A knowledge graph-based domain knowledge pushing method and system

Abstract

The application is suitable for the field of computers and provides a field knowledge pushing method and system based on a knowledge graph, the method comprising: acquiring first pushing information of a certain field, the first pushing information being confirmed by a first user; detecting the number of terminals in a target area; when it is detected that there are multiple terminals in the target area, identifying the demand attributes of the users of at least one terminal, the demand attributes of each terminal being different from each other, the demand attributes being determined according to the operations of the users of the terminals; and determining a target terminal for pushing the first pushing information, wherein the target terminal is determined according to the knowledge graph classification of the first pushing information and the demand attributes, and the multiple terminals include at least one target terminal, and the application has the beneficial effect of meeting the convenience of pushing the pushing information to multiple receiving targets after the pushing information is processed according to the knowledge graph classification under the regional condition and improving the pushing efficiency.

Description

TECHNICAL FIELD

[0001] The present application belongs to the field of computer, and particularly relates to a domain knowledge pushing method and system based on a knowledge graph. BACKGROUND

[0002] The way of finding knowledge is called knowledge pushing, which is also a way of knowledge service. When the domain of knowledge is strong, it is domain knowledge.

[0003] In the prior art, there are mainly the following three ways of knowledge pushing: strong association pushing: the knowledge to be pushed is fixed, which is suitable for business commonness with high accuracy and strong regularity, such as international standards; rule-based pushing: this way is suitable for most enterprises, and related pushing is carried out based on the current business rules; and business scenario-based pushing: the knowledge base intelligently pushes the knowledge matched with the current behavior of the user. In the prior art, when the pushing object of domain knowledge is multiple users in an actual area, the pushing efficiency is poor, and it is difficult to meet the personalized needs. SUMMARY

[0004] The purpose of the embodiment of the present application is to provide a domain knowledge pushing method and system based on a knowledge graph, aiming at solving the problems in the background technology.

[0005] The embodiment of the present application is implemented in this way. On the one hand, a domain knowledge pushing method based on a knowledge graph comprises the following steps:

[0006] Obtaining first pushing information of a certain domain, the first pushing information being confirmed by a first user; detecting the number of terminals in a target area;

[0007] When it is detected that there are multiple terminals in the target area, identifying the demand attributes of the users of at least one terminal, the demand attributes of each terminal being different from each other, the demand attributes being determined according to the operations of the users of the terminals;

[0008] Determining a target terminal for pushing the first pushing information, wherein the target terminal is determined according to the knowledge graph classification of the first pushing information and the demand attributes, and the multiple terminals include at least one target terminal;

[0009] Pushing the first pushing information to the determined target terminal.

[0010] As a further scheme of the present application, the method further comprises:

[0011] Obtaining pre-pushing information, and generating a to-be-processed confirmation prompt;

[0012] According to the to-be-processed confirmation prompt, a confirmation operation of the first user in a local range is acquired to realize confirmation of the pre-push information.

[0013] As a further scheme of the present application, the confirmation operation of the first user in the local range is acquired according to the to-be-processed confirmation prompt to realize confirmation of the pre-push information, and specifically includes:

[0014] When it is detected that connection signal strengths of a plurality of confirmation terminals in the local range are within a preset strength range, at least two terminals in an online operation state are identified from the plurality of confirmation terminals;

[0015] When it is detected that a distance between the at least two terminals is not greater than a transmission switching distance, the at least two terminals are marked as first terminals;

[0016] A push switching channel of the at least two first terminals under a set communication condition is established, and the set communication condition includes Bluetooth connection;

[0017] The pre-push information including the pre-push sub-information is sent to the at least two first terminals respectively, and the pre-push information carries a priority for indicating a confirmation sequence of the pre-push sub-information, and the confirmation operation of the first user is acquired according to the priority.

[0018] As a further scheme of the present application, the method further includes:

[0019] When it is detected according to the priority that there is unconfirmed pre-push sub-information in the corresponding confirmation operation, the unconfirmed pre-push sub-information is sent to at least one other first terminal and displayed based on the push switching channel until the unconfirmed pre-push sub-information is confirmed to generate first push information, and the unconfirmed pre-push sub-information includes at least one of missed confirmation pre-push sub-information and uncertain pre-push sub-information.

