retrieval request from user equipment, wherein the retrieval request comprises retrieval information of a user aiming at target content, and performing word segmentation analysis on the retrieval information; extracting the attention points of the user from the retrieval information by using the attention point model; determining target knowledge corresponding to the attention point of the user in the layered knowledge graph according to the attention point of the user and a pre-constructed layered knowledge graph, wherein the layered knowledge graph comprises a technical field knowledge graph and a non-technical field knowledge graph, the technical field knowledge graph comprises a plurality of subdivided technical field knowledge graphs, and the non-technical field knowledge graph comprises a plurality of subdivided non-technical field knowledge graphs; and pushing the target knowledge as the target content to the user equipment.

According to yet another aspect of the present disclosure, there is provided a computer device including: a memory, a processor, and a computer program stored on the memory, wherein the processor is configured to execute the computer program to implement the steps of the method as described in the present disclosure.

According to yet another aspect of the present disclosure, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing a computer to perform a method as described in the present disclosure.

According to yet another aspect of the disclosure, a computer program product is provided, comprising a computer program, wherein the computer program realizes the steps of the method as described in the present disclosure when executed by a processor.

According to one or more embodiments of the disclosure, the method and the system can help the staff to timely and effectively locate the key problem in the system and quickly find a way and a method for solving the problem.

It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the embodiments and, together with the description, serve to explain the exemplary implementations of the embodiments. The illustrated embodiments are for purposes of illustration only and do not limit the scope of the claims. Throughout the drawings, identical reference numbers designate similar, but not necessarily identical, elements.

FIG. 1 illustrates a schematic diagram of an exemplary system in which various methods described herein may be implemented, according to an embodiment of the present disclosure;

FIG. 2 illustrates a flow diagram of a hierarchical knowledge-graph based push information method in accordance with an embodiment of the present disclosure;

FIG. 3 illustrates a flow diagram for building a hierarchical knowledge graph according to an embodiment of the present disclosure;

FIG. 4 illustrates a flow diagram for building a member representation tag in accordance with an embodiment of the present disclosure;

FIG. 5 illustrates a flow diagram of subdividing a membership representation tag in accordance with an embodiment of the present disclosure;

FIG. 6 shows a block diagram of a hierarchical knowledge graph-based push information device, according to an embodiment of the present disclosure;

FIG. 7 illustrates a structural block diagram of an exemplary electronic device that can be used to implement embodiments of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

In the present disclosure, unless otherwise specified, the use of the terms "first", "second", etc. to describe various elements is not intended to limit the positional relationship, timing relationship, or importance relationship of the elements, and such terms are used only to distinguish one element from another. In some examples, the first element and the second element may point to the same instance of the element, while in some cases they may also refer to different instances based on the context description.

The terminology used in the description of the various described examples in this disclosure is for the purpose of describing particular examples only and is not intended to be limiting. Unless the context clearly indicates otherwise, if the number of elements is not particularly limited, the elements may be one or more. Furthermore, the term "and/or" as used in this disclosure encompasses any and all possible combinations of the listed items.

In order to solve the above problems in the prior art, the present disclosure analyzes search information submitted by a user based on semantic analysis in a natural language processing technology, extracts a user focus, and rapidly and accurately locates target knowledge based on a hierarchical knowledge graph technology, and orders and pushes the target knowledge, thereby providing the following technical scheme for pushing information based on a hierarchical knowledge graph.

As used herein, the term "clustering algorithm" refers to unsupervised classification of entities using computation of similarity between entities; the term "TextCNN" refers to an algorithm for classifying text using a convolutional neural network.

Embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

Fig. 1 illustrates a schematic diagram of an exemplary system 100 in which various methods and apparatus described herein may be implemented in accordance with embodiments of the present disclosure. Referring to fig. 1, the system 100 includes one or

more client devices

101, 102, 103, 104, 105, and 106, a server 120, and one or more communication networks 110 coupling the one or more client devices to the server 120.

Client devices

101, 102, 103, 104, 105, and 106 may be configured to execute one or more applications.

