CN112035727A

CN112035727A - Information acquisition method, device, equipment, system and readable storage medium

Info

Publication number: CN112035727A
Application number: CN201910478239.2A
Authority: CN
Inventors: 郏海峰; 唐亮; 韩长东; 陈曦; 方圆; 余志乾; 蒋冠军
Original assignee: Alibaba Group Holding Ltd
Current assignee: Alibaba Group Holding Ltd
Priority date: 2019-06-03
Filing date: 2019-06-03
Publication date: 2020-12-04

Abstract

The invention discloses an information acquisition method, an information acquisition device, information acquisition equipment and a readable storage medium. The method comprises the following steps: acquiring a recommended query statement set corresponding to a target query statement according to the target query statement input by a user; respectively acquiring a target query statement and trigger content of each recommended query statement in the recommended query statement set in a preset content trigger mode; determining direct content corresponding to the target query statement according to the target query statement and the trigger content of each recommended query statement, and realizing the purpose of providing information expected to be obtained by a user to the user by performing associated display on the direct content and the target query statement.

Description

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

Technical Field

The present invention relates to the field of information technologies, and in particular, to an information obtaining method, apparatus, device, system, and readable storage medium.

Background

With the rapid development of internet technology, searching information by accessing a network has become a common information acquisition means.

People can generally input an information Query statement (Query) reflecting own information acquisition requirements in an application (such as a browser application) providing information search services, and trigger the application to search in an information database available to a network according to the information Query statement to obtain and display a corresponding search result so as to acquire information meeting the requirements.

However, at present, a user usually needs to trigger an information search process according to an information query statement after inputting the information query statement, wait for a returned search result, and browse and select in the returned search result, so that information really meeting the information acquisition requirement of the user can be determined, which is long in time consumption, high in information acquisition cost and affects information acquisition experience.

Disclosure of Invention

It is an object of the present invention to provide a new solution for obtaining information.

According to a first aspect of the present invention, there is provided an information acquisition method, including:

acquiring a recommended query statement set corresponding to a target query statement input by a user;

respectively acquiring the target query statement and the trigger content of each recommended query statement in the recommended query statement set in a preset content trigger mode; the triggering content is content which is associated with the corresponding target query statement or the corresponding recommended query statement in advance;

determining direct content corresponding to the target query statement according to the target query statement and the trigger content of each recommended query statement, and realizing that the information which the user desires to obtain is provided for the user by performing associated display on the direct content and the target query statement.

According to a second aspect of the present invention, there is provided an information acquisition method, including:

receiving input operation of a user, and determining a target query statement corresponding to the input operation;

triggering and acquiring direct content corresponding to the target query statement according to the target query statement; the through content is acquired according to any one of the information acquisition methods provided by the second aspect of the present invention;

and performing associated display on the direct content and the target query statement to realize the purpose of providing the information which the user desires to obtain for the user.

According to a third aspect of the present invention, there is provided an information acquisition apparatus comprising:

the recommendation acquisition unit is used for acquiring a recommendation query statement set corresponding to a target query statement input by a user;

the content triggering unit is used for respectively acquiring the target query statement and the triggering content of each recommended query statement in the recommended query statement set in a preset content triggering mode; the triggering content is content which is associated with the corresponding target query statement or the corresponding recommended query statement in advance;

and the direct obtaining unit is used for determining direct content corresponding to the target query statement according to the target query statement and the trigger content of each recommended query statement, and realizing that the information which the user desires to obtain is provided for the user by performing associated display on the direct content and the target query statement.

According to a fourth aspect of the present invention, there is provided an information acquisition apparatus comprising:

the query determining unit is used for receiving input operation of a user and determining a target query statement corresponding to the input operation;

a direct obtaining unit, configured to trigger obtaining of direct content corresponding to the target query statement according to the target query statement; the through content is acquired according to the information acquisition method according to any one of the first aspect of the present invention;

and the associated display unit is used for displaying the direct content and the target query statement in an associated manner, so that the information which the user desires to obtain is provided for the user.

According to a fifth aspect of the present invention, there is provided an information acquisition apparatus, comprising:

a memory for storing executable instructions;

a processor, configured to execute the information acquisition device to perform any one of the information acquisition methods according to the first aspect of the present invention according to the executable instructions.

According to a sixth aspect of the present invention, there is provided an information acquisition apparatus comprising:

a display device;

a memory for storing executable instructions;

a processor, configured to execute the information acquisition device to perform any one of the information acquisition methods according to the second aspect of the present invention according to the executable instructions.

According to a seventh aspect of the present invention, there is provided a readable storage medium storing a computer program readable and executable by a computer, the computer program, when read by the computer, executing any one of the information acquisition methods according to the first aspect of the present invention or the information acquisition method according to the second aspect of the present invention.

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

an information acquisition apparatus according to a third aspect of the present invention and an information acquisition apparatus according to a fourth aspect of the present invention;

alternatively, the first and second electrodes may be,

an information acquisition apparatus according to a fifth aspect of the present invention and an information acquisition apparatus according to a sixth aspect of the present invention.

According to one embodiment of the disclosure, trigger contents associated with target query sentences input by a user and each recommended query sentence corresponding to the target query sentences can be acquired in advance through a preset content trigger mode, then direct contents corresponding to the target query sentences and capable of accurately meeting the information query requirements of the user are determined according to the target query sentences and the trigger contents of each recommended query sentence, and the direct contents and the target query sentences are displayed in an associated mode, so that the user can acquire information accurately meeting the information query requirements of the user in real time without waiting for an information search process and performing information browsing selection after inputting the target query sentences, the time for the user to acquire the information is greatly shortened, and the information acquisition cost of the user is reduced.

Other features of the present invention and advantages thereof will become apparent from the following detailed description of exemplary embodiments thereof, which proceeds with reference to the accompanying drawings.

Drawings

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

Fig. 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.

Fig. 2 shows a flowchart of an information acquisition method of the first embodiment of the present invention.

Fig. 3 shows a block diagram of an information acquisition apparatus 3000 of the first embodiment of the present invention.

Fig. 4 shows a block diagram of an information acquisition apparatus 4000 of the first embodiment of the present invention.

Fig. 5 shows a flowchart of an information acquisition method of the second embodiment of the present invention.

FIG. 6 is a diagram showing an example of a direct content and target query statement association display of the second embodiment of the present invention.

Fig. 7 shows a block diagram of an information acquisition apparatus 5000 of a second embodiment of the present invention.

Fig. 8 shows a block diagram of an information acquisition apparatus 6000 of the second embodiment of the present invention.