[0020] As a further scheme of the present application, the demand attribute of the user where the at least one terminal is located specifically includes:

[0021] Demand information of the user where the terminal is located is acquired;

[0022] The demand information is identified to generate a demand classification;

[0023] The demand classification is combined with user distinguishing information to generate the demand attribute of the user where the terminal is located, and the user distinguishing information includes device identification information of the terminal.

[0024] As a further scheme of the present application, the target terminal for pushing the first push information specifically includes:

[0025] classify the first push information according to a knowledge graph of a certain field to generate a plurality of groups of at least two entities connected by mutual relations and supplementary information associated with each entity;

[0026] associate the knowledge graph classification result with the demand attribute of the user to generate first push sub-information corresponding to a plurality of target terminals.

[0027] As a further scheme of the present application, the method further comprises:

[0028] When a supplementary viewing demand of a user of the target terminal is detected, at least one first push sub-information is matched according to the supplementary viewing demand, and the matched first push sub-information is sent to the corresponding target terminal.

[0029] On the other hand, a field knowledge push system based on a knowledge graph, the system comprises:

[0030] An acquisition module is configured to acquire first push information of a certain field, the first push information being confirmed by a first user;

[0031] A detection module is configured to detect the number of terminals in a target area;

[0032] A demand attribute identification module is configured to, when it is detected that there are a plurality of terminals in the target area, identify a demand attribute of a user of at least one terminal, the demand attribute of each terminal being different from each other, the demand attribute being determined according to the operation of the user of the terminal;

[0033] A target terminal determination module is configured to determine a target terminal for push of the first push information, wherein the target terminal is determined according to the knowledge graph classification of the first push information and the demand attribute, and the plurality of terminals include at least one target terminal;

[0034] A push execution module is configured to push the first push information to the determined target terminal.

[0035] The embodiment of the present application provides a field knowledge pushing method and system based on a knowledge graph, first pushing information confirmed by a first user in a field is acquired, when it is detected that a plurality of terminals exist in a target area, a demand attribute of a user where at least one terminal is located is recognized, the demand attribute corresponding to each terminal is different from each other, the demand attribute is determined according to the operation of the user where the terminal is located, a target terminal used for pushing the first pushing information is determined, wherein the target terminal is determined according to the knowledge graph classification of the first pushing information and the demand attribute, and the target terminal is determined according to the knowledge graph classification of the first pushing information and the demand attribute, and the plurality of terminals include at least one target terminal, the first pushing information is pushed based on the determined target terminal, the first pushing information is pushed in a supervision scene, the pushing information is pushed after being classified according to an entity relationship under the individualized demand, the convenience of pushing the pushing information to a plurality of receiving targets after the pushing information is processed according to the knowledge graph classification under the regional condition is met, and the pushing efficiency is improved. BRIEF DESCRIPTION OF DRAWINGS

[0036] Figure 1 It is a main flowchart of a field knowledge pushing method based on a knowledge graph.

[0037] Figure 2 It is a flowchart for confirming pre-pushing information in a field knowledge pushing method based on a knowledge graph.

[0038] Figure 3 It is a flowchart for acquiring a confirmation operation of a first user according to the priority in a field knowledge pushing method based on a knowledge graph.

[0039] Figure 4 It is a flowchart for making unconfirmed pre-pushing sub-information be confirmed in a field knowledge pushing method based on a knowledge graph.

[0040] Figure 5 It is a flowchart for making unconfirmed pre-pushing sub-information be confirmed in a field knowledge pushing method based on a knowledge graph.

[0041] Figure 6 It is a main structure diagram of a field knowledge pushing system based on a knowledge graph. EMBODIMENT

[0042] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application is further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, and are not used to limit the present application.

[0043] The specific implementation of the present application is described in detail below with reference to specific embodiments.

[0044] The application provides a field knowledge pushing method and system based on a knowledge graph, and solves the technical problems in the background art.

[0045] As shown in FIG. 1, a main flowchart of a field knowledge pushing method based on a knowledge graph is provided by an embodiment of the application, and the field knowledge pushing method based on the knowledge graph comprises the following steps. Figure 1

[0046] Step S10: acquiring first pushing information of a certain field, wherein the first pushing information is confirmed by a first user; considering the selective presentation of field knowledge to terminal users, the first pushing information is confirmed by the first user, and the first user can be a supervisory user for supervising and confirming the first pushing information in advance.

[0047] Step S11: detecting the number of terminals in a target area.