In embodiments of the present disclosure, the server 120 may run one or more services or software applications that enable the hierarchical knowledge-graph based push information approach to be performed. It will be appreciated that this is not limiting and that in certain

embodiments client devices

101, 102, 103, 104, 105, and 106 may have sufficient storage and computing resources such that they are also capable of executing one or more services or software applications of the hierarchical knowledge-graph-based push information method.

In some embodiments, the server 120 may also provide other services or software applications that may include non-virtual environments and virtual environments. In certain embodiments, these services may be provided as web-based services or cloud services, for example, provided to users of

client devices

101, 102, 103, 104, 105, and/or 106 under a software as a service (SaaS) model.

In the configuration shown in fig. 1, server 120 may include one or more components that implement the functions performed by server 120. These components may include software components, hardware components, or a combination thereof, which may be executed by one or more processors. A user operating a

client device

101, 102, 103, 104, 105, and/or 106 may, in turn, utilize one or more client applications to interact with the server 120 to take advantage of the services provided by these components. It should be understood that a variety of different system configurations are possible, which may differ from system 100. Accordingly, fig. 1 is one example of a system for implementing the various methods described herein and is not intended to be limiting.

A user may use

client device

101, 102, 103, 104, 105, and/or 106 to submit a retrieval request containing the retrieval information. The client device may provide an interface that enables a user of the client device to interact with the client device. The client device may also output information to the user via the interface. Although fig. 1 depicts only six client devices, those skilled in the art will appreciate that any number of client devices may be supported by the present disclosure.

Client devices

101, 102, 103, 104, 105, and/or 106 may include various types of computer devices, such as portable handheld devices, general purpose computers (such as personal computers and laptop computers), workstation computers, wearable devices, gaming systems, thin clients, various messaging devices, sensors or other sensing devices, and so forth. These computer devices may run various types and versions of software applications and operating systems, such as Microsoft Windows, Apple iOS, UNIX-like operating systems, Linux, or Linux-like operating systems (e.g., Google Chrome OS); or include various Mobile operating systems, such as Microsoft Windows Mobile OS, iOS, Windows Phone, Android. Portable handheld devices may include cellular phones, smart phones, tablets, Personal Digital Assistants (PDAs), and the like. Wearable devices may include head mounted displays and other devices. The gaming system may include a variety of handheld gaming devices, internet-enabled gaming devices, and the like. The client devices are capable of executing a variety of different applications, such as various Internet-related applications, communication applications (e.g., email applications), Short Message Service (SMS) applications, and may use a variety of communication protocols.

Network 110 may be any type of network known to those skilled in the art that may support data communications using any of a variety of available protocols, including but not limited to TCP/IP, SNA, IPX, etc. By way of example only, one or more networks 110 may be a Local Area Network (LAN), an ethernet-based network, a token ring, a Wide Area Network (WAN), the internet, a virtual network, a Virtual Private Network (VPN), an intranet, an extranet, a Public Switched Telephone Network (PSTN), an infrared network, a wireless network (e.g., bluetooth, WIFI), and/or any combination of these and/or other networks.

The server 120 may include one or more general purpose computers, special purpose server computers (e.g., PC (personal computer) servers, UNIX servers, mid-end servers), blade servers, mainframe computers, server clusters, or any other suitable arrangement and/or combination. The server 120 may include one or more virtual machines running a virtual operating system, or other computing architecture involving virtualization (e.g., one or more flexible pools of logical storage that may be virtualized to maintain virtual storage for the server). In various embodiments, the server 120 may run one or more services or software applications that provide the functionality described below.

The computing units in server 120 may run one or more operating systems including any of the operating systems described above, as well as any commercially available server operating systems. The server 120 may also run any of a variety of additional server applications and/or middle tier applications, including HTTP servers, FTP servers, CGI servers, JAVA servers, database servers, and the like.

In some implementations, server 120 may include one or more applications to analyze and consolidate data feeds and/or event updates received from users of

client devices

101, 102, 103, 104, 105, and 106. Server 120 may also include one or more applications to display data feeds and/or real-time events via one or more display devices of

client devices

101, 102, 103, 104, 105, and 106.