Fig. 9 shows a flowchart of an example of an information acquisition method implemented by the information acquisition system 7000 of the third embodiment of the present invention.

FIG. 10 is a first diagram showing an example of the display of the direct content associated with the target query statement according to the third embodiment of the present invention.

FIG. 11 is a diagram II showing an example of the display of the direct content in association with the target query statement according to the third embodiment of the present invention.

FIG. 12 is a diagram III showing an example of the direct content and target query statement associated display according to the third embodiment of the present invention.

FIG. 13 is a diagram IV showing an example of the direct content and target query statement association display according to the third embodiment of the present invention.

Detailed Description

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 the components and steps, the numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise.

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.

Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail but are intended to be part of the specification where appropriate.

In all examples shown and discussed herein, any particular value should be construed as merely illustrative, and not limiting. Thus, other examples of the exemplary embodiments may have different values.

It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, further discussion thereof is not required in subsequent figures.

< hardware configuration >

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

As shown in fig. 1, information system 1000 includes a server 1100, a client 1200, and a network 1300.

The server 1100 may be, for example, a blade server, a cloud server, a server group composed of a plurality of servers, or the like. In one example, the server 1100 may be as shown in FIG. 1, including 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 speakers, microphones, etc., these components are not relevant to the present invention and are omitted here. The processor 1110 may be, for example, a central processing unit CPU, a microprocessor MCU, or the like. The memory 1120 includes, for example, a ROM (read only memory), a RAM (random access memory), a nonvolatile memory such as a hard disk, and the like. The interface device 1130 includes, for example, a USB interface, a serial interface, and the like. The communication device 1140 is capable of wired or wireless communication, for example. The display device 1150 is, for example, a liquid crystal display panel. Input devices 1160 may include, for example, a touch screen, a keyboard, and the like.

Client 1200 may be a laptop (1200-1), desktop (1200-2), cell phone (1200-3), tablet (1200-4), etc. As shown in fig. 1, client 1200 may include a processor 1210, memory 1220, interface device 1230, communication device 1240, display device 1250, input device 1260, speaker 1270, microphone 1280, and so on. The processor 1210 may be a central processing unit CPU, a microprocessor MCU, or the like. The memory 1220 includes, for example, a ROM (read only memory), a RAM (random access memory), a nonvolatile memory such as a hard disk, and the like. The interface device 1230 includes, for example, a USB interface, a headphone interface, and the like. The communication device 1240 can perform wired or wireless communication, for example. The display device 1250 is, for example, a liquid crystal display, a touch display, or the like. The input device 1260 may include, for example, a touch screen, a keyboard, and the like. A user can input/output voice information through the speaker 1270 and the microphone 1280.

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

The information system 1000 shown in fig. 1 is merely illustrative and is in no way intended to limit the present invention, its application, or uses. In an embodiment of the present invention, the memory 1120 of the server 1100 is configured to store instructions for controlling the processor 1110 to operate so as to execute any one of the information obtaining methods provided by the embodiment of the present invention. In addition, the memory 1220 of the client 1200 is used for storing instructions for controlling the processor 1210 to operate so as to execute any one of the information methods provided by the embodiments of the present invention. It will be appreciated by those skilled in the art that although a number of devices are shown in FIG. 1 for both server 1100 and client 1200, the present invention may refer to only some of the devices, for example, server 1100 may refer to only processor 1110 and storage 1120, or client 1200 may refer to only processor 1210 and storage 1220, etc. The skilled person can design the instructions according to the disclosed solution. How the instructions control the operation of the processor is well known in the art and will not be described in detail herein.

The general concept of the implementation of the invention is to provide a new scheme for acquiring information, which can respectively acquire the target query statement input by a user and the trigger content pre-associated with each recommended query statement corresponding to the target query statement through a preset content trigger mode, then determine the direct content corresponding to the target query statement and capable of accurately meeting the information query requirement of the user according to the target query statement and the trigger content of each recommended query statement, and perform associated display on the direct content and the target query statement, so that the user can acquire the information accurately meeting the information query requirement of the user immediately after inputting the target query statement without waiting for the information search process and performing information browsing selection, thereby greatly shortening the time for acquiring the information by the user and reducing the information acquisition cost of the user.

< first embodiment >

In the present embodiment, an information acquisition method is provided. The information may include any content accessible over a local or wide area network, for example, the information may include web content, pictures, audio, video, terms, encyclopedias, and the like.

The information obtaining method in this embodiment may be implemented by a server, and the server may include a blade server, a cloud server, or a server cluster. In one example, the information acquisition method in the present embodiment may be implemented by the server 1100 shown in fig. 1.

As shown in fig. 2, the information acquisition method includes: steps S2100-S2300.

Step S2100, according to the target query statement input by the user, obtains a recommended query statement set corresponding to the target query statement.

The recommended query statement set comprises a plurality of recommended query statements corresponding to the target query statement. In this embodiment, after performing semantic analysis, content association, and other processing on the target query statement, the corresponding recommended query statement may be obtained, for example, assuming that the query statement of the target query input by the user is "spring," and after performing semantic analysis, content association, and other processing on "spring," the corresponding recommended query statement "coming from spring," "flower in spring," "poetry in spring," and the like may be obtained. In this embodiment, a plurality of recommended query sentences ranked in the top order of the queried times in the latest statistical time period may be selected according to the queried times of the plurality of recommended query sentences in the latest statistical time period, so as to reduce the processing amount of subsequent steps and further improve the information acquisition efficiency.

Step S2200 is to obtain the target query statement and the trigger content of each recommended query statement included in the recommended query statement set, respectively, in a preset content trigger manner.

The trigger content is content that is associated with a corresponding target query statement or recommended query statement in advance.

The preset content triggering mode is a mode of acquiring triggering content of a target query statement or a recommended query statement, and is different from a general information searching mode of searching and matching in massive information of a wide area network or a local area network according to the query statement to find a corresponding search result, and the target query statement or the recommended query statement can be used as a trigger to quickly and directly acquire the triggering content associated with the triggered query statement in advance.

Through a preset content triggering mode, content which is associated with a target query statement or a recommended query statement in advance can be quickly and directly acquired without searching and matching in massive acquirable information, so that direct content which corresponds to the target query statement and can accurately meet the information query requirement of a user is determined from the triggering content in combination with subsequent steps, and the user can immediately meet the information acquisition requirement of the user after inputting the target query statement without waiting for an information searching process and browsing and selecting information.

