Information acquisition method, device, equipment, system and readable storage medium

Abstract

The present invention discloses an information acquisition method, device, equipment and readable storage medium. The method comprises: according to a target query statement input by a user, obtaining a set of recommended query statements corresponding to the target query statement; obtaining the target query statement and the trigger content of each recommended query statement included in the recommended query statement set respectively through a preset content triggering method; according to the target query statement and the trigger content of each recommended query statement, determining the direct content corresponding to the target query statement, so as to provide the user with the information he / she expects to obtain by associating the direct content with the target query statement and displaying it.

Description

Technical Field

[0001] The present invention relates to the field of information technology, and more specifically, to an information acquisition method, device, equipment, system and readable storage medium. Background Art

[0002] With the rapid development of Internet technology, searching for information through accessing the Internet has become a common means of obtaining information.

[0003] People can usually enter an information query statement (Query) that reflects their own information acquisition needs in an application that provides information search services (such as a browser application), triggering the application to search the information database accessible on the Internet based on the information query statement, obtain the corresponding search results and display them, in the hope of obtaining information that meets their needs.

[0004] However, currently users usually need to trigger an information search process based on an information query statement after entering the information query statement, and wait for the returned search results. They also need to browse and select from the returned search results before they can finally determine the information that truly meets their own information acquisition needs. This is time-consuming, resulting in a high cost of information acquisition, and affecting the information acquisition experience. Summary of the invention

[0005] An object of the present invention is to provide a new technical solution for acquiring information.

[0006] According to a first aspect of the present invention, there is provided an information acquisition method, comprising:

[0007] According to the target query statement input by the user, a set of recommended query statements corresponding to the target query statement is obtained;

[0008] By means of a preset content triggering method, the triggering content of each recommended query statement included in the target query statement and the recommended query statement set is respectively obtained; the triggering content is content pre-associated with the corresponding target query statement or the recommended query statement;

[0009] According to the target query statement and the triggering content of each of the recommended query statements, the direct content corresponding to the target query statement is determined, so as to provide the user with the information he or she expects to obtain by associating the direct content with the target query statement and displaying the direct content with the target query statement.

[0010] According to a second aspect of the present invention, there is provided an information acquisition method, comprising:

[0011] Receiving an input operation from a user, and determining a target query statement corresponding to the input operation;

[0012] According to the target query statement, triggering acquisition of direct content corresponding to the target query statement; the direct content is acquired according to any one of the information acquisition methods provided in the second aspect of the present invention;

[0013] The direct content is associated with the target query statement and displayed, so as to provide the user with the information he or she expects to obtain.

[0014] According to a third aspect of the present invention, there is provided an information acquisition device, comprising:

[0015] A recommendation acquisition unit, configured to acquire a set of recommended query statements corresponding to a target query statement input by a user;

[0016] A content triggering unit, configured to obtain triggering content of each recommended query statement included in the target query statement and the recommended query statement set respectively through a preset content triggering method; the triggering content is content pre-associated with the corresponding target query statement or the recommended query statement;

[0017] A direct acquisition unit is used to determine the direct content corresponding to the target query statement based on the target query statement and the trigger content of each recommended query statement, so as to provide the user with the information he or she expects to obtain by associating the direct content with the target query statement and displaying it.

[0018] According to a fourth aspect of the present invention, there is provided an information acquisition device, comprising:

[0019] A query determination unit, configured to receive an input operation from a user and determine a target query statement corresponding to the input operation;

[0020] a direct access acquisition unit, configured to trigger, according to the target query statement, acquisition of direct access content corresponding to the target query statement; the direct access content is acquired according to the information acquisition method as described in any one of the first aspects of the present invention;

[0021] The associated display unit is used to associate and display the direct content with the target query sentence to provide the user with the information he or she expects to obtain.

[0022] According to a fifth aspect of the present invention, there is provided an information acquisition device, comprising:

[0023] A memory for storing executable instructions;

[0024] The processor is used to run the information acquisition device to execute any one of the information acquisition methods described in the first aspect of the present invention according to the executable instructions.

[0025] According to a sixth aspect of the present invention, there is provided an information acquisition device, comprising:

[0026] Display device;

[0027] A memory for storing executable instructions;

[0028] The processor is used to run the information acquisition device to execute any one of the information acquisition methods described in the second aspect of the present invention according to the executable instructions.

[0029] According to the seventh aspect of the present invention, a readable storage medium is provided, wherein the readable storage medium stores a computer program that can be read and executed by a computer, and when the computer program is read by the computer, it executes any one of the information acquisition methods described in the first aspect of the present invention or the information acquisition method described in the second aspect of the present invention.

[0030] According to an eighth aspect of the present invention, there is provided an information acquisition system, comprising:

[0031] The information acquisition device according to the third aspect of the present invention and the information acquisition device according to the fourth aspect of the present invention;

[0032] or,

[0033] The information acquisition device as described in the fifth aspect of the present invention and the information acquisition device as described in the sixth aspect of the present invention.

[0034] According to an embodiment of the present disclosure, a preset content triggering method can be used to obtain trigger contents that are pre-associated with a target query statement input by a user and each recommended query statement corresponding to the target query statement, respectively. Then, based on the trigger contents of the target query statement and each recommended query statement, direct content that corresponds to the target query statement and can accurately meet the user's information query needs is determined, and the direct content is displayed in association with the target query statement. This allows users to instantly obtain information that accurately meets their own information query needs without having to wait for the information search process or make information browsing selections after entering the target query statement, thereby greatly shortening the time it takes for users to obtain information and reducing the user's information acquisition costs.

[0035] Further features and advantages of the present invention will become apparent from the following detailed description of exemplary embodiments of the present invention with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate embodiments of the invention and, together with the description, serve to explain the principles of the invention.

[0037] Figure 1 is a block diagram showing an example of a hardware configuration of an information system 1000 that can be used to implement an embodiment of the present invention.

[0038] Figure 2 A flow chart showing an information acquisition method according to a first embodiment of the present invention.

[0039] Figure 3 A block diagram of an information acquisition device 3000 according to a first embodiment of the present invention is shown.

[0040] Figure 4 A block diagram showing an information acquisition device 4000 according to the first embodiment of the present invention.

[0041] Figure 5 A flow chart showing an information acquisition method according to a second embodiment of the present invention is shown.

[0042] Figure 6 A schematic diagram showing an example of displaying the direct content associated with the target query sentence according to the second embodiment of the present invention.

[0043] Figure 7 A block diagram of an information acquisition device 5000 according to a second embodiment of the present invention is shown.

[0044] Figure 8 A block diagram showing an information acquisition device 6000 according to a second embodiment of the present invention.

[0045] Fig. 9 A flowchart showing an example of an information acquisition method implemented by the information acquisition system 7000 according to the third embodiment of the present invention.

[0046] Fig.10 Schematic diagram showing an example of displaying the direct content associated with the target query sentence according to the third embodiment of the present invention Figure 1 .

[0047] Fig.11 Schematic diagram showing an example of displaying the direct content associated with the target query sentence according to the third embodiment of the present invention Figure 2 .

[0048] Fig.12 Schematic diagram showing an example of displaying the direct content associated with the target query sentence according to the third embodiment of the present invention Figure 3 .

[0049] Fig.13 Schematic diagram showing an example of displaying the direct content associated with the target query sentence according to the third embodiment of the present invention Figure 4 . DETAILED DESCRIPTION

[0050] Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that the relative arrangement of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present invention unless otherwise specifically stated.

[0051] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses.

[0052] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered as part of the specification.

[0053] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not limiting. Therefore, other examples of the exemplary embodiments may have different values.

[0054] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0055] <Hardware Configuration>

[0056] Figure 1 1 is a block diagram showing a hardware configuration of an information system 1000 that can implement an embodiment of the present invention.

[0057] like Figure 1 As shown, the information system 1000 includes a server 1100 , a client 1200 , and a network 1300 .

[0058] The server 1100 may be, for example, a blade server, a cloud server, or a server group consisting of multiple servers. Figure 1 As shown, the server includes a processor 1110, a memory 1120, an interface device 1130, a communication device 1140, a display device 1150, and an input device 1160. Although the server may also include a speaker, a microphone, etc., these components are irrelevant to the present invention and are omitted here. Among them, the processor 1110 may be, for example, a central processing unit CPU, a microprocessor MCU, etc. The memory 1120 may include, for example, a ROM (read-only memory), a RAM (random access memory), a non-volatile memory such as a hard disk, etc. The interface device 1130 may include, for example, a USB interface, a serial interface, etc. The communication device 1140 may be capable of wired or wireless communication, for example. The display device 1150 may be, for example, a liquid crystal display. The input device 1160 may include, for example, a touch screen, a keyboard, etc.