In some embodiments, the server 120 may be a server of a distributed system, or a server incorporating a blockchain. The server 120 may also be a cloud server, or an intelligent cloud computing server or an intelligent cloud host with artificial intelligence technology. The cloud Server is a host product in a cloud computing service system, and is used for solving the defects of high management difficulty and weak service expansibility in the traditional physical host and Virtual Private Server (VPS) service.

The system 100 may also include one or more databases 130. In some embodiments, these databases may be used to store data and other information. For example, one or more of the databases 130 may be used to store information such as audio files and video files. The data store 130 may reside at various locations. For example, the data store used by the server 120 may be local to the server 120, or may be remote from the server 120 and may communicate with the server 120 via a network-based or dedicated connection. The data store 130 may be of different types. In certain embodiments, the data store used by the server 120 may be a database, such as a relational database. One or more of these databases may store, update, and retrieve data to and from the database in response to the command.

In some embodiments, one or more of the databases 130 may also be used by applications to store application data. The databases used by the application may be different types of databases, such as key-value stores, object stores, or conventional stores supported by a file system.

The system 100 of fig. 1 may be configured and operated in various ways to enable application of the various methods and apparatus described in accordance with the present disclosure.

According to an exemplary embodiment of the present disclosure, the present disclosure provides a computer-implemented hierarchical knowledge graph-based information pushing method, including: acquiring a retrieval request from user equipment, wherein the retrieval request comprises retrieval information of a user aiming at target content; extracting the point of interest of the user from the retrieval information; determining target knowledge corresponding to the attention point of the user in the layered knowledge graph according to the attention point of the user and a pre-constructed layered knowledge graph, wherein the layered knowledge graph comprises a technical field knowledge graph and a non-technical field knowledge graph, the technical field knowledge graph comprises a plurality of subdivided technical field knowledge graphs, and the non-technical field knowledge graph comprises a plurality of subdivided non-technical field knowledge graphs; and pushing the target knowledge as the target content to the user equipment.

FIG. 2 shows a flow diagram of a hierarchical knowledge-graph-based push information method 200, according to an embodiment of the present disclosure.

In step S201, the system acquires a retrieval request from a user.

According to some embodiments, a user retrieval request from a client device (e.g.,

client devices

101, 102, 103, 104, 105, or 106 in fig. 1) is received in real-time and user retrieval information is stored, for example, in database 130 in fig. 1.

According to some embodiments, obtaining the retrieval request from the user comprises: the system receives a retrieval request from the client device and acquires retrieval information input by a user.

In step S203, the point of interest of the user is extracted based on a search request including search information from the user.

According to some embodiments, the user's points of interest are extracted through a point of interest model by performing a word segmentation analysis on the user input.

According to some embodiments, for example, the text information corresponding to the user input is determined, the text information is segmented, part-of-speech tagging is performed on each segmented word, part-of-speech of each segmented word, and segmentation analysis is performed.

According to some embodiments, the points of interest of the user's search information are extracted based on the user's word segmentation through the trained point of interest model.

In step S205, based on the user interest point and the pre-constructed hierarchical knowledge graph, corresponding target knowledge is determined.

According to some embodiments, the pre-constructed hierarchical knowledge graph comprises a technical domain knowledge graph and a non-technical domain knowledge graph; the technical field knowledge graph simultaneously comprises a plurality of knowledge graphs for subdividing the technical field; the non-technical field knowledge graph simultaneously comprises a plurality of subdivided non-technical field knowledge graphs

According to some embodiments, the technical field knowledge-graph is collectively composed of a plurality of subdivided technical field knowledge-graphs. For example, the medical and aesthetic segmentation knowledge graph, the financial and technology segmentation knowledge graph, the medical field segmentation knowledge graph, the big data segmentation knowledge graph and the like.

According to some embodiments, the non-technical field knowledge-graph is collectively composed of a plurality of subdivided non-technical field knowledge-graphs. For example, party build domain subdivision knowledge graph, administrative domain subdivision knowledge graph, property domain subdivision knowledge graph, customer service domain subdivision knowledge graph, and the like.

