CN111523019B

CN111523019B - Method, apparatus, device and storage medium for outputting information

Info

Publication number: CN111523019B
Application number: CN202010326136.7A
Authority: CN
Inventors: 崔雪霏; 王志华
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2020-04-23
Filing date: 2020-04-23
Publication date: 2023-05-09
Anticipated expiration: 2040-04-23
Also published as: CN111523019A

Abstract

The application discloses a method, a device, equipment and a storage medium for outputting information, and relates to the field of retrieval. The specific implementation scheme is as follows: receiving a search statement; analyzing the search sentence to determine entity words and Guan Jici contained in the search sentence; based on the entity words and the relationship words, at least one of the following searches is performed: knowledge map retrieval, table retrieval, full text retrieval, question-answer pair retrieval, and obtaining a retrieval result; and sequencing the search results, and outputting the sequenced search results. The implementation mode can utilize the method of carrying out multiple search on the search sentences and sequencing the search results. The retrieval efficiency is improved, and meanwhile, the accuracy of the retrieval result is improved, so that the retrieval experience of a user is improved.

Description

Method, apparatus, device and storage medium for outputting information

Technical Field

The present application relates to the field of computer technology, and in particular, to the field of natural language processing, and in particular, to a method and apparatus for outputting information.

Background

In the current internet, massive information is distributed in different message sources, the correlation is sparse, and it becomes more difficult to accurately and rapidly obtain valuable information by using a traditional search engine. Traditional manual indication management mode can not efficiently meet the requirement of users for obtaining the indication in real time. In addition, the questions encountered in many community questions and answers do not guarantee the accuracy of the answers, and some answers are not timeliness.

Disclosure of Invention

Provided are a method, apparatus, device, and storage medium for outputting information.

According to a first aspect, there is provided a method for outputting information, comprising: receiving a search statement; analyzing the search sentence to determine entity words and Guan Jici contained in the search sentence; based on the entity words and the relationship words, at least one of the following searches is performed: knowledge map retrieval, table retrieval, full text retrieval, question-answer pair retrieval, and obtaining a retrieval result; and sequencing the search results, and outputting the sequenced search results.

According to a second aspect, there is provided an apparatus for outputting information, comprising: a receiving unit configured to receive a search sentence; a determining unit configured to analyze the search sentence, determine an entity word and Guan Jici included therein; a search unit configured to perform at least one search of the following based on the entity word and the relationship word: knowledge map retrieval, table retrieval, full text retrieval, question-answer pair retrieval, and obtaining a retrieval result; and the output unit is configured to sort the search results and output the sorted search results.

According to a third aspect, there is provided an electronic device comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method as described in the first aspect.

According to a fourth aspect, there is provided a non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method as described in the first aspect.

According to the technology, the technical problem that the existing retrieval method needs to construct a plurality of similar problems and cannot accurately touch the retrieval result is solved, and the retrieval accuracy and efficiency are improved.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.

Drawings

The drawings are for better understanding of the present solution and do not constitute a limitation of the present application. Wherein:

FIG. 1 is an exemplary system architecture diagram in which an embodiment of the present application may be applied;

FIG. 2 is a flow chart of one embodiment of a method for outputting information according to the present application;

FIG. 3 is a schematic illustration of one application scenario of a method for outputting information according to the present application;

FIG. 4 is a flow chart of another embodiment of a method for outputting information according to the present application;

FIG. 5 is a schematic diagram of a structure for outputting information according to one embodiment of the present application;

fig. 6 is a block diagram of an electronic device for implementing a method for outputting information of an embodiment of the present application.

Detailed Description

Exemplary embodiments of the present application are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present application to facilitate understanding, and should be considered as merely exemplary. Accordingly, one 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 and spirit of the present application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

It should be noted that, in the case of no conflict, the embodiments and features in the embodiments may be combined with each other. The present application will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.

Fig. 1 illustrates an exemplary system architecture 100 to which embodiments of the methods for outputting information or the apparatus for outputting information of the present application may be applied.

As shown in fig. 1, a system architecture 100 may include

terminal devices

101, 102, 103, a network 104, and a server 105. The network 104 is used as a medium to provide communication links between the

terminal devices

101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.

The user may interact with the server 105 via the network 104 using the

terminal devices

101, 102, 103 to receive or send messages or the like. Various communication client applications, such as a web browsing type application, a search type application, a voice recognition type application, etc., may be installed on the

terminal devices

101, 102, 103.