[0059] The client 1200 may be a portable computer (1200-1), a desktop computer (1200-2), a mobile phone (1200-3), a tablet computer (1200-4), etc. Figure 1 As shown, the client 1200 may include a processor 1210, a memory 1220, an interface device 1230, a communication device 1240, a display device 1250, an input device 1260, a speaker 1270, a microphone 1280, and the like. The processor 1210 may be a central processing unit CPU, a microprocessor MCU, and the like. The memory 1220 may include, for example, a ROM (read-only memory), a RAM (random access memory), a non-volatile memory such as a hard disk, and the like. The interface device 1230 may include, for example, a USB interface, an earphone interface, and the like. The communication device 1240 may, for example, be capable of wired or wireless communication. The display device 1250 may be, for example, a liquid crystal display screen, a touch display screen, and the like. The input device 1260 may include, for example, a touch screen, a keyboard, and the like. The user may input / output voice information through the speaker 1270 and the microphone 1280.

[0060] The communication network 1300 may be a wireless network or a network, and may be a local area network or a wide area network. Figure 1 In the information system 1000 shown, clients 1200 - 1 , 1200 - 2 , 1200 - 3 , 1200 - 4 and server 1100 can communicate via a communication network 1300 .

[0061] Figure 1 The information system 1000 shown is merely illustrative and is in no way intended to limit the present invention, its application or use. In the embodiments of the present invention, the memory 1120 of the server 1100 is used to store instructions, which are used to control the processor 1110 to operate to perform any one of the information acquisition methods provided in the embodiments of the present invention. In addition, the memory 1220 of the client 1200 is used to store instructions, which are used to control the processor 1210 to operate to perform any one of the information acquisition methods provided in the embodiments of the present invention. It should be understood by those skilled in the art that although in Figure 1 In the embodiment, multiple devices are shown for both the server 1100 and the client 1200, but the present invention may only involve some of the devices, for example, the server 1100 only involves the processor 1110 and the storage device 1120, or the client 1200 only involves the processor 1210 and the storage device 1220, etc. A technician may design instructions according to the scheme disclosed in the present invention. How instructions control the processor to operate is well known in the art, so it will not be described in detail here.

[0062] The overall concept implemented by the present invention is to provide a new solution for obtaining information. Through a preset content triggering method, trigger content that is pre-associated with a target query statement input by a user and each recommended query statement corresponding to the target query statement can be obtained respectively. Then, based on the triggering content of the target query statement and each recommended query statement, direct content corresponding to the target query statement that can accurately meet the user's information query needs is determined, and the direct content is displayed in association with the target query statement. This allows users to obtain information that accurately meets their own information query needs immediately after entering the target query statement without having to wait for the information search process or make information browsing selections, thereby greatly shortening the time it takes for users to obtain information and reducing the user's information acquisition costs.

[0063] <First Embodiment>

[0064] In this embodiment, a method for obtaining information is provided. The information may include any content that can be accessed through a local area network or a wide area network, for example, the information may include web page content, pictures, audio, video, entries, encyclopedias, etc.

[0065] The information acquisition method in this embodiment can be implemented by a server, which may include a blade server, a cloud server, or a server cluster. In one example, the information acquisition method in this embodiment can be implemented by Figure 1 Server 1100 implementation is shown.

[0066] like Figure 2 As shown, the information acquisition method includes: steps S2100-S2300.

[0067] Step S2100: acquiring a set of recommended query statements corresponding to the target query statement according to the target query statement input by the user.

[0068] The recommended query statement set includes multiple recommended query statements corresponding to the target query statement. In this embodiment, the corresponding recommended query statement can be obtained by performing semantic analysis, content association and other processing on the target query statement. For example, assuming that the target query statement input by the user is "spring", after performing semantic analysis, content association and other processing on "spring", the corresponding recommended query statements "spring is coming", "spring flowers", "spring poems" and so on can be obtained. In this embodiment, according to the query times of the multiple recommended query statements obtained after processing in the recent statistical period, several recommended query statements with the query times in the recent statistical period sorted in ascending order can be selected as recommended query statements in the recommended query statement set, so as to reduce the processing amount of subsequent steps and further improve the efficiency of information acquisition.

[0069] Step S2200 , obtaining the target query statement and the triggering content of each recommended query statement included in the recommended query statement set respectively through a preset content triggering method.

[0070] The trigger content is the content that is pre-associated with the corresponding target query statement or recommended query statement.

[0071] The preset content triggering method is a method of obtaining the triggering content of the target query statement or the recommended query statement. Different from the general information search method of searching and matching the massive information in the wide area network or local area network according to the query statement to find the corresponding search results, the target query statement or the recommended query statement can be used as a trigger to quickly and directly obtain the triggering content that is pre-associated with the triggered query statement.

[0072] Through the preset content triggering method, it is possible to quickly and directly obtain content that is pre-associated with the target query statement or recommended query statement without searching and matching in the massive amount of available information, so that in combination with subsequent steps, direct content corresponding to the target query statement and that can accurately meet the user's information query needs can be determined from these triggering contents. This allows users to meet their information acquisition needs instantly after entering the target query statement without having to wait for the information search process or make information browsing selections.

[0073] In one example, the preset content triggering method includes at least one of the four methods: vertical card triggering, selected question and answer triggering, official website data triggering, and vertical skill triggering.

[0074] Vertical cards are information cards constructed by obtaining corresponding field information in different vertical sub-fields through machine crawling or manual mining. For example, for the field of "movies", vertical sub-fields can include "comedy movies", "love movies", "ethical movies", "animated movies", "European and American movies", "Chinese movies" and other fields. To obtain corresponding content in different vertical sub-fields, multiple vertical cards can be constructed. For example, "love movies" include "Roman Holiday", and the vertical card constructed for "Roman Holiday" includes entity information such as the movie name, movie introduction, and movie starring. After this vertical card is constructed, it is associated with the movie name "Roman Holiday" and the movie starring "Audrey Hepburn".

[0075] Correspondingly, the vertical card trigger is a content triggering method in which the target query statement or the recommended query statement is triggered as a query statement, and a vertical card associated with the query statement is obtained as the corresponding trigger content.

[0076] Selected Q&A can be Q&A content extracted from available knowledge graphs. The purpose of knowledge graphs is to describe the information and concepts of entities that exist in the real world, as well as the relationships between entities. Currently available knowledge graphs usually cover a large number of entity information and the associations between entities, and these entity information and the associations between entities are usually reflected in the form of Q&A content. For example, the knowledge graph will include the correct answer to "Why is the sky blue?", and the correct answer is associated with the query statement "Why is the sky blue?". These Q&A contents are extracted from the available knowledge graph as selected Q&A, and a large amount of information content associated with the questions in the Q&A content as query statements can be obtained accordingly.

[0077] Correspondingly, the selected question and answer trigger is a content triggering method that triggers the target query statement or the recommended query statement as a query statement, and obtains the answer in the selected question and answer data associated with the query statement as the corresponding trigger content.

[0078] Official website data refers to data published by the official website corresponding to an entity. The data published on the official website usually includes the entity information or entity concept of the corresponding entity and the association with other entities. For example, the most accurate and detailed data about a movie star will be published on the official website of the movie star, and the association between the movie star data and the query statements related to the name of the movie star will be established. Through machine crawling or manual mining, these official website data with established corresponding associations can be obtained from multiple accessible and authenticated official websites.

[0079] Correspondingly, the official website data trigger is a content triggering method that triggers the target query statement or the recommended query statement as a query statement, and obtains the official website data associated with the query statement as the corresponding trigger content.

[0080] Vertical skills are application skills developed for application needs in different vertical segments. For example, a courier query skill is developed for courier query needs. By calling this vertical skill, you can query the corresponding courier logistics information by entering the courier number. Similarly, there are weather queries, scenic spot queries, etc. By calling vertical skills, you can directly, quickly, and accurately obtain related content.

[0081] Correspondingly, vertical skill triggering is a content triggering method in which a target query statement or a recommended query statement is triggered as a query statement, a corresponding vertical skill is called, and content associated with the query statement is obtained as the corresponding trigger content.

[0082] After step S2200, enter:

[0083] Step S2300, based on the target query statement and the triggering content of each recommended query statement, determine the direct content corresponding to the target query statement, so as to provide the user with the information he or she expects to obtain by associating the direct content with the target query statement and displaying it.

[0084] The target query statement and the trigger content of each recommended query statement are contents that are pre-associated with the target query statement or the recommended query statement. Determining the direct content corresponding to the target query statement from these trigger contents can accurately meet the user's information query needs, thereby allowing the user to instantly meet their own information acquisition needs after entering the target query statement without having to wait for the information search process or make information browsing selections, thereby greatly reducing the cost of information acquisition.

[0085] In one example, the step of determining the direct content corresponding to the target query statement according to the target query statement and the triggering content of each recommended query statement includes: steps S2310-S2330.