According to some embodiments, the knowledge information is targeted based on the associated entities determined by the pre-built hierarchical knowledge graph and the knowledge information associated with the entities.

In step S207, pushing to the user equipment based on the corresponding target knowledge.

According to some embodiments, the system responds to the retrieval request of the user, sorts the target knowledge associated with the retrieval request according to a certain rule, and pushes the target knowledge to the user equipment to solve the problem of the user.

In the method for pushing information based on the hierarchical knowledge graph provided by the embodiment, the user image of the member is constructed based on the combination of the self attribute of the member and the associated knowledge document of the member, the retrieval of the future response user is realized, and the pushed information not only can contain the associated document knowledge, but also can comprise the information of the associated member; the layered knowledge graph constructed in the embodiment can accurately position the target knowledge in the knowledge graph and quickly respond to the retrieval of the user. In a large-scale mechanism, the problem is quickly positioned, retrieval of a user is responded, target information is quickly and accurately pushed, and the working efficiency of the mechanism is improved.

According to some embodiments, the hierarchical knowledge-graph provided by exemplary embodiments of the present disclosure is constructed by: acquiring historical data of a plurality of members in a group; constructing a member portrait tag for each member based on historical data of the plurality of members; hierarchically categorizing the member representation tags of the plurality of members to obtain a technology class tag and a non-technology class tag, wherein the technology class tag comprises a plurality of subdivided technology tags associated with a plurality of subdivided technology fields and the non-technology class tag comprises a plurality of subdivided non-technology tags associated with a plurality of subdivided non-technology fields; constructing the plurality of segmentation technology domain knowledge graphs and the plurality of segmentation non-technology domain knowledge graphs based on the plurality of segmentation technology tags and the plurality of segmentation non-technology tags, respectively; and respectively forming the technical field knowledge maps and the non-technical field knowledge maps by the plurality of subdivision technical field knowledge maps and the plurality of subdivision non-technical field knowledge maps so as to obtain the layered knowledge maps.

Fig. 3 shows a flowchart of a hierarchical knowledge-graph based push information method 300 according to an embodiment of the present disclosure.

In step S301, history data of a plurality of members within a community is acquired.

According to some embodiments, the member's history data contains both the community's own history data and the third party's external history data.

The owned history data contains attribute data describing attributes of each member within the community and at least one knowledge document maintained by the member. Such as the department, job level, work group, and historical behavioral data of the employee and knowledge document data associated with the employee in the enterprise internal software.

Obtaining external history data from a third party, wherein the external history data comprises usage log data of third party software of each member. For example, the history information of the third-party software of the employee can be crawled by using a crawler technology to obtain the use log data of the third-party software.

In step S303, an internal member representation is constructed based on the member history data obtained in step S301.

According to some embodiments, the known documents associated with the internal members are processed and analyzed by using a natural language processing model, and corresponding category labels are added to the corresponding documents; constructing a portrait label for the internal member based on the category label and respective attribute data of the plurality of members.

In step S305, member representation tags of the plurality of members are hierarchically classified to obtain a technology class tag comprising a plurality of subdivided technology tags associated with a plurality of subdivided technology fields and a non-technology class tag comprising a plurality of subdivided non-technology tags associated with a plurality of subdivided non-technology fields.

According to some embodiments, the internal member portrait tags obtained in step S303 are hierarchically classified into technical class tags and non-technical class tags by a clustering algorithm.

According to some embodiments, the technical class labels and the non-technical class labels are multi-classified by a deep learning algorithm to obtain a plurality of subdivided technical class labels and a plurality of subdivided non-technical class labels. For example, the subdivision technology class tags may be artificial intelligence tags, software development tags, signal encoding and decoding tags, and tags containing other specialized technologies; the subdivision non-technical class labels may be personnel labels, supply chain labels, administrative labels, and labels that contain the functional non-technical class.

In step S307, the plurality of segmentation technology field knowledge maps and the plurality of segmentation non-technology field knowledge maps are constructed based on the plurality of segmentation technology class labels and the plurality of segmentation non-technology class labels, respectively.

According to some embodiments, the association relationship between the multi-modal data is determined by analyzing the data such as text data, video, picture voice and the like through a multi-modal data model based on the plurality of segmentation technology class labels and the plurality of segmentation non-technology class labels.