In one example, the preset content triggering mode at least comprises one of a vertical card triggering mode, a fine question and answer triggering mode, an official website data triggering mode and a vertical skill triggering mode.

The vertical card is an information card which is constructed by acquiring corresponding field information by means of machine crawling or manual mining and the like in different vertical subdivision fields. For example, for the field of "movie", the vertical subdivision may include multiple fields such as "comedy movie", "love movie", "ethical movie", "animation movie", "europe and america movie", "chinese movie", and corresponding content is obtained for different vertical subdivision fields, and multiple vertical cards may be constructed, for example, "love movie" includes "roman holiday", and the vertical card constructed for "roman holiday" includes entity information such as movie name, movie introduction, movie lead actor and the like. This vertical card, after construction, is associated with the movie name "roman holiday", the movie lead actor "oredlichbook", and so on.

Correspondingly, the vertical card triggering is a content triggering mode in which a target query statement or a recommended query statement is triggered as a query statement, and a vertical card associated with the query statement is acquired as corresponding triggering content.

The choice questions may be the content of the questions extracted by an available knowledge map. The purpose of a knowledge graph is to describe the information and concepts of entities present in the real world, as well as the relationships that exist between entities. The currently available knowledge-graph typically covers entity information and associations between a large number of entities, which are typically embodied in the form of question-answer content, e.g., the knowledge-graph includes "why is the sky blue? "the corresponding exact answer, and accordingly, the exact answer is associated with" why sky is blue? "this query statement establishes an association. The question and answer contents are extracted from the acquirable knowledge graph to be used as the selected question and answer, and accordingly a large amount of information contents which are correspondingly established by taking the questions in the question and answer contents as query sentences can be obtained.

Correspondingly, the fine question-answer triggering is a content triggering mode which takes a target query statement or a recommended query statement as a query statement to trigger, and obtains an answer in fine question-answer data which is associated with the query statement as corresponding triggering content.

The official website data is data published by an official website corresponding to an entity. Entity information or entity concepts of its corresponding entities and associations with other entities are typically included in the data published by the official website. For example, the most accurate and detailed movie star data of a movie star is published in the official website of the movie star, and the association between the movie star data and the query statement related to the name of the movie star is correspondingly established. The official website data which are established with corresponding association can be obtained from a plurality of accessible and authenticated official websites through machine crawling or manual mining.

Correspondingly, the official website data triggering is a content triggering mode which takes a target query statement or a recommended query statement as a query statement to trigger and acquires official website data which is associated with the query statement as corresponding triggering content.

Vertical skills are application skills developed for the application requirements of different vertical subdivision domains. For example, for express delivery query requirements, developed express delivery query skills, and the vertical skills are called, the corresponding express delivery logistics information can be queried through the input express delivery bill number. Similarly, there are weather queries, attraction queries, and the like. By invoking vertical skills, the associated content can be directly, quickly, accurately, etc.

Correspondingly, the vertical skill triggering is a content triggering mode which takes a target query statement or a recommended query statement as a query statement for triggering, calls the corresponding vertical skill, and acquires the content which is associated with the query statement as the corresponding triggering content.

After step S2200, the process proceeds to:

step S2300, determining the direct content corresponding to the target query statement according to the target query statement and the trigger content of each recommended query statement, so as to provide the user with the information that the user desires to obtain by displaying the direct content in association with the target query statement.

The target query statement and the trigger content of each recommended query statement are content which is associated with the target query statement or the recommended query statement in advance, direct content corresponding to the target query statement is determined from the trigger content, the information query requirement of a user can be met accurately, the user can meet the information acquisition requirement immediately after inputting the target query statement without waiting for an information search process and performing information browsing selection, and the information acquisition cost is greatly reduced.

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

Step S2310, using the target query statement and each recommended query statement as a query statement, performing confidence judgment on the query statement according to trigger content of the query statement, and determining a confidence query statement passing the confidence judgment.

The trigger content of the target query statement and each recommended query statement is content that is associated with the corresponding target query statement or recommended query statement in advance. In some cases, although the trigger content can reflect the information query intention of the corresponding query statement to a certain extent, and can and certainly satisfy the main information query requirement (actual, most important information query requirement) embodied by the corresponding query statement, in step S2310, the query statement can be subjected to confidence judgment according to the trigger content of the query statement, and the confidence query statement subjected to confidence judgment is the query statement of which the corresponding trigger content can satisfy the main information query requirement embodied by the query statement, so that the direct content which can more accurately satisfy the actual information query requirement of the user can be obtained by combining with the subsequent steps, and the information acquisition efficiency of the user can be improved.

In a more specific example, the step S2310 of performing confidence judgment by using the target query statement or the recommended query statement as a query statement may include: steps S2311-S2313.

Step S2311, determining whether the query statement is a high frequency query statement according to the historical query times of the query statement.

The historical query times of the query statement are the times of the query statement used by a user for querying information in a preset historical statistic time period, and the historical query times can be obtained by analyzing and counting according to a log of an application providing information query service in the historical statistic time period. The historical statistical time period may be set according to a specific application scenario or an application requirement, and is not limited to a specific numerical value here.

In this example, a high frequency query threshold may be set according to engineering experience or experimental simulation, and a query statement in which the historical query frequency of the query statement is greater than the high frequency query threshold is determined as a high frequency query statement.

Whether the query statement is a high-frequency query statement or not is distinguished according to the historical query times of the query statement, different confidence judgment strategies can be implemented for the high-frequency query statement and the non-high-frequency statement in combination with the subsequent steps, accurate confidence judgment is achieved, accurate confidence query statements are correspondingly obtained, and then direct contents of actual information query requirements of users can be met accurately.

Step S2312, when the query statement is determined to be the high-frequency query statement, the click score of the trigger content of the query statement is obtained, and when the click score meets the score confidence condition, the query statement is determined to pass confidence judgment to obtain the corresponding confidence query statement.

And the click score of the trigger content of the query statement is the score obtained by the user click data meter according to the corresponding trigger content.

The historical query times of the high-frequency query sentences are high, the probability that the corresponding trigger content is clicked by the user is high, confidence judgment is conducted on the high-frequency query sentences through the corresponding click scores, and accurate confidence judgment results can be obtained.

In a more specific example, when the query statement is determined to be a high-frequency query statement, the step of obtaining the click score of the trigger content of the query statement includes:

s23121, user click data of the trigger content in the latest statistical time period is obtained, and click scores of the trigger content are obtained by fitting the user click data according to a pre-constructed click score model.

The statistical time period is a time period for counting user click data of the trigger content, and may be set according to a specific application scenario or application requirements, for example, the statistical time period may be 1 week, 1 month, or N days.