[0086] Step S2310: The target query statement and each recommended query statement are respectively regarded as a query statement, and confidence judgment is performed on the query statement according to the triggering content of the query statement to determine the confident query statement that passes the confidence judgment.

[0087] The trigger content of the target query statement and each recommended query statement is the content that is pre-associated with the corresponding target query statement or recommended query statement. In some cases, although the trigger content can reflect the information query intention of the corresponding query statement to a certain extent, it cannot necessarily meet the main information query needs (actual and most important information query needs) reflected by the corresponding query statement. Therefore, in step S2310, the query statement can be judged on the basis of the trigger content of the query statement. The confident query statement that passes the confidence judgment is the query statement whose corresponding trigger content can meet the main information query needs reflected by the query statement. In combination with the subsequent steps, it is possible to obtain direct content that can more accurately meet the user's actual information query needs and improve the user's information acquisition efficiency.

[0088] In a more specific example, step S2310 of performing confidence judgment on a target query statement or a recommended query statement as a query statement may include: steps S2311-S2313.

[0089] Step S2311, determining whether the query statement is a high-frequency query statement based on the historical query times of the query statement.

[0090] The historical query count of a query statement is the number of times the query statement is used by users to query information in a preset historical statistical period. The historical query count can be obtained by analyzing and counting the logs of the application providing information query services in the historical statistical period. The historical statistical period can be set according to specific application scenarios or application requirements, and no specific numerical limit is made here.

[0091] In this example, a high-frequency query threshold may be set according to engineering experience or experimental simulation, and a query statement whose historical query times are greater than the high-frequency query threshold may be determined as a high-frequency query statement.

[0092] Whether a query statement is a high-frequency query statement can be distinguished based on the number of historical queries of the query statement. Different confidence judgment strategies can be implemented for high-frequency query statements and non-high-frequency query statements in combination with subsequent steps to achieve more accurate confidence judgments, corresponding to more accurate confidence query statements, and thus more accurate direct content that meets the user's actual information query needs.

[0093] Step S2312, when it is determined that the query statement is a high-frequency query statement, the click score of the triggering content of the query statement is obtained. When the click score meets the score confidence condition, it is determined that the query statement passes the confidence judgment and the corresponding confident query statement is obtained.

[0094] The click score of the trigger content of the query statement is a score obtained based on the user click data obtained from the corresponding trigger content.

[0095] High-frequency query statements have a high number of historical queries, and the corresponding trigger content has a high probability of being clicked by users. By performing confidence judgment on high-frequency query statements through corresponding click scores, accurate confidence judgment results can be obtained.

[0096] In a more specific example, when it is determined that the query statement is a high-frequency query statement, the step of obtaining the click score of the triggering content of the query statement includes:

[0097] S23121, obtaining user click data of the triggering content in the most recent statistical period, and fitting the user click data to obtain a click score of the triggering content according to a pre-built click score model.

[0098] The statistical period is a period used to count the user click data of the triggered content, and can be set according to the specific application scenario or application requirements. For example, the statistical period can be 1 week, 1 month, or N days.

[0099] The user click data of the trigger content in the most recent statistical period is the overall data related to user clicks on the trigger content in the most recent statistical period. The user click data includes at least the display times, click times, navigation click times, last click times, and skip click times of the corresponding trigger content. The display times of the trigger content is the total number of times the trigger content is displayed after being queried. The click times of the trigger content is the total number of times the user clicks on the trigger content after being queried and displayed. The navigation click times of the trigger content is the total number of times the user only clicks on the trigger content and no longer clicks on other trigger contents. The last click times of the trigger content is the total number of times the user clicks on the trigger content again after clicking on other trigger contents after the trigger content is queried and displayed. The skip click times of the trigger content is the total number of times the user skips over the trigger content and clicks on its trigger content after the trigger content is queried and displayed.

[0100] The click scoring model can adopt SVM (Support Vector Machine) related training methods, such as support vector regression, support vector clustering and other training methods, to obtain a machine learning model through training with a large number of collected samples. The model is used to use the input user click data including the number of impressions, click order, navigation clicks, last clicks, skip clicks, etc. as the feature values ​​of the model input, perform linear fitting, and output the corresponding click score.

[0101] By fitting the user click data with a click scoring model to obtain the click score of the corresponding trigger content, the user's information acquisition needs reflected by the trigger content can be accurately reflected.

[0102] The score confidence condition is a condition used to determine whether the trigger content meets the main information query requirement embodied by the corresponding query statement based on the click score.

[0103] In this example, the scoring confidence condition is that the click score is higher than the click threshold and the difference between the click score and the highest click score in history is less than the click difference. The click threshold and click difference can be set according to engineering experience or experimental simulation for specific confidence judgment scenarios. The highest click score in history is the highest click score that can be obtained in the historical scoring period. The historical scoring period can be set according to specific application scenarios or application requirements.

[0104] The trigger content whose click score is higher than the click threshold indicates that the trigger content can meet the information query needs reflected by the corresponding query statement to a certain extent. On this basis, the difference between the click score of the trigger content and the historical highest score is less than the click difference, indicating that the trigger content can accurately meet the information query needs reflected by the corresponding query statement with a high probability. Correspondingly, the trigger content that meets the score confidence condition is the content that can accurately meet the information query needs reflected by the corresponding query statement.

[0105] Step S2313, when it is determined that the query statement is not a high-frequency query statement, the target demand category and target query mode corresponding to the query statement are determined according to the triggering content of the query statement. When it is determined that the mode state of the target query mode under the target demand category is confident according to the acquired mode state matching list, it is determined that the query statement passes the confidence judgment and the corresponding confident query statement is obtained.

[0106] The pattern state matching list includes pattern states corresponding to multiple query patterns under each of the multiple demand categories. The pattern states include trusted and untrusted.

[0107] In this embodiment, the step of obtaining the pattern matching status list may include: steps S2301-S2304.

[0108] Step S2301, obtaining a set of historical query statements.

[0109] The historical query statement set includes all query statements that trigger queries in the historical statistical period. The historical statistical period can be set according to statistical requirements, for example, it can be set to the past year.

[0110] Step S2302: classify all query statements included in the historical query statement set according to the main demand category corresponding to each query statement in the historical query statement set to obtain multiple query statements included in different demand categories.

[0111] The main demand category corresponding to each query statement is the demand category that best matches the information query intent corresponding to the query statement, and is the demand category that effectively reflects the user's real information query needs. It can be determined based on the content type of the direct content corresponding to the query statement, the content type of the trigger content with the highest click score corresponding to the query statement, etc.

[0112] Each query statement in the historical query statement set has a corresponding main demand category. The main demand category of each query statement can be used as a demand category, and multiple demand categories can be obtained. The query statements included in the historical query statement set are classified according to these demand categories, and the query statements with the same main demand category are classified into one category. Correspondingly, multiple query statements included in each demand category can be obtained.

[0113] Step S2303, randomly extract a predetermined number of query statements under each demand category, extract a corresponding query pattern for each query statement in the predetermined number of query statements, and obtain the frequency of occurrence of multiple query patterns under each demand category.

[0114] The predetermined number can be set according to specific application scenarios or application requirements. Assuming that for a demand category "movie", there may be tens of thousands of query statements under the demand category, and the predetermined number is 100, 100 statements can be randomly selected from the tens of thousands of query statements.

[0115] For each demand category, for each query statement in the randomly selected query statements, the corresponding query pattern can be extracted according to the method for extracting the target query pattern from the target query statement described below. After obtaining the query pattern of each query statement, the number of query statements with the same query pattern can be counted as the frequency of occurrence of the query pattern, thereby obtaining the frequency of occurrence of multiple query patterns under the demand category, and so on, obtaining the frequency of occurrence of multiple query patterns under each demand category.

[0116] Step S2304, according to the frequencies of occurrence of multiple query patterns under each demand category, the pattern states corresponding to the multiple query patterns under each demand category are set, and a pattern matching state list is generated accordingly.

[0117] In this example, after obtaining the frequencies of occurrence of multiple query modes under each demand category, the query modes may be sorted in descending order according to the frequencies of occurrence, and different mode states may be set corresponding to query modes with different sorting orders.

[0118] For example, for the demand category "movie", the statistical frequency of the query pattern "movie download" is 5, and the frequency of the query pattern "movie starring" is 20. After descending sorting, the query pattern "movie download" has the highest frequency of occurrence, and the mode status of the query pattern "movie starring" can be set to trusted, while the query pattern "movie download" has the lowest frequency of occurrence, and the mode status of the query pattern "movie download" can be set to untrusted.