The

terminal devices

101, 102, 103 may be hardware or software. When the

terminal devices

101, 102, 103 are hardware, they may be various electronic devices including, but not limited to, smartphones, tablet computers, electronic book readers, car-mounted computers, laptop and desktop computers, and the like. When the

terminal devices

101, 102, 103 are software, they can be installed in the above-listed electronic devices. Which may be implemented as multiple software or software modules (e.g., to provide distributed services), or as a single software or software module. The present invention is not particularly limited herein.

The server 105 may be a server providing various services, such as a background server providing search results on the

terminal devices

101, 102, 103. The background server may receive the search statement, search the search statement, obtain a search result, and feed back the search result to the

terminal devices

101, 102, 103.

The server 105 may be hardware or software. When the server 105 is hardware, it may be implemented as a distributed server cluster formed by a plurality of servers, or as a single server. When server 105 is software, it may be implemented as a plurality of software or software modules (e.g., to provide distributed services), or as a single software or software module. The present invention is not particularly limited herein.

It should be noted that the method for outputting information provided in the embodiment of the present application is generally performed by the server 105. Accordingly, the means for outputting information is typically provided in the server 105.

It should be understood that the number of terminal devices, networks and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

With continued reference to fig. 2, a flow 200 of one embodiment of a method for outputting information according to the present application is shown. The method for outputting information of the present embodiment includes the steps of:

step 201, a search statement is received.

In this embodiment, the execution subject of the method for outputting information (e.g., the server 105 shown in fig. 1) may receive the search statement through a wired connection or a wireless connection. The search sentence may be input by the user through the terminal device and then transmitted to the execution subject. The search term may include entity words and relationship words, such as "what is the television show played by AA? ". Wherein the entity words comprise "AA", "TV show", and the relation words comprise "show".

Step 202, analyzing the search sentence to determine entity words and relationship words included therein.

After receiving the search sentence, the execution body may analyze the search sentence to determine the entity word and the relationship word included in the search sentence. Specifically, the execution body may use various entity word extraction algorithms to extract entity words, or compare the search sentence with a preset entity word list to determine entity words included in the search sentence. The execution body can also segment the search sentence, and then analyze the part of speech of each segment to determine the relation word in the search sentence.

It will be appreciated that, to ensure accuracy of the extracted entity words, the executing body may obtain a proper noun list to determine proper nouns in the search statement. The proper nouns may include "Chinese bank extreme platinum credit card".

Step 203, based on the entity words and the relation words, at least one of the following searches are performed: and (5) retrieving a knowledge graph, retrieving a table, retrieving a full text, and retrieving a question-answer pair to obtain a retrieval result.

After the entity word and the search word are obtained, the execution subject can perform multiple search based on the entity word and the search word. The above-mentioned search may include knowledge map search, table search, full text search, question-answer pair search, etc., by which search results are obtained. The knowledge graph searching refers to searching the entity words and the relation words in the knowledge graph to obtain corresponding searching results. The data of the knowledge-graph can be stored in a database, and the knowledge-graph can be expressed in the form of triples of (head entity, relation, tail entity). The table search refers to searching the entity words and the relation words in the table names, the table heads and the cells of the table. Full text retrieval refers to retrieving the entity words and the relationship words in the full text of the document. The question-answer pair retrieval means that the entity words and the relation words are retrieved from the question-answer pair set. Through the above-mentioned multiple search, the execution body can obtain multiple search results.

Step 204, sorting the search results, and outputting the sorted search results.

After obtaining the search result, the execution body may sort the search result and output the sorted search result. Specifically, the execution body may rank the search results by adjusting the confidence of each search. For example, the execution body may set the confidence of the knowledge-graph search to be highest (e.g., 0.5), the confidence of the table search and question-answer pair search to be a slightly lower value (e.g., 0.2), and the full-text search to be a lowest value (e.g., 0.1).

By sorting the search results, the user can receive more accurate search results.

With continued reference to fig. 3, a schematic diagram of one application scenario of a method for outputting information according to the present application is shown. In the application scenario of fig. 3, the user inputs the search sentence "who is the lead actor of television show a" through the terminal 301. The server 302 performs the processing of the arrangements 201 to 204 on the search sentences to obtain a plurality of ordered search results. The server may transmit the above-mentioned ordered plurality of search results to the terminal 301, and display the search results on a screen of the terminal 301.

The method for outputting information provided in the above embodiment of the present application may utilize performing a plurality of searches on the search statement, and sorting the search results. The retrieval efficiency is improved, and meanwhile, the accuracy of the retrieval result is improved, so that the retrieval experience of a user is improved.