The user click data of the trigger content in the latest statistical period is the overall data related to the user click, which occurs on the trigger content in the latest statistical period. The user click data at least comprises the display times, click times, navigation click times, final click times and skip click times of the corresponding trigger contents. The number of times the trigger content is presented is the total number of times the trigger content is queried. The number of clicks of the trigger content is the total number of clicks of the user after the trigger content is queried and displayed. The navigation click times of the trigger contents are the triggered contents of the trigger contents, and the total times that the user clicks only the trigger contents and does not click other trigger contents occur. The last click times of the trigger contents are the total times that the user clicks the trigger contents after clicking other trigger contents after the trigger contents are inquired and displayed. The number of times of skipping and clicking the trigger content is the total number of times of skipping the trigger content and clicking the trigger content by the user after the trigger content is inquired and displayed.

The click score model may adopt training methods related to an SVM (Support Vector Machine), such as training methods of Support Vector regression, Support Vector clustering and the like, and a Machine learning model obtained by training a large number of collected samples is used to perform linear fitting on the display times, click order, navigation click times, final click times, skip click times and the like included in the input user click data as characteristic values of the model input, and output corresponding click scores.

The click score of the corresponding trigger content is obtained by fitting the click data of the user through the click score model, and the user information acquisition requirement reflected by the trigger content can be accurately reflected.

The score confidence condition is a condition for judging whether the trigger content meets the main information query requirement embodied by the corresponding query statement according to the click score.

In this example, the score confidence condition is that the click score is above the click threshold and the difference between the click score and the historical highest click score is less than the click difference. The click threshold and the click difference can be set according to engineering experience or experimental simulation aiming at a specific confidence judgment scene. The historical highest click score is the highest score of click scores available in the historical scoring period. The historical scoring period may be set according to a specific application scenario or application requirements.

The trigger content with the click score higher than the click threshold indicates that the trigger content can meet the information query requirement embodied by the corresponding query statement to a certain extent, on the basis, the difference value between the click score of the trigger content and the historical highest score is smaller than the click difference value, which indicates that the trigger content can accurately meet the information query requirement embodied by the corresponding query statement with higher probability, and the corresponding trigger content meeting the score confidence condition is the content which can accurately meet the information query requirement embodied by the corresponding query statement.

Step S2313, when the query statement is determined not to be the high-frequency query statement, the target requirement category and the target query mode corresponding to the query statement are determined according to the trigger content of the query statement, and when the mode state of the target query mode in the target requirement category is determined to be confidence according to the acquired mode state matching list, the query statement is determined to obtain the corresponding confidence query statement through confidence judgment.

The pattern state matching list comprises pattern states corresponding to a plurality of query patterns under each requirement category in a plurality of requirement categories. The mode status includes trusted and untrusted.

In this embodiment, the step of obtaining the pattern matching state list may include: steps S2301-S2304.

In step S2301, a historical query statement set is acquired.

All query statements that trigger a query in a historical statistics period are included in the set of historical query statements. The historical statistical period may be set according to statistical requirements, for example, may be set to the past 1 year, etc.

Step S2302 classifies all query sentences included in the historical query sentence set according to the main requirement category corresponding to each query sentence in the historical query sentence set, to obtain a plurality of query sentences included under different requirement categories.

The main requirement category corresponding to each query statement is the requirement category which is most matched with the information query intention corresponding to the query statement and is the requirement category which effectively reflects the real information query requirement of the user. The content type of the direct content corresponding to the query statement, the content type of the trigger content corresponding to the query statement and having the highest click score, and the like can be determined.

Each query statement in the historical query statement set has a corresponding main requirement category, the main requirement category of each query statement can be used as one requirement category, a plurality of requirement categories can be obtained, the query statements included in the historical query statement set are classified according to the requirement categories, the query statements with the same main requirement categories are classified into one category, and correspondingly, a plurality of query statements included in each requirement category can be obtained.

Step S2303, randomly extracting a predetermined number of query statements in each requirement category, extracting a corresponding query pattern for each query statement in the predetermined number of query statements, and obtaining the frequency of occurrence of each query pattern in each requirement category.

The predetermined number may be set according to a specific application scenario or application requirements. Assuming that there are ten thousand query sentences under the requirement category "movie", the predetermined number is 100, and 100 sentences can be randomly extracted from the ten thousand query sentences.

For each requirement category, for each query statement in the randomly extracted query statements, a corresponding query pattern may be extracted according to a method for extracting a target query pattern from the target query statement as follows. After the query pattern of each query statement is obtained, the number of query statements with the same query pattern can be counted as the frequency of occurrence of the query pattern, so as to obtain the frequency of occurrence of each query pattern under the requirement category, and by analogy, the frequency of occurrence of each query pattern under each requirement category is obtained.

Step S2304, setting mode states corresponding to the plurality of query modes of each requirement category according to the frequency of occurrence of the plurality of query modes of each requirement category, and correspondingly generating a mode matching state list.

In this example, after obtaining the frequency of occurrence of each of the plurality of query patterns in each requirement category, the query patterns with different ordering orders may be set to have different pattern states in a descending order according to the frequency of occurrence of the plurality of query patterns.

For example, for the requirement category of "movie", the statistical frequency of occurrence of the query pattern of "download of movie" is 5, the frequency of occurrence of the query pattern of "lead actor of movie" is 20, the frequency of occurrence of the query pattern of "download of movie" after descending order is the highest, the mode status of the query pattern of "lead actor of movie" may be set as trusted, the frequency of occurrence of the query pattern of "download of movie" is the lowest, and the mode status of the query pattern of "download of movie" may be set as untrusted.

The specific mode state setting process can be automatically set by the computer after setting a setting rule which can be automatically executed by the computer, or can be manually set by combining engineering experience according to the result of descending order sorting of the frequency of occurrence of a plurality of query modes under each requirement category, for example, if the query mode of 'movie playing' in the above example is actually not suitable for confidence, the mode state of the query mode of 'movie playing' can be directly set to be non-confidence by manual operation.

In a more specific example, when it is determined that the query statement is not a high-frequency query statement, the step of determining the target requirement category and the target query pattern corresponding to the query statement according to the trigger content of the query statement includes: S23131-S23133.

Step S23131, a target requirement category of the query statement is determined according to the content type of the trigger content.