[0048] Step S12: when it is detected that there are multiple terminals in the target area, identifying the demand attributes of users of at least one terminal, wherein the demand attributes of each terminal are different from each other, and the demand attributes are determined according to the operations of the users of the terminals; when there are multiple terminals in the target area, the demand attributes confirmed by the operations of the users are different from each other, which indicates that the demands of each user for field knowledge are different, and the differences can be displayed in combination with different pushing modes.

[0049] Step S13: determining a target terminal for pushing the first pushing information, wherein the target terminal is determined according to the knowledge graph classification of the first pushing information and the demand attributes, and the multiple terminals include at least one target terminal; the knowledge graph is mainly used for the corresponding relationship between entities, and the basic form of the knowledge graph is a triple of <entity, relationship, entity>, the entities are connected to each other through the relationship, and a complex network knowledge structure is formed; the first pushing information is pushed in the form of combination of the knowledge graph classification and the demand attributes, which meets the individual demands of different users and determines at least one target terminal.

[0050] Step S14: pushing the first pushing information to the determined target terminal. The scenario of multiple users in an actual area can be met, for example, business introduction (such as bank business expansion introduction, e-commerce new product promotion system, insurance business introduction, and new type of workshop ventilation safety system promotion) of a to-be-promoted enterprise in front of a conference system, and the business introduction is based on different participating enterprises; for another example, the application is applied to an academic research system, and the scenario of field knowledge promotion is not limited herein.

[0051] ​In this embodiment, when applied, by acquiring first push information confirmed by a first user within a certain domain, and when multiple terminals are detected within the target area, the demand attributes of at least one terminal user are identified. The demand attributes corresponding to each terminal are different, and the demand attributes are determined based on the operations of the terminal user. The target terminal for pushing the first push information is determined, wherein the target terminal is determined comprehensively based on the knowledge graph classification of the first push information and the demand attributes, and the multiple terminals include at least one target terminal. The first push information is pushed based on the determined target terminal. In the regulatory scenario, the first push information is pushed, which satisfies both the need for personalized push information to be pushed after being classified according to entity relationships, and the need for convenient push information to be pushed to multiple receiving targets after being classified according to knowledge graph under regional conditions, thereby improving push efficiency.

[0052] like Figure 2 As shown, in a preferred embodiment of the present invention, before obtaining the first push information in a certain field, the method further includes:

[0053] Step S20: Obtain pre-push information and generate a confirmation prompt to be processed;

[0054] Step S21: Based on the pending confirmation prompt, obtain the confirmation operation of the first user within the local area to confirm the pre-push information.

[0055] Understandably, obtaining confirmation from the first user within the local area based on the pending confirmation prompt can improve the autonomy of confirmation. Confirmation of pre-push information can involve manual judgment of the pre-push information to filter out the first push information that meets the requirements.

[0056] like Figure 3 As shown, in a preferred embodiment of the present invention, the step of obtaining the confirmation operation of the first user within the local area based on the pending confirmation prompt to realize the confirmation of the pre-push information specifically includes:

[0057] Step S211: When the connection signal strength of multiple confirmed terminals within the local area is detected to be within a preset strength range, identify at least two terminals that are in online operation among the multiple confirmed terminals;

[0058] Step S212: When it is detected that the distance between at least two terminals is not greater than the transmission switching distance, mark the corresponding at least two terminals as the first terminal;

[0059] Step S213: Establish push switching channels for at least two first terminals under set communication conditions, wherein the set communication conditions include Bluetooth connection; the set communication conditions may also be short-range communication such as Zigbee or Wifi;

[0060] Step S214: sending the pre-push information including the pre-push sub-information to the at least two first terminals respectively, the pre-push information carrying a priority for indicating a confirmation sequence of the pre-push sub-information, and obtaining a confirmation operation of the first user according to the priority.

[0061] It can be understood that the confirmation terminal in the local range can not only meet the requirement of the at least two terminals in the online operation state receiving the pre-push information, but also enable the pre-push information to be smoothly delivered, and the pre-push information can be delivered in the form of pre-push sub-information, preferably synchronously, so as to meet the requirement of rapidly confirming the pre-push information. The pre-push information carries a priority for indicating a confirmation sequence of the pre-push sub-information. For example, when the at least two first terminals contain a plurality of pre-push sub-information, in order to avoid repeated confirmation of the first terminal user, the priority can avoid the occurrence of such a situation, for example, one is in sequence and the other is in reverse sequence, and the actual number of pre-push sub-information of the two can be not more than twice the total number of pre-push sub-information. After confirmation, the pre-push sub-information can be returned according to the channel, or directly pushed to the target terminal according to the requirement.