[0119] The specific mode state setting process can be automatically set by the computer after setting setting rules that can be automatically executed by the computer, or it can be set manually based on the results of descending sorting of the frequencies of occurrence of multiple query modes under each demand category, combined with engineering experience. For example, assuming that the "movie playback" in the above example is actually not suitable for a trusted query mode, the mode state of the "movie playback" query mode can be directly set manually to untrusted.

[0120] In a more specific example, when it is determined that the query statement is not a high-frequency query statement, the steps of determining the target demand category and the target query mode corresponding to the query statement according to the triggering content of the query statement include: S23131-S23133.

[0121] Step S23131, determining the target demand category of the query statement according to the content type of the triggering content.

[0122] For example, the trigger content is a vertical card, and the content type of the eye-catching content can be used as the target demand category of the query statement. Alternatively, the trigger content is the answer in a selected question and answer, and the content type of the trigger content can be determined based on the classification of the selected question and answer in the knowledge graph of its source, as the target demand category of the query statement. Alternatively, the trigger content is content obtained by calling a vertical skill, and the content type of the trigger content can be determined based on the application scenario classification described in the vertical skill, as the target demand category of the query statement. Alternatively, the trigger content is official website data, and the content type of the trigger content can be determined based on the data classification of the official website data, as the target demand category of the query statement, and so on.

[0123] Step S23132, when the trigger content belongs to a vertical card, the entity name is obtained according to the entity information included in the trigger content, and the card type of the trigger content is used as the entity label; when the trigger content does not belong to a vertical card, natural language processing is performed on the query statement corresponding to the trigger content, and the entity name is obtained according to the pre-acquired knowledge graph, and the category attribute with the highest information popularity corresponding to the entity name is used as the entity label.

[0124] Vertical cards are constructed based on the corresponding content in different vertical segments, and often contain entity information of the corresponding entity. For example, a vertical card of the movie type is a movie, and displays information related to the movie "Wushuang". The content displayed is the introduction, cast, and poster of the movie "Wushuang". Correspondingly, the vertical card includes the entity information of the movie "Wushuang". When the trigger content is this vertical card, the entity name "Wushuang" can be obtained from the entity information of the vertical card.

[0125] The vertical card has a corresponding card type, and the card type can be used as an entity label. For example, if the card type is a movie information card, the corresponding entity label is "movie".

[0126] When the triggering content does not belong to a vertical card, the entities corresponding to the target query statement can be mined through automatic word segmentation, syntactic analysis, natural language classification, information extraction and other technical means included in natural language processing (NLP), based on the pre-acquired knowledge graph used to describe entity information and the relationship between entities, and the corresponding entity name is obtained. The category attribute of the entity with the highest information popularity among multiple entities with the same entity name is used as the entity label. For example, for the entity name "Wushuang", there may be entities belonging to different types of attributes in the knowledge graph, such as the novel "Wushuang", the movie "Wushuang", and the TV series "Wushuang". Among them, the movie "Wushuang" has the highest information popularity, and the corresponding entity label is "movie".

[0127] Step S23133: In the query statement corresponding to the trigger content, the entity name is replaced by the entity tag to obtain the corresponding target query pattern.

[0128] Taking the target query sentence "the leading actor of Wushuang" as an example, assuming that the extracted entity label is "movie" and the entity name is "Wushuang", after executing step S23133, it can be obtained that the target query pattern is "the leading actor of the movie".

[0129] When the query statement is not a high-frequency query statement, it is not possible to obtain more user click data. By determining the target demand category and target query mode corresponding to the query statement, and according to the corresponding mode state matching list, determining the mode state of the target query mode under the target demand category for confidence judgment, accurate confidence judgment results can be obtained accordingly.

[0130] After determining the confidence query statement for confidence judgment, enter:

[0131] Step S2320, respectively obtain the relevance score between the target query statement and each confident query statement.

[0132] A confident query statement is a query statement whose corresponding trigger content can satisfy the main information query demand it embodies. The relevance score between the target query statement and each confident query statement is an indicator reflecting the relevance between the target query statement and the corresponding confident query statement. By obtaining the relevance score between the target query statement and each confident query statement, the trigger content that actually satisfies the main information demand of the target query statement can be selected as the direct content in combination with subsequent steps, effectively satisfying the user's information query demand.

[0133] In a more specific example, the step of respectively obtaining the relevance score of the target query statement and each of the confident query statements includes:

[0134] Step S2321, input the query features of the target query statement, the recommended query features of the confident query statement, and the correlation features between the target query statement and the confident query statement as model features into the correlation model, and obtain the correlation score between the target query statement and the confident query statement output by the correlation model.

[0135] In this example, the query features of the target query statement are features related to the information query needs reflected by the target query statement, including at least the number of queries of the corresponding query statement in the recommended scenario in the recent statistical period, the number of clicks on the recommended query statement, the number of continued inputs, and the number of queries in the query scenario and the length of the statement. The specific time length of the recent statistical period can be set according to the specific application scenario or application needs, and is not limited here.

[0136] The recommendation scenario refers to a scenario in which a corresponding recommended query statement is displayed when a query statement is entered, and the user clicks to select it instead of the query statement to perform information search.

[0137] The number of queries for a query statement in a recommendation scenario is the number of times a user inputs the query statement in the recommendation scenario.

[0138] The number of clicks on the recommended query statement in the recommendation scenario is the total number of clicks on the recommended query statement by users in the recommendation scenario.

[0139] The number of times a query statement is continuously input in a recommendation scenario refers to the number of times a user continues to input information after inputting the query statement. For example, if the user inputs the query statement "spring" and then continues to input "day" without finishing, the number of continuous inputs is considered to be increased by 1.

[0140] The query scenario refers to the scenario where the user ends the information query after entering the query statement.

[0141] The number of queries of a query statement in a query scenario refers to the number of times a user directly searches for information without further input after entering a query statement.

[0142] The statement length of a query statement is the number of words or characters in the query statement.

[0143] The recommended query features of a recommended query statement are features related to the information query needs reflected by the recommended query statement, including at least the total number of clicks on the recommended scenario, the number of queries in the query scenario, the main demand satisfaction, and the sentence length of the corresponding query statement when it is used as a recommended query statement in the recent statistical period.

[0144] The total number of recommended scenario clicks of a recommended query statement refers to the number of times a query statement is clicked and selected by a user as a recommended query statement to perform information search instead of the input query statement.

[0145] The number of queries of the query scenario of the recommended query statement refers to the number of times the query statement is used as an input query statement for information search.

[0146] The main requirement satisfaction of the recommended query statement refers to the degree to which the trigger content of the recommended query statement can satisfy the information query requirement embodied by the recommended query statement. According to the steps similar to the above-mentioned confidence judgment of the query statement according to the corresponding trigger content, the main requirement satisfaction of the recommended query statement that passes the confidence judgment can be set to 1, otherwise it is set to 0.

[0147] The relevant features are features that reflect the correlation between the target query statement and the recommended query statement, and at least include the number of impressions and clicks of the confident query statement and the content type of the triggering content of the confident query statement in the most recent statistical period when the confident query statement is used as the recommended query statement under the target query statement.

[0148] The correlation model is a machine learning model trained based on the gradient boosting decision tree algorithm. The gradient boosting decision tree algorithm, also known as GBDT (Gradient Boosting Decision Tree), is an iterative decision tree algorithm that consists of multiple decision trees. The conclusions of all trees are accumulated as the final answer. It is an algorithm with strong generalization ability. It can obtain relatively excellent performance when used for model training in information query scenarios.

[0149] In this embodiment, the collected samples containing the above-mentioned query features, recommended query features, and related features can be trained based on the gradient boosting decision tree algorithm to construct a correlation model. Through the correlation model, the query features of the target query statement, the recommended query features of the confident query statement, and the related features between the two can be used to accurately evaluate the correlation between the target query statement and the confident query statement. In this example, the higher the phototropism score output by the correlation model, the stronger the correlation between the target query statement and the confident query statement, and the more the confident query statement can reflect the information query intent actually reflected by the target query statement.

[0150] Through the above step S2321, the relevance score between the target query statement and each confident query statement can be obtained respectively.

[0151] In another example, the step of respectively obtaining the relevance score between the target query statement and each of the confident query statements includes: steps S23201-S23202.

[0152] The step is 23201, the query features of the target query statement, the recommended query features of the confident query statement, and the correlation features between the target query statement and the confident query statement are respectively input into the first correlation model and the second correlation model as model features, and a first correlation score between the target query statement and the confident query statement output by the first correlation model and a second correlation score between the target query statement and the confident query statement output by the second correlation model are obtained.

[0153] The query features of the target query statement, the recommended query features of the confident query statement, and the related features between the target query statement and the confident query statement are as described in the above example and will not be described again here.

[0154] The first correlation model is a machine learning model trained based on the gradient boosting decision tree algorithm. The correlation model used in the above example will not be described in detail here.