For example, the trigger content is a vertical card, the content type of the trigger content may be used as the target requirement category of the query statement, or the trigger content is an answer in a refined question-answer, and the content type of the trigger content may be determined as the target requirement category of the query statement according to a classification in a knowledge graph of the source of the refined question-answer, or the trigger content is a content obtained by invoking a vertical skill, and the content type of the trigger content may be determined as the target requirement category of the query statement according to an application scene classification described by the vertical skill, or the trigger content is the official website data, and the content type of the trigger content may be determined as the target requirement category of the query statement according to a data classification of the official website data, and so on.

Step S23132, when the trigger content belongs to the vertical card, acquiring an entity name according to entity information included in the trigger content, and using the card type of the trigger content as an entity label; and when the trigger content does not belong to the vertical card, performing natural language processing on the query sentence corresponding to the trigger content, acquiring an entity name according to a pre-acquired knowledge graph, and taking the category attribute with the highest information heat corresponding to the entity name as an entity label.

The vertical cards are constructed by obtaining corresponding contents in different vertical subdivision fields, and often have entity information of corresponding entities. For example, the card type is a movie, a vertical card showing related information of the movie "no double", the content shown is a brief introduction, a clerk list, a poster, etc. of the movie "no double", and correspondingly, the vertical card includes entity information of an entity of the movie "no double", and when the triggering content is the vertical card, the entity name can be obtained from the entity information of the vertical card: "No double".

The vertical card has a corresponding card type, which can be used as a physical tag. Taking the information card of which the card type is a movie as an example, the entity tag obtained correspondingly is "movie".

When the trigger content does not belong to the vertical card, according to technical means such as automatic word segmentation, syntactic analysis, Natural Language classification, information extraction and the like included in Natural Language Processing (NLP), an entity corresponding to a target query statement is mined according to a pre-acquired knowledge graph for describing entity information and relationships between entities, an entity name is correspondingly obtained, and a category attribute of an entity with the highest information heat degree in a plurality of entities with the same entity name is used as an entity label, for example, for the entity name 'no double', the entity with different types of attributes such as saying 'no double', movie 'no double', television drama 'no double' and the like may exist in the knowledge graph, wherein the information heat degree of the movie 'no double' is the highest, and the corresponding entity label is 'movie'.

Step S23133, in the query statement corresponding to the trigger content, replacing the entity name with the entity label to obtain a corresponding target query pattern.

Taking the target query statement as "dual-purpose lead actor" as an example, assuming that the extracted entity label is "movie", and the entity name is "dual-purpose", after step S23133 is executed, it can be obtained that the target query pattern is "lead actor of movie".

When the query statement is not a high-frequency query statement, a large amount of user click data cannot be acquired, the target requirement category and the target query mode corresponding to the query statement are determined, the mode state of the target query mode in the target requirement category is determined according to the corresponding mode state matching list for confidence judgment, and an accurate confidence judgment result can be acquired correspondingly.

After determining the confidence query statement of the confidence judgment, entering:

step S2320, the relevance scores of the target query statement and each confidence query statement are respectively obtained.

The confidence query statement is a query statement of which the corresponding trigger content can meet the main requirement of the information query embodied by the confidence query statement. The relevance score for the target query statement and each of the confidence query statements is an index that reflects the relevance between the target query statement and the corresponding confidence query statement. By obtaining the relevance scores of the target query statement and each confidence query statement, the trigger content of the main information requirement of the actual full target query statement can be selected as the direct content by combining the subsequent steps, and the information query requirement of the user is effectively met.

In a more specific example, the step of obtaining a relevance score for the target query statement and each of the confidence query statements separately comprises:

step S2321, inputting the query characteristics of the target query statement, the recommendation query characteristics of the confidence query statement and the correlation characteristics between the target query statement and the confidence query statement as model characteristics into a correlation model, and acquiring the correlation score between the target query statement and the confidence query statement output by the correlation model.

In this example, the query feature of the target query statement is a feature related to the information query requirement embodied by the target query statement, and at least includes the query frequency of the corresponding query statement in the recommended scene of the latest statistical period, the click frequency of the recommended query statement, the number of continuous inputs, the query frequency of the query scene, and the statement length. The specific time length of the recent statistical time period may be set according to a specific application scenario or application requirement, which is not limited herein.

The recommendation scene is a scene in which the corresponding recommended query statement is displayed when the query statement is input, and a user clicks and selects the recommended query statement to replace the query statement for information query.

The query times of the query statement in the recommendation scene are the times of the user inputting the query statement in the recommendation scene.

The number of clicks of the recommended query statement of the query statement in the recommendation scene is the total number of clicks of the recommended query statement of the query statement by the user in the recommendation scene.

The continuous input times of the query statement in the recommended scene refer to the times that the user continuously inputs the query statement and then performs information query. For example, if the query sentence input by the user is "spring" and the user does not end the continuous input of "day" thereafter, the number of continuous inputs is considered to be increased by 1.

The query scenario refers to a scenario in which a user finishes performing information query after inputting a query statement.

The query times of the query statement in the query scene refer to the times of directly querying information after the user inputs the query statement without inputting any more.

The term length of a query term is the number of words or characters of the query term.

The recommended query features of the recommended query statement are features related to the information query requirement embodied by the recommended query statement, and at least comprise the total click times of the recommended scene, the query times of the query scene, the main requirement satisfaction degree and the statement length when the corresponding query statement is used as the recommended query statement in the latest statistical period.

The total click times of the recommended scenes of the recommended query sentences refer to the times of information query by clicking and selecting the input query sentences instead by the user when the query sentences are used as the recommended query sentences.

The query frequency of the query scenario of the recommended query statement refers to the frequency of information query performed by the query statement as an input query statement.

The main requirement satisfaction degree of the recommended query statement refers to the degree that the triggering content of the recommended query statement corresponds to the information query requirement embodied by the recommended query statement. According to the step of performing confidence judgment on the query statement according to the corresponding trigger content, which is similar to the above, the main requirement satisfaction degree of the recommended query statement through the confidence judgment is set to be 1, and otherwise, the main requirement satisfaction degree is set to be 0.

The relevant features are features for reflecting the relevance between the target query statement and the recommended query statement, and at least comprise the display times, the click times and the content type of the trigger content of the trusted query statement in the latest statistical time period when the trusted query statement is used as the recommended query statement under the target query statement.

The correlation model is a machine learning model obtained by training based on a gradient boosting decision tree algorithm. The gradient Boosting Decision tree algorithm, also called gbdt (gradient Boosting Decision tree), is an iterative Decision tree algorithm, and is composed of a plurality of Decision trees, and the conclusions of all the trees are accumulated to make a final answer, so that the algorithm is a high generalization capability (generalization) algorithm, and is used for performing model training in an information query scene to obtain excellent performance.