[0062] As a preferred embodiment of the present application, the method further comprises:

[0063] Step S20: when it is detected according to the priority that there is unconfirmed pre-push sub-information in the corresponding confirmation operation, sending the unconfirmed pre-push sub-information to at least another first terminal and displaying the unconfirmed pre-push sub-information based on the push switching channel until the unconfirmed pre-push sub-information is confirmed, to generate the first push information, wherein the unconfirmed pre-push sub-information includes at least one of the missed confirmation pre-push sub-information and the uncertain pre-push sub-information. This embodiment can improve the range of the first push information to meet the more extensive demand of the users for the domain knowledge.

[0064] It should be understood that, as can be seen in combination with the foregoing embodiments, the present embodiment can send the unconfirmed pre-push information (on one first terminal) to at least another first terminal and display the unconfirmed pre-push information. In actual application, it can be detected whether the pre-push sub-information is operated to jump to determine whether it is unconfirmed pre-push sub-information. If yes, it indicates that it is unconfirmed pre-push sub-information. At this time, the conversion confirmation can be performed based on the pre-push switching channel. Since the communication condition is set as Bluetooth connection in the push switching channel, the pre-push sub-information can be quickly transmitted in a short distance, and the network transmission channel of the first terminal does not need to be occupied.

[0065] As shown in FIG. 1, as a preferred embodiment of the present application, the identification of the demand attribute of the user of the at least one terminal specifically comprises: Figure 4 It should be understood that, as can be seen in combination with the foregoing embodiments, the present embodiment can send the unconfirmed pre-push information (on one first terminal) to at least another first terminal and display the unconfirmed pre-push information. In actual application, it can be detected whether the pre-push sub-information is operated to jump to determine whether it is unconfirmed pre-push sub-information. If yes, it indicates that it is unconfirmed pre-push sub-information. At this time, the conversion confirmation can be performed based on the pre-push switching channel. Since the communication condition is set as Bluetooth connection in the push switching channel, the pre-push sub-information can be quickly transmitted in a short distance, and the network transmission channel of the first terminal does not need to be occupied.

[0066] Step S121: obtaining demand information of a user to which the terminal belongs;

[0067] Step S122: identifying the demand information to generate a demand classification;

[0068] Step S123: combining the demand classification with user distinguishing information to generate a demand attribute of the user to which the terminal belongs, the user distinguishing information including device identification information of the terminal.

[0069] In application of the embodiment, the classification of the demand is generally corresponding to the knowledge graph classification of the first push information, and each demand classification can correspond to at least one knowledge graph classification of the first push information, so that the demand information can be combined with the user distinguishing information to generate the mutually distinguished user demand attribute; it should be noted that the identification information of the device can be used as the user distinguishing information of the user in the embodiment, that is, the terminals bound by each user are different from each other.

[0070] As shown in Figure 5 As a preferred embodiment of the application, the determination of the target terminal for the first push information specifically includes:

[0071] Step S131: classifying the first push information according to the knowledge graph of a certain field to generate a plurality of groups of at least two entities connected by mutual relationship and supplementary information associated with each entity;

[0072] Step S132: associating the knowledge graph classification result with the demand attribute of the user to generate first push sub-information corresponding to a plurality of target terminals.

[0073] It can be understood that the embodiment provides a method for determining a push object of first push information. According to the embodiment, the first push sub-information corresponding to the multiple target terminals can be obtained according to the demand attributes of the user. Since the demand attributes corresponding to each terminal are different from each other, the first push sub-information after association is also different from each other. When the first push sub-information is pushed and published, confusion will not occur, so that each target terminal can correspond to at least one first push sub-information clearly. In addition, it needs to be pointed out that when classification is performed according to the knowledge graph, the supplementary information is information that cannot form mutual corresponding information or information with weak corresponding relationship between at least two entities. The supplementary information can be used as an attached entity supplement. For example, at least two entities in the safety operation specification of the operating device in the workshop are a ventilation device and a warning device. When the ventilation device fails, the warning device will give an early warning of gradually decreasing ventilation efficiency. The warning device can be associated with sound control alarm and color alarm through the action mode. The ventilation device can be associated with a fan and a power device of the fan through a hierarchical relationship. At this time, the supplementary information can be a dust removal device in the workshop, because dust affects the efficiency of ventilation (often due to dust blockage in the ventilation duct or dust accumulation on the casing of the ventilation device, so that the temperature rise of the ventilation motor is more than 10 DEG C higher than usual, causing the operating temperature of the ventilation motor to be too high and the carrying capacity to be reduced).