[0155] The second correlation model is a machine learning model trained based on the Wide&Deep deep learning algorithm. The Wide&Deep deep learning algorithm is the deep learning algorithm based on which the Wide&Deep model is built. The Wide&Deep model is a type of model used for classification and regression. The core idea is to combine the memorization ability of the linear model (i.e., discovering the correlation between items or features from historical data) and the generalization ability of the DNN model (i.e., discovering the correlation between features from historical data), and optimize the parameters of the two models simultaneously during the training process, so as to achieve the optimal prediction ability of the overall model.

[0156] In this embodiment, based on the Wide&Deep deep learning algorithm, the collected samples containing the above-mentioned query features, recommended query features, and related features can be trained to construct a second correlation model.

[0157] Step S23202: multiply the first correlation score and the second correlation score by the corresponding weights respectively and sum them up to obtain the correlation score.

[0158] The weight corresponding to the first correlation score and the weight corresponding to the second correlation score can be set according to engineering experience or experimental simulation data.

[0159] By multiplying the first correlation score output by the first correlation model and the second correlation score output by the second correlation model by the corresponding weights and summing them up to obtain the correlation score, the model performance of the two correlation models can be combined to make a more accurate evaluation of the correlation between the target query statement and the recommended query statement.

[0160] After getting the relevance score, go to:

[0161] Step S2330, based on the relevance scores between the target query and each of the confident query statements, the triggering content of the confident query statement that meets the content direct access condition is determined as the direct access content corresponding to the target query statement.

[0162] The content direct access condition is that the correlation score between the confidence query statement and the target query statement is higher than the correlation threshold and the correlation score is the highest. The correlation threshold is used to determine whether the confidence query statement and the target query statement are actually related based on the correlation score, and can be set based on engineering experience or experimental simulation data.

[0163] A confident query statement is a query statement whose corresponding trigger content can satisfy the main information query demand it embodies. A confident query statement has a correlation score with the target query statement that is higher than the correlation threshold, which means that the confident query statement is actually related to the target query statement. A confident query statement has the highest correlation score with the target query statement, which means that the confident query statement is most related to the target query statement and can best reflect the real information query demand embodied by the target query statement.

[0164] Correspondingly, the content direct access conditions set as above can quickly determine the trigger content that can actually meet the real information query needs reflected by the target query statement as the direct access content, so that the direct access content can actually meet the corresponding information acquisition needs.

[0165] <Information Acquisition Device>

[0166] In this embodiment, an information acquisition device 3000 is also provided. Figure 3 As shown, it includes: a recommendation acquisition unit 3100, a content triggering unit 3200 and a direct acquisition unit 3300, which are used to implement the information acquisition method provided in this embodiment, and will not be repeated here.

[0167] The recommendation acquisition unit 3100 is configured to acquire a set of recommended query statements corresponding to a target query statement input by a user.

[0168] The content triggering unit 3200 is used to obtain the triggering content of the target query statement and each recommended query statement included in the recommended query statement set through a preset content triggering method; the triggering content is the content that is pre-associated with the corresponding target query statement or the recommended query statement.

[0169] Optionally, the preset content triggering method includes at least one of the four methods: vertical card triggering, selected question and answer triggering, official website data triggering, and vertical skill triggering.

[0170] The direct acquisition unit 3300 is used to determine the direct content corresponding to the target query statement based on the trigger content of the target query statement and each of the recommended query statements, so as to provide the user with the information he or she expects to obtain by associating the direct content with the target query statement and displaying it.

[0171] Optionally, the direct acquisition unit 3300 is further configured to implement the following steps:

[0172] The target query statement and each of the recommended query statements are respectively regarded as a query statement, and according to the triggering content of the query statement, confidence judgment is performed on the query statement to determine a confident query statement that passes the confidence judgment;

[0173] Respectively obtaining a relevance score between the target query statement and each of the confident query statements;

[0174] According to the relevance score between the target query and each of the confident query, the trigger content of the confident query that meets the content direct access condition is determined as the direct access content corresponding to the target query;

[0175] The content direct access condition is that the relevance score between the confident query statement and the target query statement is higher than a relevance threshold and the relevance score is the highest.

[0176] Optionally, the step of performing confidence judgment on the query statement according to the trigger content of the query statement and obtaining a confident query statement that passes the confidence judgment, which is implemented by the direct acquisition unit 3300, includes:

[0177] Determining whether the query statement is a high-frequency query statement based on the historical query times of the query statement;

[0178] When it is determined that the query statement is a high-frequency query statement, the click score of the triggering content of the query statement is obtained, and when the click score meets the score confidence condition, it is determined that the query statement passes the confidence judgment, and the corresponding confident query statement is obtained; the score confidence condition is that the click score is higher than the click threshold and the difference between the click score and the highest click score in history is less than the click difference;

[0179] When it is determined that the query statement is not a high-frequency query statement, the target demand category and the target query pattern corresponding to the query statement are determined according to the triggering content of the query statement. When it is determined that the pattern state of the target query pattern under the target demand category is trusted according to the acquired pattern state matching list, it is determined that the query statement passes the confidence judgment and obtains the corresponding trusted query statement; the pattern state matching list includes pattern states corresponding to multiple query patterns under each of the multiple demand categories; the pattern states include trusted and untrusted.

[0180] Optionally, the step of obtaining the click score of the triggering content of the query statement when the direct acquisition unit 3300 is used to implement the determination that the query statement is a high-frequency query statement includes:

[0181] Obtain user click data of the trigger content in the most recent statistical period, and fit the user click data to obtain a click score of the trigger content according to a pre-built click score model; the user click data at least includes the number of impressions, clicks, navigation clicks, last clicks, and skip clicks of the trigger content;

[0182] as well as,

[0183] When it is determined that the query statement is not a high-frequency query statement, the step of determining a target demand category and a target query mode corresponding to the query statement according to the triggering content of the query statement includes:

[0184] Determining the target demand category of the query statement according to the content type of the trigger content;

[0185] When the trigger content belongs to a vertical card, the entity name is obtained according to the entity information included in the trigger content, and the card type of the trigger content is used as the entity label; when the trigger content does not belong to a vertical card, the query statement corresponding to the trigger content is subjected to natural language processing, the entity name is obtained according to the pre-acquired knowledge graph, and the category attribute with the highest information popularity corresponding to the entity name is used as the entity label;

[0186] In the query statement corresponding to the trigger content, the entity name is replaced by the entity tag to obtain the corresponding target query pattern.

[0187] Optionally, the step of respectively obtaining the relevance score between the target query statement and each of the confident query statements implemented by the direct acquisition unit 3300 includes:

[0188] Inputting the query features of the target query statement, the recommended query features of the confident query statement, and the correlation features between the target query statement and the confident query statement as model features into a correlation model, and obtaining a correlation score between the target query statement and the confident query statement output by the correlation model;

[0189] The query features include at least the number of queries for the corresponding query statement in the recommended scenario in the recent statistical period, the number of clicks on the recommended query statement, the number of continued inputs, the number of queries for the query scenario, and the length of the sentence; the recommended query features include at least the total number of clicks on the recommended scenario, the number of queries for the query scenario, the degree of satisfaction of the main demand, and the sentence length when the corresponding query statement is used as a recommended query statement in the recent statistical period; the related features include at least the number of displays, the number of clicks, and the content type of the triggering content of the confident query statement in the recent statistical period when the confident query statement is used as a recommended query statement under the target query statement; the correlation model is a machine learning model trained based on a gradient boosting decision tree algorithm;

[0190] or,

[0191] The step of respectively obtaining the relevance score between the target query statement and each of the confident query statements comprises:

[0192] Inputting the query features of the target query statement, the recommended query features of the confident query statement, and the correlation features between the target query statement and the confident query statement as model features into a first correlation model and a second correlation model, respectively, to obtain a first correlation score between the target query statement and the confident query statement output by the first correlation model and a second correlation score between the target query statement and the confident query statement output by the second correlation model;

[0193] Among them, the query features at least include the query times of the corresponding query statement in the recommended scenario in the recent statistical period, the click times of the recommended query statement, the number of continued input times, the query times of the query scenario and the sentence length; the recommended query features at least include the total click times of the recommended scenario, the query times of the query scenario, the main demand satisfaction and the sentence length when the corresponding query statement is used as a recommended query statement in the recent statistical period; the related features at least include the display times, the click times and the content type of the triggering content of the confident query statement in the recent statistical period when the confident query statement is used as a recommended query statement under the target query statement; the first relevance model is a machine learning model trained based on the gradient boosting decision tree algorithm; the second relevance model is a machine learning model trained based on the Wide&Deep deep learning algorithm;

[0194] The first relevance score and the second relevance score are respectively multiplied by corresponding weights and summed to obtain the relevance score.