In this embodiment, the collected samples including the query feature, the recommended query feature, and the relevant feature may be trained based on a gradient boosting decision tree algorithm to construct a relevance model, and the relevance strength between the target query statement and the confidence query statement may be accurately evaluated according to the query feature of the target query statement, the recommended query feature of the confidence query statement, and the relevant feature therebetween. In this example, the higher the phototropic score output by the relevance model is, the stronger the relevance between the target query statement and the confidence query statement is, and the more the confidence query statement can reflect the information query intention actually reflected by the target query statement.

Through the above step S2321, the relevance scores between the target query statement and each of the confidence query statements may be obtained respectively.

In another example, the step of obtaining a relevance score for the target query statement and each of the confidence query statements separately comprises: steps S23201-S23202.

Step 23201, the query feature of the target query statement, the recommended query feature of the confidence query statement and the correlation feature between the target query statement and the confidence query statement are used as model features to be respectively input into the first correlation model and the second correlation model, and a first correlation score of the target query statement and the confidence query statement output by the first correlation model and a second correlation score of the target query statement and the confidence query statement output by the second correlation model are obtained.

The query characteristics of the target query statement, the recommended query characteristics of the confidence query statement, and the correlation characteristics between the target query statement and the confidence query statement, as described in the above example, are not described herein again.

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

The second correlation model is a machine learning model obtained by training based on Wide & Deep learning algorithm. The Wide & Deep learning algorithm is a Deep learning algorithm based on which a Wide & Deep model is constructed. The Wide & Deep model is a model for classification and regression, and the core idea is to combine the memory ability (i.e. finding out the correlation between items or features from historical data) of the linear model and the generalization ability (i.e. finding out the correlation between features from historical data) of the DNN model, and simultaneously optimize the parameters of 2 models in the training process, so as to achieve the optimal prediction ability of the whole model.

In this embodiment, the collected samples including the query feature, the recommended query feature, and the relevant feature may be trained based on a Wide & Deep learning algorithm to construct and form a second relevance model.

Step S23202, the first correlation score and the second correlation score are multiplied by the corresponding weights respectively and summed up to obtain the correlation score.

The weight corresponding to the first relevance score and the weight corresponding to the second relevance score may be set according to engineering experience values or experimental simulation data.

The first relevance score output by the first relevance model and the second relevance score output by the second relevance model are respectively multiplied by corresponding weights and summed to obtain the relevance scores, so that the model performances of the two relevance models can be integrated, and the relevance between the target query statement and the recommended query statement can be more accurately evaluated.

After obtaining the relevance score, enter:

step S2330, according to the relevance scores of the target query sentences and each confidence query sentence, determining the trigger contents of the confidence query sentences meeting the content direct condition as the direct contents corresponding to the target query sentences.

The content-through condition is that the relevance score between the confidence query statement and the target query statement is above a relevance threshold and the relevance score is highest. The correlation threshold is a threshold for judging whether the confidence query statement and the target query statement are actually correlated according to the correlation score, and may be set according to engineering experience values or experimental simulation data.

The confidence query statement is a query statement of which the corresponding trigger content can meet the main requirement of the information query embodied by the confidence query statement. A confidence query statement is a score of a correlation with the target query statement that is above a correlation threshold, meaning that the confidence query statement is actually correlated with the target query statement. The confidence query statement has the highest relevance score with the target query statement, which means that the confidence query statement is most relevant with the target query statement and can best reflect the real information query requirement embodied by the target query statement.

Correspondingly, the content direct condition set as described above can quickly determine the trigger content capable of actually meeting the real information query requirement embodied by the target query statement as the direct content, so that the direct content can actually meet the corresponding information acquisition requirement.

< information acquiring apparatus >

In the present embodiment, there is also provided an information acquisition apparatus 3000, as shown in fig. 3, including: the recommendation obtaining unit 3100, the content triggering unit 3200, and the direct obtaining unit 3300 are used to implement the information obtaining method provided in this embodiment, and are not described herein again.

A recommendation obtaining unit 3100, configured to obtain, according to a target query statement input by a user, a recommendation query statement set corresponding to the target query statement.

A content triggering unit 3200, configured to obtain the target query statement and a triggering content of each recommended query statement included in the recommended query statement set, respectively, in a preset content triggering manner; the trigger content is content associated with the corresponding target query statement or the recommended query statement in advance.

Optionally, the preset content triggering mode at least comprises one of a vertical card triggering mode, a fine question and answer triggering mode, an official website data triggering mode and a vertical skill triggering mode.

A direct obtaining unit 3300, configured to determine, according to the target query statement and the trigger content of each recommended query statement, a direct content corresponding to the target query statement, and implement to provide information that the user desires to obtain to the user by performing associated display on the direct content and the target query statement.

Optionally, the direct acquisition unit 3300 is further configured to perform the following steps:

taking the target query statement and each recommended query statement as a query statement respectively, performing confidence judgment on the query statement according to the trigger content of the query statement, and determining the confidence query statement passing the confidence judgment;

respectively obtaining the relevance scores of the target query statement and each confidence query statement;

determining the trigger content of the confidence query statement meeting the content direct condition as direct content corresponding to the target query statement according to the relevance score of the target query statement and each confidence query statement;

the content-through condition is that the relevance score between the confidence query statement and the target query statement is above a relevance threshold and the relevance score is highest.

Optionally, the step of performing confidence judgment on the query statement according to the trigger content of the query statement, which is implemented by the direct obtaining unit 3300, to obtain a confidence query statement passing the confidence judgment includes:

determining whether the query statement is a high-frequency query statement or not according to the historical query times of the query statement;

when the query statement is determined to be a high-frequency query statement, acquiring a click score of the trigger content of the query statement, and when the click score meets a score confidence condition, determining that the query statement obtains the corresponding confidence query statement through confidence judgment; the score confidence condition is that the click score is above a click threshold and the difference between the click score and the historical highest click score is less than a click difference;

when the query statement is determined not to be a high-frequency query statement, determining a target demand category and a target query mode corresponding to the query statement according to the trigger content of the query statement, and when the mode state of the target query mode in the target demand category is determined to be confidence according to an obtained mode state matching list, determining that the query statement obtains the corresponding confidence query statement through confidence judgment; the mode state matching list comprises mode states corresponding to a plurality of query modes under each requirement category in a plurality of requirement categories; the mode states include trusted and untrusted.