[0074] Step S30: as a preferred embodiment of the application, the method further comprises:

[0075] When the supplementary viewing demand of the user where the target terminal is located is detected, at least one first push sub-information is matched according to the supplementary viewing demand, and the matched first push sub-information is sent to the corresponding target terminal.

[0076] It can be understood that through the implementation of the embodiment, the certain degree of deficiency caused by the classification of the knowledge graph can be supplemented, so that all the domain knowledge does not have to be pushed at one time, but is pushed in combination with the knowledge graph classification of the user and the demand attribute. The embodiment can also meet the additional viewing demand. The additional viewing demand can also be supplemented based on the update of the first push information. For example, the operation doubt after the operation system of the device is updated is additionally supplemented to meet the demand of the user for correct operation.

[0077] As shown in Figure 6 As another preferred embodiment of the application, on the other hand, a domain knowledge push system based on a knowledge graph, the system comprises:

[0078] The acquisition module 100 is configured to: acquire first push information of a certain domain, the first push information being confirmed by a first user; and detect the number of terminals in a target area.

[0079] The detection module 200 is configured to detect the number of terminals in the target area.

[0080] The demand attribute identification module 300 is configured to identify the demand attribute of the user of at least one terminal when it is detected that there are multiple terminals in the target area, wherein the demand attribute of each terminal is different from each other, and the demand attribute is determined according to the operation of the user of the terminal.

[0081] The target terminal determination module 400 is configured to determine the target terminal for the first push information push, wherein the target terminal is determined according to the knowledge graph classification of the first push information and the demand attribute, and the multiple terminals include at least one target terminal.

[0082] The push execution module 500 is configured to push the first push information to the determined target terminal.

[0083] The above embodiments of the present application provide a knowledge graph-based domain knowledge push method, and a knowledge graph-based domain knowledge push system based on the knowledge graph-based domain knowledge push method. By acquiring first push information in a certain field confirmed by a first user, when it is detected that there are multiple terminals in the target area, the demand attribute of the user of at least one terminal is identified, wherein the demand attribute of each terminal is different from each other, and the demand attribute is determined according to the operation of the user of the terminal. The target terminal for the first push information push is determined, wherein the target terminal is determined according to the knowledge graph classification of the first push information and the demand attribute, and the multiple terminals include at least one target terminal. The first push information is pushed based on the determined target terminal. In the regulatory scenario, the first push information is pushed. The push information is pushed according to the entity relationship classification under the individualized demand, and the convenience of pushing the push information to multiple receiving targets according to the knowledge graph classification under the regional condition is met. The push efficiency is improved.

[0084] In order to enable the above method and system to run smoothly, the system can include more or less components than described above, or combine some components, or different components, for example, it can include input and output devices, network access devices, buses, processors and memories, etc.

[0085] The processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The above-mentioned processor is the control center of the system, and is connected with various parts through various interfaces and lines.

[0086] The memory can be used to store computer programs and / or modules of the system and / or the computer, and the processor can realize various functions by running or executing the computer programs and / or modules stored in the memory and calling data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application program required by a function (such as an information collection template display function, a product information publishing function, etc.), etc. The data storage area can store data created according to the use of the berth state display system (such as product information collection templates corresponding to different product categories, product information to be published by different product providers, etc.). In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, for example, a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state memory devices.

[0087] It should be understood that, although each step in the flowchart of each embodiment of the present application is displayed in sequence according to the direction of the arrow, these steps are not necessarily executed in sequence according to the direction of the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other sequences. Moreover, at least part of the steps in each embodiment can include multiple sub-steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence of these sub-steps or stages is not necessarily sequential, but can be executed in rotation or alternation with at least part of other steps or sub-steps or stages of other steps.

[0088] Any technical features in the above-described embodiments can be combined in any manner, and for the sake of brevity, not all possible combinations are described, but it is understood that the scope of the present specification includes all possible combinations.

[0089] The above-described embodiments only express several implementation manners of the present application, and the description is relatively specific and detailed, but should not be understood as a limitation on the patent scope of the present application. It should be noted that, for those skilled in the art, some modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application patent should be subject to the appended claims.