[0195] Those skilled in the art should understand that the information acquisition device 3000 can be implemented in various ways. For example, the information acquisition device 3000 can be implemented by configuring the processor through instructions. For example, the instructions can be stored in a ROM, and when the device is started, the instructions are read from the ROM into a programmable device to implement the information acquisition device 3000. For example, the information acquisition device 3000 can be solidified into a dedicated device (such as an ASIC). The information acquisition device 3000 can be divided into independent units, or they can be combined together for implementation. The information acquisition device 3000 can be implemented by one of the various implementations described above, or it can be implemented by a combination of two or more of the various implementations described above.

[0196] In this embodiment, the information acquisition device 3000 may be a server program that provides information acquisition services, or may be a software development kit (such as SDK) that is packaged and implements the data acquisition method after being called.

[0197] <Information Acquisition Device>

[0198] In this embodiment, an information acquisition device 4000 is also provided. Figure 4 As shown, including:

[0199] Memory 4100, used to store executable instructions;

[0200] The processor 4200 is used to run the information acquisition device 4000 to execute any one of the information acquisition methods provided in this embodiment according to the executable instructions.

[0201] In this embodiment, the information acquisition device 4000 may be any device having data management and processing functions, such as a blade server, a cloud server, or a server group. Figure 1 The server 1100 shown also includes a communication device and the like.

[0202] <Readable Storage Medium>

[0203] In this embodiment, a readable storage medium is further provided, which stores a computer program that can be read and executed by a computer. The computer program is used to execute the information acquisition method described in this embodiment when read and executed by the computer.

[0204] A readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. The readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the above. More specific examples of readable storage media (a non-exhaustive list) include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the above. The readable storage medium used herein is not to be interpreted as a transient signal itself, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.

[0205] The first embodiment of the present invention has been described above in conjunction with the accompanying drawings. According to this embodiment, an information acquisition method, apparatus, device and readable storage medium are provided. Through a preset content triggering method, trigger contents pre-associated with a target query statement input by a user and each recommended query statement corresponding to the target query statement are respectively acquired. Then, according to the trigger contents of the target query statement and each recommended query statement, direct content corresponding to the target query statement that can accurately meet the user's information query needs is determined, and the direct content is displayed in association with the target query statement. This allows the user to instantly obtain information that accurately meets their own information query needs without having to wait for the information search process or make information browsing selections after entering the target query statement, thereby greatly shortening the time it takes for the user to obtain information and reducing the user's information acquisition cost.

[0206] <Second Embodiment>

[0207] In this embodiment, a method for obtaining information is provided. The information may include any content that can be accessed through a local area network or a wide area network, for example, the information may include web page content, pictures, audio, video, entries, encyclopedias, etc.

[0208] The information acquisition method in this embodiment can be implemented by a client, which can include a mobile phone, a laptop computer, a desktop computer, a tablet computer, etc. In one example, the information acquisition method in this embodiment can be implemented by Figure 1 Client 1200 implementation is shown.

[0209] like Figure 5 As shown, the information acquisition method includes: steps S4100-S4300.

[0210] Step S4100: receiving an input operation from a user, and determining a target query statement corresponding to the input operation.

[0211] In this embodiment, the user's input operation may include a text input operation, a voice input operation, etc. For example, Figure 6 As shown, an information query bar can be set in the information query interface to receive the user's input operation, and after receiving the user's input, the corresponding target query sentence "Japan" is determined.

[0212] Step S4200: triggering, according to the target query statement, obtaining direct content corresponding to the target query statement.

[0213] The direct content corresponding to the target query statement is obtained according to the information acquisition method provided in the first embodiment, which will not be described in detail here.

[0214] In this embodiment, the client implementing this embodiment can receive the user's input operation, determine the corresponding target query statement and send it to the server implementing the first embodiment, and the server obtains the direct content corresponding to the target query statement according to the information acquisition method of the first embodiment and returns it to the client.

[0215] Step S4300: associate the direct content with the target query statement and display it, so as to provide the user with the information he or she expects to obtain.

[0216] The direct content corresponding to the target query statement is associated with the target query statement and displayed, so that after entering the target query statement, the user does not need to wait for the information search process or make information browsing selections, and can immediately obtain the direct content that accurately meets their own information query needs, greatly shortening the time for users to obtain information and reducing the user's information acquisition costs.

[0217] In a specific example, the target query statement is displayed after receiving an input operation through an information query bar set in the information query interface, for example, Figure 6 As shown, the user enters "Japan" in the information query bar in the information query interface, and correspondingly, "Japan" is displayed in the information query bar; correspondingly, the step of associating and displaying the direct content with the target query statement includes:

[0218] The content items corresponding to the direct access content are displayed through the content display area arranged above the information query bar.

[0219] The content entry is used to display the direct content after receiving a click operation from the user.

[0220] For example, if the user enters "Japan", the corresponding direct content obtained is a vertical card introducing Japan. Figure 6 As shown, the content entry corresponding to the vertical card, which uses the Japan-related picture in the vertical card as an icon and displays part of the information in the vertical card, is displayed above the information query bar, allowing the user to directly click to display the specific content of the vertical card.

[0221] In this embodiment, in step S2200, while obtaining the direct content corresponding to the target query statement, a set of recommended query statements corresponding to the target query statement can also be obtained. In step S2300, while the direct content is associated with the target query statement and displayed, the recommended query statements are also associated with the target query statement and displayed. For example, Figure 6 As shown, the area above the content display area above the information input box also displays recommended query statements corresponding to "Japan", such as "Japanese weather" and "Japanese movies". In addition to directly accessing the content, users can also obtain information by clicking on the recommended query statements, thereby expanding the scope of information acquisition.

[0222] In this embodiment, the information acquisition method provided also includes:

[0223] When a change in the input operation is detected, a target query statement corresponding to the changed input operation is re-determined, so as to trigger the steps of acquiring the direct content and associating the direct content with the target query statement for display according to the target query statement.

[0224] For example, after the user enters "Japan" and then continues to enter "travel", the target query statement corresponding to the changed input operation is re-determined as "Japan travel", and the steps of triggering the acquisition of direct access content and associating and displaying the direct access content with the target query statement are re-executed according to "Japan travel", resulting in a refreshed information query interface. Or, after the user enters "Japan" and then deletes "Japan", the target query statement corresponding to the changed input operation is re-determined as "Japan", and the steps of triggering the acquisition of direct access content and associating and displaying the direct access content with the target query statement are re-executed according to "Japan", resulting in a refreshed information query interface.

[0225] By dynamically acquiring the corresponding direct access content for associated display according to the changes in the user's input operations, it can adaptively adapt to the changes in the user's information acquisition needs, acquire the direct access content that meets the changed information acquisition needs for display, so as to meet the user's real-time and dynamically changing information acquisition needs.

[0226] <Information acquisition device>

[0227] In this embodiment, an information acquisition device 5000 is further provided. As Figure 7 shown, it includes: a query determination unit 5100, a direct access acquisition unit 5200, and an associated display unit 5300, which are used to implement the information acquisition method provided in this embodiment and will not be elaborated here.

[0228] The query determination unit 5100 is configured to receive the user's input operation and determine the target query statement corresponding to the input operation.

[0229] The direct access acquisition unit 5200 is configured to trigger the acquisition of the direct access content corresponding to the target query statement according to the target query statement; the direct access content is acquired according to any one of the information acquisition methods in the first embodiment.

[0230] The associated display unit 5300 is configured to associate and display the direct access content with the target query statement to provide the user with the information they expect to obtain.

[0231] Optionally, the target query statement is displayed in the information query bar set in the information query interface after receiving the input operation; the associated display unit 5300 is further configured to:

[0232] Display the content entries corresponding to the direct access content through the content display area set above the information query bar; the content entries are used to display the direct access content after receiving the user's click operation.

[0233] Optionally, the information acquisition device 5000 is further configured to:

[0234] When a change in the input operation is detected, the target query statement corresponding to the changed input operation is re-determined, so as to execute the steps of triggering acquisition of the direct content and associating and displaying the direct content with the target query statement according to the target query statement.

[0235] Those skilled in the art should understand that the information acquisition device 5000 can be implemented in various ways. For example, the information acquisition device 5000 can be implemented by configuring the processor through instructions. For example, the instructions can be stored in a ROM, and when the device is started, the instructions are read from the ROM into a programmable device to implement the information acquisition device 5000. For example, the information acquisition device 5000 can be solidified into a dedicated device (such as an ASIC). The information acquisition device 5000 can be divided into independent units, or they can be combined together for implementation. The information acquisition device 5000 can be implemented by one of the various implementations described above, or it can be implemented by a combination of two or more of the various implementations described above.

[0236] In this embodiment, the information acquisition device 5000 may be a client application software that provides information acquisition services, for example, it may be a browser client, an information flow application client, etc.