Optionally, when the direct obtaining unit 3300 is configured to perform the step of determining that the query statement is a high-frequency query statement, the step of obtaining the click score of the trigger content of the query statement includes:

acquiring user click data of the trigger content in the latest statistical time period, and fitting the user click data according to a pre-constructed click score model to obtain a click score of the trigger content; the user click data at least comprises the display times, click times, navigation click times, final click times and skip click times of the trigger content;

and the number of the first and second groups,

when the query statement is determined not to be the high-frequency query statement, the step of determining the target demand category and the target query mode corresponding to the query statement according to the trigger content of the query statement comprises:

determining a 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, acquiring an entity name according to entity information included in the trigger content, and taking the card type of the trigger content as an entity tag; when the trigger content does not belong to a vertical card, performing natural language processing on the query sentence corresponding to the trigger content, acquiring an entity name according to a pre-acquired knowledge graph, and taking a category attribute with the highest information heat corresponding to the entity name as an entity label;

and replacing the entity name with the entity label in the query statement corresponding to the trigger content to obtain the corresponding target query mode.

Optionally, the step of separately obtaining the relevance score of the target query statement and each of the confidence query statements, which is implemented by the direct obtaining unit 3300, includes:

inputting the query features of the target query statement, the recommended query features of the confidence query statement and the relevant features between the target query statement and the confidence query statement as model features into a relevance model, and acquiring the relevance score of the target query statement and the confidence query statement output by the relevance model;

the query features at least comprise the query times of the corresponding query statement in the recommended scene in the latest statistical time period, the click times of the recommended query statement, the continuous input times, the query times of the query scene and the statement length; the recommended query features at least comprise recommended scene total click times, query times of a query scene, main requirement satisfaction and sentence lengths when the corresponding query sentences serve as recommended query sentences in the latest statistical time period; the relevant features at least comprise the display times and click times of the confidence query statement and the content type of the trigger content of the confidence query statement in the recent statistical time period when the confidence query statement is taken as a recommendation query statement under the target query statement; the correlation model is a machine learning model obtained by training based on a gradient lifting decision tree algorithm;

alternatively, the first and second electrodes may be,

the step of obtaining the relevance scores of the target query statement and each of the confidence query statements respectively comprises:

inputting the query feature of the target query statement, the recommended query feature of the confidence query statement and the correlation feature between the target query statement and the confidence query statement as model features into a first correlation model and a second correlation model respectively, and acquiring a first correlation score of the target query statement and the confidence query statement output by the first correlation model and a second correlation score of the target query statement and the confidence query statement output by the second correlation model;

the query features at least comprise the query times of the corresponding query statement in the recommended scene in the latest statistical time period, the click times of the recommended query statement, the continuous input times, the query times of the query scene and the statement length; the recommended query features at least comprise recommended scene total click times, query times of a query scene, main requirement satisfaction and sentence lengths when the corresponding query sentences serve as recommended query sentences in the latest statistical time period; the relevant features at least comprise the display times and click times of the confidence query statement and the content type of the trigger content of the confidence query statement in the recent statistical time period when the confidence query statement is taken as a recommendation query statement under the target query statement; the first correlation model is a machine learning model obtained by training based on a gradient lifting decision tree algorithm; the second correlation model is a machine learning model obtained by training based on Wide & Deep learning algorithm;

and multiplying the first correlation score and the second correlation score by corresponding weights respectively and summing to obtain the correlation score.

It will be appreciated by those skilled in the art that the information acquisition apparatus 3000 can be implemented in various ways. For example, the information acquisition apparatus 3000 may be realized by an instruction configuration processor. For example, the information acquisition apparatus 3000 may be implemented by storing instructions in a ROM and reading the instructions from the ROM into a programmable device when starting up the device. For example, the information acquisition device 3000 may be cured into a dedicated device (e.g., ASIC). The information acquisition apparatus 3000 may be divided into units independent of each other, or may be implemented by combining them together. The information acquisition apparatus 3000 may be implemented by one of the various implementations described above, or may be implemented by a combination of two or more of the various implementations described above.

In the present embodiment, the information acquiring apparatus 3000 may be a server program providing an information acquiring service, or may be a software development kit (e.g., SDK) or the like packaged to be called and then implementing a data acquiring method.

< information acquiring apparatus >

In this embodiment, an information acquiring apparatus 4000 is further provided, as shown in fig. 4, including:

a memory 4100 for storing executable instructions;

a processor 4200, configured to execute the information obtaining apparatus 4000 to perform any one of the information obtaining methods provided in this embodiment according to the executable instructions.

In this embodiment, the information obtaining device 4000 may be any device having data management and processing functions, for example, a blade server, a cloud server, or a server group. In one example, the information acquisition apparatus 4000 may be the server 1100 shown in fig. 1, further including a communication device and the like.

< readable storage Medium >

In this embodiment, a readable storage medium is further provided, where a computer program that can be read and executed by a computer is stored, and the computer program is configured to execute the information acquisition method according to this embodiment when the computer program is read and executed by the computer.

The readable storage medium may be a tangible device that can hold and store instructions for use by an instruction execution device. The readable storage medium may be, for example, but not limited to, an electronic memory device, a magnetic memory device, an optical memory device, an electromagnetic memory device, a semiconductor memory device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a Static Random Access Memory (SRAM), a portable compact disc read-only memory (CD-ROM), a Digital Versatile Disc (DVD), a memory stick, a floppy disk, a mechanical coding device, such as punch cards or in-groove projection structures having instructions stored thereon, and any suitable combination of the foregoing. A readable storage medium as used herein is not to be construed as a transitory 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 an electrical wire.

The first embodiment of the present invention has been described above with reference to the accompanying drawings, and according to this embodiment, an information obtaining method, an apparatus, a device, and a readable storage medium are provided, in which a preset content triggering manner is used to respectively obtain a target query statement input by a user and trigger content pre-associated with each recommended query statement corresponding to the target query statement, and then according to the target query statement and the trigger content of each recommended query statement, direct content corresponding to the target query statement and capable of accurately satisfying the information query requirement of the user is determined, and the direct content and the target query statement are displayed in an associated manner, so that the user can obtain information accurately satisfying the information query requirement of the user immediately without waiting for an information search process and performing information browsing selection after inputting the target query statement, and the time for the user to obtain information is greatly shortened, and the information acquisition cost of the user is reduced.

< second embodiment >

The information acquisition method in this embodiment may be implemented by a client, where the client may include a mobile phone, a notebook computer, a desktop computer, a tablet computer, and the like. In an example, the information obtaining method in this embodiment may be implemented by the client 1200 shown in fig. 1.