According to some embodiments, the association relationship between the plurality of modal data may also be extracted by a deep learning algorithm.

According to some embodiments, a knowledge graph is constructed for each subdivision technology class label and subdivision non-technology class label separately. For example, the construction of a label knowledge graph in the technical field of subdivision is carried out on technical labels such as artificial intelligent labels, software development labels and the like; and (4) constructing a non-technical domain knowledge graph by subdividing non-technical labels such as personnel labels and supply chain labels.

In step S309, the plurality of subdivided technical field knowledge maps and the plurality of subdivided non-technical field knowledge maps are respectively composed into the technical field knowledge map and the non-technical field knowledge map, thereby obtaining the hierarchical knowledge map.

According to some embodiments, a technical-field knowledge graph and a non-technical-field knowledge graph are constructed based on the subdivided technical-field knowledge graph and the subdivided non-technical-field knowledge graph constructed in S307, respectively.

According to some embodiments, the technical domain knowledge graph and the non-technical domain knowledge graph are combined into one knowledge graph, the layered knowledge graph is obtained, and the construction of the layered knowledge graph is completed. For example, a knowledge graph comprising the technical fields of the artificial intelligence field, the software development field and the like and a knowledge graph comprising the non-technical fields of the human field, the administrative field and the like are jointly constructed into a domain knowledge graph, so that the detailed construction of the knowledge graph is realized, the association of the technical fields and the non-technical fields through the knowledge graph is realized, and the target knowledge is quickly and accurately positioned.

According to some embodiments, constructing a member representation tag for each member based on historical data of the plurality of members comprises: analyzing knowledge documents of the plurality of members using a natural language processing model; adding corresponding category labels to knowledge documents of the plurality of members based on analysis results of the natural language processing model; and constructing respective member portrait tags for the plurality of members based on the category tags and respective attribute data of the plurality of members.

Fig. 4 shows a flowchart of a hierarchical knowledge-graph based push information method 400 according to an embodiment of the present disclosure.

In step S401, the plurality of member documents are subjected to analysis processing based on a natural language processing model.

According to some embodiments, the natural language processing model includes, but is not limited to, a point of interest model, a keyword extraction model, and a chapter topic model. By evaluating the document analysis results, the most suitable model is selected for use.

In step S403, adding a corresponding category label to the knowledge document of the internal member according to the analysis result.

According to some embodiments, the class labels of the knowledge documents of the obtained internal members may be class labels of natural language processing, big data, java development, personnel archive management, supply chain procurement and the like.

In step S405, portrait tags of the plurality of members are constructed based on the category tags and the attribute data of each of the plurality of members.

According to some embodiments, the member portrait of the internal member is constructed jointly based on the obtained category labels of the knowledge document of the internal member in combination with the attribute data of the internal member. For example, the portrait label of the employee is constructed based on the basic information of the employee, the age, the department, the post and other basic data, and the historical behavior data of the employee, in combination with the label of the employee related knowledge document obtained in step S403.

According to the embodiment, the employee portrait constructed based on the self attribute of the employee and the label of the knowledge document associated with the employee more accurately reflects the information of the user compared with the employee portrait constructed based on the self attribute.

According to some embodiments, said tagging the membership representation of the plurality of members into a hierarchical classification comprises: utilizing a clustering algorithm to divide the member portrait labels of the plurality of members into technical class labels and non-technical class labels; and performing multi-classification on the technical class labels and the non-technical class labels by using a deep learning algorithm to obtain the plurality of subdivided technical labels and the plurality of subdivided non-technical labels.

Fig. 5 shows a flowchart of a hierarchical knowledge-graph based push information method 500 according to an embodiment of the present disclosure.

In step S501, the member images are classified by using the clustering algorithm.

According to some embodiments, k portrait tags are randomly selected, for example, using a basic clustering algorithm, each portrait tag initially representing the center of a cluster; assigning each of the remaining portrait labels to the nearest cluster based on its distance from the center of each cluster; recalculating the average value of each cluster, and updating the average value into a new cluster center; the first two steps are repeated until the criterion function converges. And the classification of the technical class labels and the non-technical class labels is realized through a clustering algorithm.