[0237] <Information Acquisition Device>

[0238] In this embodiment, an information acquisition device 6000 is also provided. Figure 8 As shown, including:

[0239] Display device 6100;

[0240] Memory 6200, used to store executable instructions;

[0241] The processor is used to run the information acquisition device 6000 to execute the information acquisition method provided in this embodiment according to the executable instructions.

[0242] In this embodiment, the information acquisition device 6000 may be an electronic device such as a mobile phone, a desktop computer, a laptop computer, a tablet computer, etc. For example, the information acquisition device 6000 may be a mobile phone installed with a client application software that provides information acquisition services.

[0243] In one example, the information acquisition device 6000 can also Figure 1 The client 1200 shown includes a communication device and the like.

[0244] <Readable Storage Medium>

[0245] In this embodiment, a readable storage medium is further provided, which stores a computer program that can be read and executed by a computer. The computer program is used to execute the information acquisition method described in this embodiment when read and executed by the computer.

[0246] A readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. The readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the above. More specific examples of readable storage media (a non-exhaustive list) include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the above. The readable storage medium used herein is not to be interpreted as a transient signal itself, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.

[0247] The second embodiment of the present invention has been described above in conjunction with the accompanying drawings. According to this embodiment, an information acquisition method, apparatus, device and readable storage medium are provided, which can trigger the acquisition of corresponding direct content that meets the user's information query needs and associate it with the target query statement based on the target query statement input by the user, so that the user does not need to wait for the information search process and make information browsing selections after entering the target query statement, and can immediately obtain information that accurately meets their own information query needs, greatly shortening the time for users to obtain information and reducing the user's information acquisition costs.

[0248] <Third Embodiment>

[0249] In this embodiment, an information acquisition system 7000 is also provided, which includes:

[0250] The information acquisition device 3000 provided in the first embodiment and the information acquisition device 5000 provided in the second embodiment;

[0251] or,

[0252] The information acquisition device 4000 provided in the first embodiment and the information acquisition device 6000 provided in the second embodiment.

[0253] In one example, the information acquisition system 7000 can be as follows: Figure 1The information acquisition system 1000 shown includes a server 1100 as the information acquisition device 4000 and a client 1200 as the information acquisition device 6000 .

[0254] <Example>

[0255] The following will be combined Fig. 9 The information acquisition method implemented by the information acquisition system 7000 in this embodiment is further illustrated by way of example, wherein the information acquisition system 7000 includes a server as the information acquisition device 4000 and a client as the information acquisition device 6000 .

[0256] like Fig. 9 As shown, the information acquisition method includes: S301-S312.

[0257] S301, the client receives the user's input operation and determines the corresponding target query statement.

[0258] S302: The client sends the target query statement to the server.

[0259] S303: The server determines a set of recommended query statements corresponding to the target query statement according to the received target query statement.

[0260] S304: The server obtains the target query statement and the triggering content of each recommended query statement in the recommended query statement set by using a preset content triggering method.

[0261] In this example, the content triggering methods include vertical card triggering, selected pomelo triggering, official website data triggering, and vertical skill triggering.

[0262] S305, the server determines whether the corresponding target query statement or recommended query statement is a high-frequency query statement based on the trigger content of the target query statement and each recommended query statement. If it is a high-frequency query statement, enter S306; if it is not a high-frequency query statement, enter S307.

[0263] S306: The server calculates the click score according to the trigger content and makes a confidence judgment according to the score confidence condition.

[0264] S307, the server obtains the target demand category and the target query mode of the corresponding query statement, obtains the corresponding mode state according to the pre-acquired mode state matching list, and performs confidence judgment.

[0265] S308: The server obtains a confidence query statement that passes the confidence judgment.

[0266] S309: The server calculates the relevance score between the target query statement and each recommended query statement based on the two relevance models, the GDBT model and the Wide&Deep model.

[0267] S310, the server determines that the triggering content of the confident query statement whose relevance score meets the content direct access condition is the direct access content corresponding to the target query statement.

[0268] S311, the server returns the direct content corresponding to the target query statement and the recommended query statement set to the client.

[0269] S312, the client associates and displays the direct content and the recommended query statement set corresponding to the target query statement with the target query statement.

[0270] In this example, assuming that the target query is "Nobody", the corresponding direct content is the vertical card of the movie "Nobody", and the recommended query set includes "Nobody movie", etc. The information query interface for related display can be as follows: Fig.10 As shown, the user can trigger the display of the vertical card by clicking on the content item of the vertical card displayed in the content display area above the information query box; similarly, when the target query statement is the name of a star, the direct content can be the vertical card of the star, and the corresponding related information query interface is also similar as shown in FIG. Fig.10 shown.

[0271] Alternatively, assuming that the target query is "Wutai Mountain Weather", the corresponding direct content is obtained by calling the vertical skill of weather query. The recommended query statement set includes "Wutai Mountain Weather Forecast", etc. The information query interface for associated display can be as follows: Fig.11 As shown in FIG. 1 , the user can directly check the corresponding Wutai Mountain weather by directly clicking on the content item displayed in the content display area above the information query box, and can also click on the content item to enter a more detailed weather forecast page; similarly, when the target query statement is an express delivery number, a certain country's exchange rate, or a certain test, the direct content can be the express logistics, real-time exchange rate, test time and location, etc. obtained by calling the corresponding vertical skills, and the corresponding associated information query interface is also similar to FIG. Fig.11 shown.

[0272] Alternatively, assuming that the target query is "PlayerUnknown's Battlegrounds", the corresponding direct content obtained is the official website data of the game "PlayerUnknown's Battlegrounds", and the recommended query statement set includes "PlayerUnknown's Battlegrounds update announcement", etc. The information query interface for the associated display can be as follows: Fig.12 As shown, the user can trigger a jump to the official website page of "PUBG" by clicking on the content item of the official website data displayed in the content display area above the information query box.

[0273] Alternatively, assuming that the target query is “Why is the sky blue?”, the corresponding direct content is the relevant content extracted from the available knowledge graph. The recommended query set includes “Why is the sky blue?”, etc. The information query interface for the associated display can be as follows: Fig.13 As shown, the user can trigger the display of the entire content of the corresponding direct content by clicking on the content item displayed in the content display area above the information query box.

[0274] The specific implementation method of each step in the above steps S301-S312 can be as described in the first and second embodiments, and will not be repeated here.

[0275] Through the information acquisition system in this example, after the client receives the target query statement input by the user, it can be sent to the server, triggering the server to obtain the trigger content that is pre-associated with the target query statement input by the user and each recommended query statement corresponding to the target query statement through a preset content triggering method, and then determine the direct content corresponding to the target query statement that can accurately meet the user's information query needs based on the trigger content of the target query statement and each recommended query statement. The server then returns the direct content to the client, and the client associates the direct content with the target query statement for display, so that the user does not need to wait for the information search process and make information browsing selections after entering the target query statement, and can immediately obtain information that accurately meets their own information query needs, greatly shortening the time for users to obtain information and reducing the user's information acquisition costs.

[0276] The present invention may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present invention.

[0277] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples of computer-readable storage media (a non-exhaustive list) include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium is not to be interpreted as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.

[0278] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0279] The computer program instructions for performing the operation of the present invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. Computer-readable program instructions may be executed entirely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be personalized by utilizing the state information of the computer-readable program instructions, and the electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present invention.

[0280] Various aspects of the present invention are described herein with reference to the flow charts and / or block diagrams of the methods, devices (systems) and computer program products according to embodiments of the present invention. It should be understood that each box of the flow chart and / or block diagram and the combination of each box in the flow chart and / or block diagram can be implemented by computer-readable program instructions.

[0281] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0282] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0283] The flow charts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to multiple embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a part of a module, a program segment or an instruction, and a part of the module, a program segment or an instruction contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions. It is well known to those skilled in the art that it is equivalent to implement it by hardware, implement it by software, and implement it by combining software and hardware.

[0284] Embodiments of the present invention have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements in the marketplace, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein. The scope of the present invention is defined by the appended claims.

Claims

1. A method for obtaining information, characterized in that: include: According to the target query statement input by the user, a set of recommended query statements corresponding to the target query statement is obtained; Obtaining the target query statement and the triggering content of each recommended query statement included in the recommended query statement set respectively through a preset content triggering method; The trigger content is content pre-associated with the corresponding target query statement or the recommended query statement, and the preset content triggering method is to use the target query statement or each recommended query statement as a trigger to obtain the trigger content pre-associated with the triggered query statement; Determining, according to the target query statement and the triggering content of each of the recommended query statements, the direct content corresponding to the target query statement, so as to provide the user with the information that the user expects to obtain by associating the direct content with the target query statement and displaying the direct content, specifically comprising: treating the target query statement and each of the recommended query statements as a query statement, respectively, performing confidence judgment on the query statements according to the triggering content of the query statements, and determining a confident query statement that passes the confidence judgment; Respectively obtaining a relevance score between the target query statement and each of the confident query statements; According to the relevance score between the target query and each of the confident query, the trigger content of the confident query that meets the content direct access condition is determined as the direct access content corresponding to the target query; The content direct access condition is that the relevance score between the confident query statement and the target query statement is higher than the relevance threshold and the relevance score is the highest; wherein, The trusted query statement is a query statement whose corresponding trigger content satisfies the main information query requirement embodied by the corresponding query statement.