In some alternative implementations of the present embodiment, table retrieval may be achieved by the following steps, not shown in fig. 2: determining the position information of the cell corresponding to the entity word as target position information according to the entity word and the corresponding relation between the prestored entity word and the position relation; determining the cell content corresponding to the target position information as target cell content according to the target position information and the corresponding relation between the pre-stored position information and the cell content; and taking the content of the target cell as a table retrieval result.

In this implementation manner, the execution subject may first obtain a correspondence between pre-stored entity words and position relationships, and a correspondence between pre-stored position information and cell contents. The positional relationship of the cells may include a table name, a table header, a row position, and a column position. The two correspondences may be stored at other electronic devices (e.g. in a database) in the form of key-value pairs. The execution subject may determine, according to the entity word and the correspondence between the entity word and the position relationship, the position information of the cell corresponding to the entity word as the target position information. And then, according to the target position information and the corresponding relation between the position information and the cell content, determining the cell content corresponding to the target position information as target cell content. And finally, taking the content of the target cell as a table retrieval result.

For example, the user inputs "what is the platinum card main annual fee honored? ". The execution body may find the corresponding table according to the table name and the table header, and then find the corresponding cell according to the row position and the column position. Then, the corresponding relation between the position information and the cell content is inquired, and the content in the cell is determined to be 'RMB 360 yuan/card'.

The method realizes the retrieval of the cell contents in the table, and is not limited to the retrieval of the table names and the table heads, so that the retrieval can directly contact with accurate results.

With continued reference to fig. 4, a flow 400 of another embodiment of a method for outputting information according to the present application is shown. As shown in fig. 4, the method for outputting information of the present embodiment may include the steps of:

step 401, a search statement is received.

Step 402, analyzing the search sentence to determine entity words and relationship words included therein.

Step 403, based on the entity words and the relation words, at least one of the following searches is performed: and (5) retrieving a knowledge graph, retrieving a table, retrieving a full text, and retrieving a question-answer pair to obtain a retrieval result.

The principle of steps 401 to 403 is similar to that of steps 201 to 203 and will not be described here again.

In some alternative implementations of the present embodiment, when performing a multiple search using entity words and relationship words, the search may be performed by the following steps, which are not shown in fig. 4: determining synonyms of entity words and/or relationship words; and according to the determined synonyms, entity words and relationship words, performing at least one of the following search: knowledge graph search, table search, full text search and question-answer pair search.

In this implementation, the execution body may determine synonyms for each entity word and/or relationship word. And during the retrieval, the retrieval is carried out according to the determined synonyms, entity words and relationship words. Thus, the search range is enlarged, and the coverage rate of the search result is improved. In addition, if the execution subject determines that the entity word is not a proper noun, the entity word may also be segmented. And searching by using the segmentation words, the synonyms, the entity words and the relationship words.

Step 404, obtaining feedback data corresponding to each page in the search result.

In this embodiment, the search result may include a plurality of pages, where each page includes the entity word and the relationship word. Before outputting the search result, the execution body may acquire feedback data of each page. The feedback data may be the user's praise, number of praise and comment information for the pages. Specifically, the user may provide feedback data through a feedback entry of the page of the history retrieval result, and the execution body may count the feedback data. The feedback entry may include a praise button, a click button, and a comment input box.

Step 405, determining a display order of each page according to the feedback data.

In this embodiment, the execution body may analyze the feedback data, and display and sort the pages according to the analysis result. For example, the executing body may rank the most number of pages in favor first and the most number of pages in click last. Alternatively, the execution subject may perform emotion analysis on comment information included in the feedback data. If the comment information is positive emotion in the forward direction, the ranking is adjusted forward. If the comment information is a backward positive emotion, the ranking is adjusted backward. And the display ordering adjustment is carried out on each page in the search result through the feedback data, so that the accuracy of the search result is improved.

Step 406, generating a display card according to the page positioned at the first position of the display order.

In this embodiment, the execution body may generate the display card from the page located at the first position of the display order. Here, a part of the content in the page is displayed in the display card. Specifically, the display card may directly display the answer corresponding to the search sentence. Alternatively, the display card may display a paragraph that includes an answer. Through the display card, the user can quickly obtain the answer of the search statement, and the search efficiency is improved.

Step 407, outputting the display card and the rest search results.

After the execution body obtains the display card, the execution body can output the display card and the rest search results. The method for outputting information provided by the embodiment of the present application can sort the pages according to the feedback data of the pages in the search result, so that the accuracy of the output search result can be improved. Meanwhile, the answers are directly displayed in the form of the display card, so that the answer obtaining efficiency of the user is improved.

In some optional implementations of the present embodiment, the method may further include the following steps not shown in fig. 4: acquiring a plurality of recommended search sentences; and outputting the recommended search statement in response to determining that the similarity of the search statement and the recommended search statement is greater than a preset threshold.