[0090] The above-described embodiments only express several implementation manners of the present application, and the description is relatively specific and detailed, but should not be understood as a limitation on the patent scope of the present application. It should be noted that, for those skilled in the art, some modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application patent should be subject to the appended claims. The above-described embodiments only express several implementation manners of the present application, and the description is relatively specific and detailed, but should not be understood as a limitation on the patent scope of the present application. It should be noted that, for those skilled in the art, some modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application patent should be subject to the appended claims.

Claims

1. A knowledge graph-based domain knowledge pushing method, characterized in that, The method comprises: obtaining first push information in a certain field, the first push information being confirmed by a first user; detecting the number of terminals in a target area; when detecting that there are multiple terminals in the target area, identifying the demand attributes of the users of at least one terminal, the demand attributes of each terminal being different from each other, the demand attributes being determined according to the operations of the users of the terminals; determining a target terminal for pushing the first push information, wherein the target terminal is determined according to the knowledge graph classification of the first push information and the demand attributes, and the multiple terminals include at least one target terminal; pushing the first push information to the determined target terminal; before obtaining the first push information in a certain field, the method further comprises: obtaining pre-push information and generating a to-be-processed confirmation prompt; obtaining the confirmation operations of the first user in a local area according to the to-be-processed confirmation prompt to realize the confirmation of the pre-push information; the step of obtaining the confirmation operations of the first user in a local area according to the to-be-processed confirmation prompt to realize the confirmation of the pre-push information specifically comprises: when detecting that the connection signal strengths of multiple confirmation terminals in a local area are within a preset strength range, identifying at least two terminals in an online operation state from the multiple confirmation terminals; when detecting that the distance between the at least two terminals is not greater than a transmission switching distance, marking the corresponding at least two terminals as first terminals; establishing a push switching channel of the at least two first terminals under a set communication condition, the set communication condition including Bluetooth connection; sending the pre-push information including pre-push sub-information to the at least two first terminals respectively, the pre-push information carrying a priority for indicating the confirmation order of the pre-push sub-information, and obtaining the confirmation operations of the first user according to the priority; when detecting that there is unconfirmed pre-push sub-information in the corresponding confirmation operations according to the priority, sending the unconfirmed pre-push sub-information to at least one other first terminal and displaying the unconfirmed pre-push sub-information based on the push switching channel until the unconfirmed pre-push sub-information is confirmed to generate the first push information, wherein the unconfirmed pre-push sub-information includes at least one of missed confirmation pre-push sub-information and uncertain pre-push sub-information; the step of determining a target terminal for pushing the first push information specifically comprises: classifying the first push information according to a knowledge graph in a certain field to generate a plurality of groups of at least two entities connected by mutual relationships and supplementary information associated with each entity; associating the knowledge graph classification result with the demand attributes of the users to generate first push sub-information corresponding to multiple target terminals. 2.The knowledge graph-based domain knowledge pushing method according to claim 1, characterized in that, the step of identifying the demand attributes of the users of at least one terminal specifically comprises: obtaining demand information of the users of the terminals; identifying the demand information to generate a demand classification; combining the demand classification with user distinguishing information to generate the demand attributes of the users of the terminals, the user distinguishing information including device identification information of the terminals. 3.The knowledge graph-based domain knowledge pushing method according to claim 1, characterized in that, the method further comprises: When a supplementary viewing requirement of a user where the target terminal is located is detected, at least one first push sub-information is matched according to the supplementary viewing requirement, and the matched first push sub-information is sent to the corresponding target terminal.

4. A pushing system for the knowledge graph-based domain knowledge pushing method of claims 1-3, characterized in that, The system comprises: An acquisition module is configured to acquire first push information in a certain field, wherein the first push information is confirmed by a first user; and detect the number of terminals in a target area; A requirement attribute identification module is configured to identify a requirement attribute of a user where at least one terminal is located when it is detected that there are multiple terminals in the target area, wherein the requirement attribute of each terminal is different from each other, and the requirement attribute is determined according to the operation of the user where the terminal is located; A target terminal determination module is configured to determine a target terminal for the first push information push, wherein the target terminal is determined according to the knowledge graph classification of the first push information and the requirement attribute, and the multiple terminals include at least one target terminal; A push execution module is configured to push the first push information to the determined target terminal.

Images