In step S503, the technical class labels and the non-technical class labels classified in S501 are multi-classified based on the deep learning algorithm model.

According to some embodiments, for example, a TextCNN deep learning model is adopted to perform multi-classification on the technical class labels, and the technical class labels are subdivided into specific industry fields, such as the technical industry fields of software development, machine learning and the like; and performing multi-classification on the non-technical labels, and subdividing the labels into non-technical industry fields such as personnel fields, administrative fields and the like.

According to the embodiment, the labels are classified twice through the clustering algorithm and the deep learning algorithm, so that a better classification effect is obtained. The knowledge graph constructed based on the subdivided labels can be used for responding to the retrieval of a user, and the corresponding domain, the corresponding entity and the corresponding associated target knowledge can be quickly positioned in the knowledge graph.

According to some embodiments, said extracting the user's point of interest from the retrieved information comprises: determining a text string from the retrieval information; segmenting the word string to obtain one or more words; extracting points of interest of the user from the one or more words using a point of interest model.

According to some embodiments, for example, for a search request of a user, the search information includes "how I should go to transact personal records", the system performs word segmentation on the character string, performs focused point "transacting" by using a focused point model, and performs focused point extraction on the personal records.

According to some embodiments, the determining, according to the point of interest of the user and a pre-constructed hierarchical knowledge graph, target knowledge corresponding to the point of interest of the user in the hierarchical knowledge graph includes: determining an associated entity in the hierarchical knowledge graph according to the attention point of the user; and determining target knowledge corresponding to the attention point of the user according to the type label of the knowledge related to the associated entity.

According to some embodiments, the target knowledge comprises at least one of: a knowledge document relating to the user's points of interest; and attributes of members related to the user's points of interest.

According to some embodiments, for example, an "error is reported in the front end Java code of the X project" according to the search of the software testing station employee; the system extracts an attention point 'X project' and 'Java' of the staff of the software testing post based on the retrieval information; based on the attention points of the users, the system can position the knowledge graph in the technical field in the pre-constructed knowledge graph, and further position the knowledge graph in the subdivision technical class in the software development field; a subdivision technology class knowledge graph in the field of software development determines at least one knowledge document written by X project java code and employees associated with the knowledge document.

According to the embodiment, based on the constructed hierarchical knowledge graph, the retrieval of the user is responded, and aiming at some complex problems of the retrieval, the system not only can push the document associated with the retrieval problem, but also can locate the staff associated with the problem, so that the problem solving efficiency is improved.

According to some embodiments, the pushing the target knowledge to the user equipment as the target content comprises: sequencing the target knowledge according to a sequencing rule; and pushing the sorted target knowledge to the user equipment.

The ordering rules include, but are not limited to, the following methods:

according to some embodiments, the ranking is based on the relevance between the target knowledge and the user's points of interest from high to low. For example, a scoring model is constructed, the relevance of the user focus and the target knowledge is evaluated and scored, and the user focus and the target knowledge are ranked from high to low according to the score.

According to some embodiments, the content quality based on the target knowledge is ranked from high to low. For example, a quality evaluation model is established, the determined target knowledge is extracted, and the quality evaluation model performs quality evaluation on the target knowledge and ranks the target knowledge from high to low based on the content quality.

According to some embodiments, the sorting is performed based on the order of the user's selections, allowing the user to select a sorting rule. For example, the user may select the time of target knowledge generation as the sort rule, with the content of the most recent time being presented preferentially.

Fig. 6 shows a block diagram of a hierarchical knowledge graph-based information pushing apparatus 600 according to an embodiment of the present disclosure.

According to some embodiments, the hierarchical knowledge graph-based information pushing apparatus 600 includes a retrieval obtaining module 601, a point of interest extracting module 602, an information determining module 603, and an information pushing module 604, wherein the obtaining module 601 is configured to: acquiring a retrieval request from user equipment, wherein the retrieval request comprises retrieval information of a user; the point of interest extraction module 602 is configured to: extracting the focus of the user by using a focus model based on the retrieval information of the user; the information determination module 603 is configured to: determining corresponding target knowledge based on the user attention points and a pre-constructed hierarchical knowledge graph; and the information push module 604 is configured to: based on the determined target knowledge, the system sorts according to a certain rule and then pushes the user equipment.