In this implementation, the execution body may also acquire a plurality of recommended search sentences. Here, the recommended search term may be a search term input by the user a plurality of times. If the executing body judges that the similarity between the search statement and the recommended search statement is greater than a preset threshold, the recommended search statement can be output by considering that the search statement is similar to the recommended search statement. Thus, the user can search by using similar search sentences.

With further reference to fig. 5, as an implementation of the method shown in the foregoing figures, the present application provides an embodiment of an apparatus for outputting information, where the embodiment of the apparatus corresponds to the embodiment of the method shown in fig. 2, and the apparatus may be specifically applied to various electronic devices.

As shown in fig. 5, the output information apparatus 500 of the present embodiment includes: a receiving unit 501, a determining unit 502, a retrieving unit 503, and an output unit 504.

The receiving unit 501 is configured to receive a search sentence.

The determining unit 502 is configured to analyze the search sentence and determine the entity word and the relationship word included therein.

A retrieving unit 503 configured to perform at least one of the following retrieval based on the entity word and the relationship word: and (5) retrieving a knowledge graph, retrieving a table, retrieving a full text, and retrieving a question-answer pair to obtain a retrieval result.

And an output unit 504 configured to sort the search results and output the sorted search results.

In some optional implementations of the present embodiment, the retrieving unit 503 is further configured to: determining the position information of the cell corresponding to the entity word as target position information according to the entity word and the corresponding relation between the prestored entity word and the position relation; determining the cell content corresponding to the target position information as target cell content according to the target position information and the corresponding relation between the pre-stored position information and the cell content; and taking the content of the target cell as a table retrieval result.

In some optional implementations of the present embodiment, the output unit 504 is further configured to: acquiring feedback data corresponding to each page in the search result; and determining the display sequence of each page according to the feedback data.

In some optional implementations of the present embodiment, the output unit 504 is further configured to: generating a display card according to the page positioned at the first position of the display sequence; and outputting the display card and the rest search results.

In some optional implementations of the present embodiment, the apparatus 500 may further include a recommending unit, not shown in fig. 5, configured to: acquiring a plurality of recommended search sentences; and outputting the recommended search statement in response to determining that the similarity between the search statement and the recommended search statement is greater than a preset threshold.

In some optional implementations of the present embodiment, the retrieving unit 503 is further configured to: determining synonyms of entity words and/or relationship words; and according to the determined synonyms, entity words and relationship words, performing at least one of the following search: knowledge graph search, table search, full text search and question-answer pair search.

It should be understood that the units 501 to 504 described in the apparatus 500 for outputting information correspond to the respective steps in the method described with reference to fig. 2. Thus, the operations and features described above with respect to the method for outputting information are equally applicable to the apparatus 500 and the units contained therein, and are not described in detail herein.

According to embodiments of the present application, an electronic device and a readable storage medium are also provided.

As shown in fig. 6, is a block diagram of an electronic device that performs a method for outputting information according to an embodiment of the present application. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the application described and/or claimed herein.

As shown in fig. 6, the electronic device includes: one or more processors 601, memory 602, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The various components are interconnected using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions executing within the electronic device, including instructions stored in or on memory to display graphical information of the GUI on an external input/output device, such as a display device coupled to the interface. In other embodiments, multiple processors and/or multiple buses may be used, if desired, along with multiple memories and multiple memories. Also, multiple electronic devices may be connected, each providing a portion of the necessary operations (e.g., as a server array, a set of blade servers, or a multiprocessor system). One processor 601 is illustrated in fig. 6.

Memory 602 is a non-transitory computer-readable storage medium provided herein. Wherein the memory stores instructions executable by the at least one processor to cause the at least one processor to perform the methods provided herein for outputting information. The non-transitory computer readable storage medium of the present application stores computer instructions for causing a computer to perform the methods provided herein for outputting information.

The memory 602 is used as a non-transitory computer readable storage medium, and may be used to store a non-transitory software program, a non-transitory computer executable program, and modules, such as program instructions/modules (e.g., the receiving unit 501, the determining unit 502, the retrieving unit 503, and the outputting unit 504 shown in fig. 5) corresponding to the method for outputting information in the embodiments of the present application. The processor 601 executes various functional applications of the server and data processing by running non-transitory software programs, instructions, and modules stored in the memory 602, i.e., implements the method for outputting information in the above-described method embodiments.