2. The method according to claim 1, characterized in that The step of performing confidence judgment on the query statement according to the triggering content of the query statement to obtain a confident query statement that passes the confidence judgment includes: Determining whether the query statement is a high-frequency query statement according to the historical query times of the query statement; When it is determined that the query statement is a high-frequency query statement, the click score of the triggering content of the query statement is obtained, and when the click score meets the score confidence condition, it is determined that the query statement passes the confidence judgment, and the corresponding confident query statement is obtained; the score confidence condition is that the click score is higher than the click threshold and the difference between the click score and the highest click score in history is less than the click difference; When it is determined that the query statement is not a high-frequency query statement, the target demand category and the target query pattern corresponding to the query statement are determined according to the triggering content of the query statement. When it is determined that the pattern state of the target query pattern under the target demand category is trusted according to the acquired pattern state matching list, it is determined that the query statement passes the confidence judgment and obtains the corresponding trusted query statement; the pattern state matching list includes pattern states corresponding to multiple query patterns under each of the multiple demand categories; the pattern states include trusted and untrusted.

3. The method according to claim 2, characterized in that When it is determined that the query statement is a high-frequency query statement, the step of obtaining the click score of the triggering content of the query statement includes: Obtain user click data of the trigger content in the most recent statistical period, and fit the user click data to obtain a click score of the trigger content according to a pre-built click score model; the user click data at least includes the number of impressions, clicks, navigation clicks, last clicks, and skip clicks of the trigger content; as well as, When it is determined that the query statement is not a high-frequency query statement, the step of determining a target demand category and a target query mode corresponding to the query statement according to the triggering content of the query statement includes: Determining the target demand category of the query statement according to the content type of the trigger content; When the trigger content belongs to a vertical card, the entity name is obtained according to the entity information included in the trigger content, and the card type of the trigger content is used as the entity label; when the trigger content does not belong to a vertical card, the query statement corresponding to the trigger content is subjected to natural language processing, the entity name is obtained according to the pre-acquired knowledge graph, and the category attribute with the highest information popularity corresponding to the entity name is used as the entity label; In the query statement corresponding to the trigger content, the entity name is replaced by the entity tag to obtain the corresponding target query pattern.

4. The method according to claim 1, characterized in that: The step of respectively obtaining the relevance score between the target query statement and each of the confident query statements comprises: Inputting the query features of the target query statement, the recommended query features of the confident query statement, and the correlation features between the target query statement and the confident query statement as model features into a correlation model, and obtaining a correlation score between the target query statement and the confident query statement output by the correlation model; The query features include at least the number of queries for the corresponding query statement in the recommended scenario in the recent statistical period, the number of clicks on the recommended query statement, the number of continued inputs, the number of queries for the query scenario, and the length of the sentence; the recommended query features include at least the total number of clicks on the recommended scenario, the number of queries for the query scenario, the degree of satisfaction of the main demand, and the sentence length when the corresponding query statement is used as a recommended query statement in the recent statistical period; the related features include at least the number of displays, the number of clicks, and the content type of the triggering content of the confident query statement in the recent statistical period when the confident query statement is used as a recommended query statement under the target query statement; the correlation model is a machine learning model trained based on a gradient boosting decision tree algorithm; or, The step of respectively obtaining the relevance score between the target query statement and each of the confident query statements comprises: Inputting the query features of the target query statement, the recommended query features of the confident query statement, and the correlation features between the target query statement and the confident query statement as model features into a first correlation model and a second correlation model, respectively, to obtain a first correlation score between the target query statement and the confident query statement output by the first correlation model and a second correlation score between the target query statement and the confident query statement output by the second correlation model; Among them, the query features at least include the query times of the corresponding query statement in the recommended scenario in the recent statistical period, the click times of the recommended query statement, the number of continued input times, the query times of the query scenario and the sentence length; the recommended query features at least include the total click times of the recommended scenario, the query times of the query scenario, the main demand satisfaction and the sentence length when the corresponding query statement is used as a recommended query statement in the recent statistical period; the related features at least include the display times, the click times and the content type of the triggering content of the confident query statement in the recent statistical period when the confident query statement is used as a recommended query statement under the target query statement; the first relevance model is a machine learning model trained based on the gradient boosting decision tree algorithm; the second relevance model is a machine learning model trained based on the Wide&Deep deep learning algorithm; The first relevance score and the second relevance score are respectively multiplied by corresponding weights and summed to obtain the relevance score.

5. The method according to claim 1, characterized in that: The preset content triggering method includes at least one of the four methods: vertical card triggering, selected question and answer triggering, official website data triggering, and vertical skill triggering.

6. A method for obtaining information, characterized in that: include: Receiving an input operation from a user, and determining a target query statement corresponding to the input operation; According to the target query statement, triggering acquisition of direct content corresponding to the target query statement; The direct content is obtained according to the information acquisition method according to any one of claims 1 to 5; The direct content is associated with the target query statement and displayed, so as to provide the user with the information he or she expects to obtain.

7. The method according to claim 6, characterized in that The method further comprises: When a change in the input operation is detected, the target query statement corresponding to the changed input operation is re-determined, so as to execute the steps of triggering acquisition of the direct content and associating and displaying the direct content with the target query statement according to the target query statement; and / or, The target query statement is displayed through an information query bar set in the information query interface after receiving the input operation; The step of associating and displaying the direct content with the target query sentence comprises: A content display area is provided above the information query bar to display a content item corresponding to the direct content; the content item is used to display the direct content after receiving a click operation from the user.

8. An information acquisition device, characterized in that: include: A recommendation acquisition unit, configured to acquire a set of recommended query statements corresponding to a target query statement input by a user; A content triggering unit, configured to obtain the target query statement and the triggering content of each recommended query statement included in the recommended query statement set respectively through a preset content triggering method; The trigger content is content pre-associated with the corresponding target query statement or the recommended query statement, and the preset content triggering method is to use the target query statement or each recommended query statement as a trigger to obtain the trigger content pre-associated with the triggered query statement; a direct access acquisition unit, configured to determine, according to the target query statement and the triggering content of each of the recommended query statements, the direct access content corresponding to the target query statement, so as to provide the user with the information that the user desires to obtain by associating the direct access content with the target query statement and displaying the same; The direct acquisition unit is used to treat the target query statement and each of the recommended query statements as a query statement respectively, and perform confidence judgment on the query statements according to the triggering content of the query statements to determine the confident query statements that pass the confidence judgment; Respectively obtaining a relevance score between the target query statement and each of the confident query statements; According to the relevance score between the target query and each of the confident query, the trigger content of the confident query that meets the content direct access condition is determined as the direct access content corresponding to the target query; The content direct access condition is that the relevance score between the confident query statement and the target query statement is higher than the relevance threshold and the relevance score is the highest; wherein, The trusted query statement is a query statement whose corresponding trigger content satisfies the main information query requirement embodied by the corresponding query statement.

9. An information acquisition device, characterized in that: include: A query determination unit, configured to receive an input operation from a user and determine a target query statement corresponding to the input operation; A direct access acquisition unit, configured to trigger, according to the target query statement, acquisition of direct access content corresponding to the target query statement; The direct content is obtained according to the information acquisition method according to any one of claims 1 to 5; The associated display unit is used to associate and display the direct content with the target query sentence to provide the user with the information he or she expects to obtain.

10. An information acquisition device, characterized in that: include: A memory for storing executable instructions; A processor is used to run the information acquisition device to execute any one of the information acquisition methods according to claims 1-5 according to the executable instructions.

11. An information acquisition device, characterized in that: include: Display device; A memory for storing executable instructions; A processor is used to run the information acquisition device to execute the information acquisition method as described in claim 6 or 7 according to the executable instructions.

12. A readable storage medium, characterized in that: The readable storage medium stores a computer program that can be read and executed by a computer. When the computer program is read by the computer, it executes any one of the information acquisition methods according to claims 1 to 5 or the information acquisition method according to claim 6 or 7.

13. An information acquisition system, characterized in that: include: The information acquisition device according to claim 8 and the information acquisition device according to claim 9; or, The information acquisition device as claimed in claim 10 and the information acquisition device as claimed in claim 11.

Images