It should be understood that the various modules shown in fig. 6, as well as other potential modules of the apparatus 600, may correspond to various steps in the method 200 described with reference to fig. 2. Thus, the operations, features and advantages described above with respect to the method 200 are equally applicable to the apparatus 600 and the modules included therein. Certain operations, features and advantages have not been described in detail herein for purposes of brevity.

According to an embodiment of the present disclosure, there is also provided an electronic device, a readable storage medium, and a computer program product.

Referring to fig. 7, a block diagram of a structure of an electronic device 700, which may be a server or a client of the present disclosure, which is an example of a hardware device that may be applied to aspects of the present disclosure, will now be described. Electronic equipment is intended to represent various forms of digital electronic computer equipment, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 7, the apparatus 700 includes a computing unit 701, which can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM)702 or a computer program loaded from a storage unit 708 into a Random Access Memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the device 700 can also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other by a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.

Various components in the device 700 are connected to the I/O interface 705, including: an input unit 706, an output unit 707, a storage unit 708, and a communication unit 709. The input unit 706 may be any type of device capable of inputting information to the device 700, and the input unit 706 may receive input numeric or character information and generate key signal inputs related to user settings and/or function controls of the electronic device, and may include, but is not limited to, a mouse, a keyboard, a touch screen, a track pad, a track ball, a joystick, a microphone, and/or a remote controller. Output unit 707 may be any type of device capable of presenting information and may include, but is not limited to, a display, speakers, a video/audio output terminal, a vibrator, and/or a printer. Storage unit 708 may include, but is not limited to, magnetic or optical disks. The communication unit 709 allows the device 700 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunications networks, and may include, but is not limited to, modems, network cards, infrared communication devices, wireless communication transceivers and/or chipsets, such as bluetooth (TM) devices, 1302.11 devices, WiFi devices, WiMax devices, cellular communication devices, and/or the like.

Computing unit 701 may be a variety of general and/or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The computing unit 701 performs the various methods and processes described above, such as the method 200 and variations thereof. For example, in some embodiments, the method 200 and variations thereof may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 708. In some embodiments, part or all of a computer program may be loaded onto and/or installed onto device 700 via ROM 702 and/or communications unit 709. One or more steps of the method 200 and its variants described above may be performed when the computer program is loaded into the RAM 703 and executed by the computing unit 701. Alternatively, in other embodiments, the computing unit 701 may be configured to perform the method 200 and variations thereof in any other suitable manner (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.

The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be performed in parallel, sequentially or in different orders, and are not limited herein as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved.

Although embodiments or examples of the present disclosure have been described with reference to the accompanying drawings, it is to be understood that the above-described methods, systems and apparatus are merely illustrative embodiments or examples and that the scope of the invention is not to be limited by these embodiments or examples, but only by the claims as issued and their equivalents. Various elements in the embodiments or examples may be omitted or may be replaced with equivalents thereof. Further, the steps may be performed in an order different from that described in the present disclosure. Further, various elements in the embodiments or examples may be combined in various ways. It is important that as technology evolves, many of the elements described herein may be replaced with equivalent elements that appear after the present disclosure.

Claims

1. A method for pushing information, comprising:

acquiring a retrieval request from user equipment, wherein the retrieval request comprises retrieval information of a user aiming at target content;

extracting the attention point of the user from the retrieval information;

determining target knowledge corresponding to the attention point of the user in the layered knowledge graph according to the attention point of the user and a pre-constructed layered knowledge graph, wherein the layered knowledge graph comprises a technical field knowledge graph and a non-technical field knowledge graph, the technical field knowledge graph comprises a plurality of subdivided technical field knowledge graphs, and the non-technical field knowledge graph comprises a plurality of subdivided non-technical field knowledge graphs; and

and pushing the target knowledge as the target content to the user equipment.