The memory 602 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, at least one application program required for a function; the storage data area may store data created according to the use of the electronic device performing the output of information, and the like. In addition, the memory 602 may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory 602 may optionally include memory provided remotely from processor 601, such remote memory being connectable through a network to the electronic device performing the functions for outputting information. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The electronic device performing the method for outputting information may further include: an input device 603 and an output device 604. The processor 601, memory 602, input device 603 and output device 604 may be connected by a bus or otherwise, for example in fig. 6.

The input device 603 may receive input numeric or character information and generate key signal inputs related to performing user settings and function controls of the electronic device for outputting the information, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, a pointer stick, one or more mouse buttons, a track ball, a joystick, etc. input devices. The output means 604 may include a display device, auxiliary lighting means (e.g., LEDs), tactile feedback means (e.g., vibration motors), and the like. The display device may include, but is not limited to, a Liquid Crystal Display (LCD), a Light Emitting Diode (LED) display, and a plasma display. In some implementations, the display device may be a touch screen.

Various implementations of the systems and techniques described here can be realized in digital electronic circuitry, integrated circuitry, application specific ASIC (application specific integrated circuit), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

These computing programs (also referred to as programs, software applications, or code) include machine instructions for a programmable processor, and may be implemented in a high-level procedural and/or object-oriented programming language, and/or in assembly/machine language. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or device (e.g., magnetic discs, optical disks, memory, programmable Logic Devices (PLDs)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.

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 pointing device (e.g., a mouse or 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 may 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 input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background 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 background, 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 a client and a server. The client and server are typically 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.

According to the technical scheme of the embodiment of the application, the learning ability of the language model to external knowledge can be improved and the accuracy of understanding the input text can be improved by introducing the reference text in the pre-training and fine-tuning processes; by marking the input text and the reference text, the introduction of noise or dilution of the input text is avoided.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present application may be performed in parallel, sequentially, or in a different order, provided that the desired results of the technical solutions disclosed in the present application can be achieved, and are not limited herein.

The above embodiments do not limit the scope of the application. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application are intended to be included within the scope of the present application.

Claims

1. A method for outputting information, comprising:

receiving a search statement;

analyzing the search sentence to determine entity words and Guan Jici included in the search sentence;

based on the entity words and Guan Jici, carrying out knowledge graph retrieval and at least one retrieval of the following: form retrieval, full text retrieval and question-answer pair retrieval to obtain a retrieval result;

and acquiring feedback data corresponding to each page in the search result, determining the display sequence of each page according to the emotion analysis result of comment information included in the feedback data, and outputting the sequenced search result.

2. The method of claim 1, wherein the table retrieval comprises:

determining the position information of the cell corresponding to the entity word as target position information according to the entity word and the corresponding relation between the prestored entity word and the position relation;

determining the cell content corresponding to the target position information as target cell content according to the target position information and the corresponding relation between the pre-stored position information and the cell content;

and taking the target cell content as a table retrieval result.

3. The method of claim 1, wherein the outputting the search result comprises:

generating a display card according to the page positioned at the first position of the display sequence;

and outputting the display card and the rest search results.

4. The method of claim 1, wherein the method further comprises:

acquiring a plurality of recommended search sentences;

and outputting the recommended search statement in response to determining that the similarity between the search statement and the recommended search statement is greater than a preset threshold.

5. The method of claim 1, wherein the retrieving is based on the entity word and the Guan Jici, at least one of: knowledge graph retrieval, table retrieval, full text retrieval, question-answer pair retrieval, including:

determining synonyms of the entity words and/or the relationship words;

based on the determined synonyms, the entity words, and the Guan Jici, at least one of the following searches is performed: knowledge graph search, table search, full text search and question-answer pair search.

6. An apparatus for outputting information, comprising:

a receiving unit configured to receive a search sentence;

a determining unit configured to analyze the search sentence, determine an entity word and Guan Jici included therein;

a search unit configured to perform a knowledge-graph search and at least one search of: form retrieval, full text retrieval and question-answer pair retrieval to obtain a retrieval result;

the output unit is configured to acquire feedback data corresponding to each page in the search result, determine display ordering of each page according to emotion analysis results of comment information included in the feedback data, and output the ordered search result.

7. The apparatus of claim 6, wherein the retrieval unit is further configured to:

and taking the target cell content as a table retrieval result.

8. The apparatus of claim 6, wherein the output unit is further configured to:

and outputting the display card and the rest search results.

9. The apparatus of claim 6, wherein the apparatus further comprises a recommendation unit configured to:

acquiring a plurality of recommended search sentences;

10. The apparatus of claim 6, wherein the retrieval unit is further configured to:

determining synonyms of the entity words and/or the relationship words;

11. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein, the liquid crystal display device comprises a liquid crystal display device,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-5.

12. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-5.