2. The method of claim 1, wherein the hierarchical knowledge-graph is constructed by:

acquiring historical data of a plurality of members in a group;

constructing a member portrait tag for each member based on historical data of the plurality of members;

hierarchically classifying member representation tags of the plurality of members to obtain a technology class tag and a non-technology class tag, wherein the technology class tag comprises a plurality of subdivision technology tags associated with a plurality of subdivided technology domains and the non-technology class tag comprises a plurality of subdivided non-technology tags associated with a plurality of subdivided non-technology domains;

constructing the plurality of segmentation technology field knowledge graphs and the plurality of segmentation non-technology field knowledge graphs based on the plurality of segmentation technology class labels and the plurality of segmentation non-technology class labels, respectively; and

and respectively forming the technical field knowledge maps and the non-technical field knowledge maps by the plurality of subdivision technical field knowledge maps and the plurality of subdivision non-technical field knowledge maps so as to obtain the layered knowledge maps.

3. The method of claim 2, wherein said obtaining historical data for a plurality of members within a community comprises:

obtaining owned history data from the community, the owned history data including attribute data describing attributes of each member within the community and at least one knowledge document maintained by the member.

4. The method of claim 3, wherein said obtaining historical data for a plurality of members within a community further comprises:

obtaining external history data from a third party, wherein the external history data comprises usage log data of third party software of each member.

5. The method of claim 3, wherein said constructing a member representation tag for each member based on historical data of the plurality of members comprises:

analyzing knowledge documents of the plurality of members using a natural language processing model;

adding corresponding category labels to knowledge documents of the plurality of members based on analysis results of the natural language processing model; and

constructing respective member portrait tags for the plurality of members based on the category tags and respective attribute data of the plurality of members.

6. The method of claim 1, wherein the target knowledge comprises at least one of:

a knowledge document relating to the user's points of interest; and

attributes of members related to the user's points of interest.

7. The method of claim 2, wherein said hierarchically classifying member portrait tags of said plurality of members comprises:

utilizing a clustering algorithm to divide the member portrait labels of the plurality of members into technical class labels and non-technical class labels; and

and performing multi-classification on the technical class labels and the non-technical class labels by using a deep learning algorithm to obtain the plurality of subdivided technical labels and the plurality of subdivided non-technical labels.

8. The method of any one of claims 1 to 7, wherein said extracting points of interest of the user from the retrieved information comprises:

determining a text string from the retrieval information;

segmenting the word string to obtain one or more words;

extracting the user's point of interest from the one or more words using a point of interest model.

9. The method of any one of claims 1 to 7, wherein the determining target knowledge in the hierarchical knowledge graph corresponding to the user's point of interest from the user's point of interest and a pre-constructed hierarchical knowledge graph comprises:

determining an associated entity in the hierarchical knowledge graph according to the attention point of the user;

and determining target knowledge corresponding to the attention point of the user according to the type label of the knowledge related to the associated entity.

10. The method of any of claims 1-7, wherein the pushing the target knowledge to the user device as the target content comprises:

sequencing the target knowledge according to a sequencing rule; and

and pushing the sorted target knowledge to the user equipment.

11. The method of claim 10, wherein the ordering rule comprises:

sorting according to the relevance between the target knowledge and the attention points of the user from high to low;

sorting according to the content quality of the target knowledge from high to low; or

And sorting according to the sequence selected by the user.

12. An apparatus for pushing information, comprising:

a retrieval acquisition module configured to: acquiring retrieval information of a user aiming at target content;

a point of interest extraction module configured to: extracting user interest points in the retrieval information based on an interest point extraction model;

an information determination module configured to: determining target knowledge corresponding to the user attention point based on the attention point of the user and a pre-constructed knowledge graph;

an information push unit configured to: and pushing the target information to the target user.

13. A computer device, comprising:

a memory, a processor, and a computer program stored on the memory,

wherein the processor is configured to execute the computer program to implement the steps of the method of any one of claims 1-11.

14. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-11.

15. A computer program product comprising a computer program, wherein the computer program realizes the steps of the method of any one of claims 1-11 when executed by a processor.