As shown in fig. 5, the information acquisition method includes: steps S4100-S4300.

Step S4100 receives an input operation by the user, and specifies a target query expression corresponding to the input operation.

In the present embodiment, the input operation by the user may include a text input operation, a voice input operation, and the like. For example, as shown in fig. 6, an input operation by a user may be received by providing an information query field in an information query interface, and after receiving a user input, a corresponding target query sentence "japan" is determined.

Step S4200, according to the target query statement, triggering to obtain the direct content corresponding to the target query statement.

The direct content corresponding to the target query statement is obtained according to the information obtaining method provided in the first embodiment, and is not described herein again.

In this embodiment, the client implementing this embodiment may receive an input operation of a user, determine that a corresponding target query statement is sent to the server implementing the first embodiment, and the server acquires direct content corresponding to the target query statement according to the information acquisition method of the first embodiment and returns the direct content to the client.

And step S4300, the direct content and the target query statement are displayed in a correlation mode, and information which the user desires to obtain is provided for the user.

The direct content corresponding to the target query sentence is displayed in a correlation mode with the target query sentence, so that a user can immediately acquire the direct content accurately meeting the information query requirement of the user without waiting for an information search process and performing information browsing selection after inputting the target query sentence, the time for the user to acquire the information is greatly shortened, and the information acquisition cost of the user is reduced.

In a specific example, the target query statement is displayed after receiving an input operation through an information query bar provided in the information query interface, for example, as shown in fig. 6, a user inputs "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 displaying the direct content and the target query statement in a correlation manner comprises the following steps:

and displaying content items corresponding to the through content through a content display area arranged above the information query bar.

The content item is used for displaying the through content after receiving the click operation of the user.

For example, assuming that the user inputs "japan" and the corresponding acquired direct content is a vertical card for introducing japan, a content item corresponding to the vertical card and having a related picture of the japanese in the vertical card as an icon and displaying information in a part of the vertical card may be displayed above the information query column as shown in fig. 6, so that the user may directly click and display specific content of the vertical card.

In this embodiment, in step S2200, the direct content corresponding to the target query sentence may be acquired and the set of recommended query sentences corresponding to the target query sentence may be acquired at the same time, and in step S2300, the direct content and the target query sentence may be displayed in association with each other and the recommended query sentences and the target query sentence may be displayed in association with each other, for example, as shown in fig. 6, the recommended query sentences corresponding to "japan" such as "weather in japan" and "movies in japan" may be displayed in an area above the content display area above the information input box. The user can directly obtain the information by clicking the recommended query sentence besides the content, and the information obtaining range is expanded.

In this embodiment, the information acquiring method further includes:

and when the input operation is detected to be changed, re-determining the target query sentence corresponding to the changed input operation, and executing the steps of triggering to acquire the direct content and carrying out associated display on the direct content and the target query sentence according to the target query sentence.

For example, after inputting "japan", the user continues to input "tour", re-determines that the target query sentence corresponding to the changed input operation is "tour", re-executes the steps of acquiring the direct content according to the "tour", and displaying the direct content in association with the target query sentence, to obtain the information query interface which is displayed in a refreshed manner, or, after inputting "japan", deletes the "book", re-determines that the target query sentence corresponding to the changed input operation is "day", re-executes the steps of acquiring the direct content according to the "day", and displaying the direct content in association with the target query sentence, to obtain the information query interface which is displayed in a refreshed manner.

By dynamically acquiring the corresponding direct content for associated display according to the change of the input operation of the user, the method can adaptively adapt to the change of the information acquisition requirement of the user, acquire the direct content meeting the changed information acquisition requirement for display, and meet the real-time dynamically changed information acquisition requirement of the user.

< information acquiring apparatus >

In the present embodiment, there is also provided an information acquisition apparatus 5000, as shown in fig. 7, including: the query determining unit 5100, the direct obtaining unit 5200, and the association display unit 5300 are configured to implement the information obtaining method provided in this embodiment, and details are not repeated here.

The query determining unit 5100 is configured to receive an input operation by a user, and determine a target query statement corresponding to the input operation.

A direct obtaining unit 5200, configured to trigger and obtain, according to the target query statement, direct content corresponding to the target query statement; the through content is acquired according to the information acquisition method described in any one of the first embodiments.

The association display unit 5300 is configured to associate and display the direct content and the target query statement, so as to provide information that the user desires to obtain to the user.

Optionally, the target query statement is displayed after receiving the input operation through an information query bar arranged in an information query interface; the association display unit 5300 is further configured to:

displaying content items corresponding to the through content through a content display area arranged above the information query bar; and the content item is used for displaying the direct content after receiving the click operation of the user.

Optionally, the information acquiring apparatus 5000 is further configured to:

and when the input operation is detected to be changed, re-determining the target query sentence corresponding to the changed input operation, and executing the steps of triggering to acquire the direct content and displaying the direct content and the target query sentence in a correlated manner according to the target query sentence.

It will be appreciated by those skilled in the art that the information acquisition apparatus 5000 may be implemented in various ways. The information acquisition apparatus 5000 can be realized by, for example, an instruction configuration processor. For example, the information acquisition apparatus 5000 may be implemented by storing instructions in a ROM and reading the instructions from the ROM into a programmable device when starting the device. For example, the information acquisition apparatus 5000 may be solidified into a dedicated device (e.g., ASIC). The information acquiring means 5000 may be divided into units independent of each other, or may be implemented by combining them together. The information acquisition means 5000 may be implemented by one of the various implementations described above, or may be implemented by a combination of two or more of the various implementations described above.

In the present embodiment, the information acquiring apparatus 5000 may be client application software that provides an information acquiring service, and may be, for example, a browser client, an information flow application client, or the like.

< information acquisition apparatus >

In this embodiment, an information acquiring apparatus 6000 is further provided, as shown in fig. 8, including:

a display device 6100;

a memory 6200 for storing executable instructions;

a processor, configured to execute the information obtaining apparatus 6000 to perform the information obtaining method as provided in this embodiment according to the executable instructions.

In this embodiment, the information acquiring device 6000 may be an electronic device such as a mobile phone, a desktop computer, a notebook computer, and a tablet computer. For example, the information acquisition apparatus 6000 may be a mobile phone in which client application software that provides an information acquisition service is installed.

In one example, the information acquiring apparatus 6000 may also be a client 1200 as shown in fig. 1, including a communication device and the like.

< readable storage Medium >

The second embodiment of the present invention has been described above with reference to the accompanying drawings, and according to this embodiment, an information obtaining method, an apparatus, a device, and a readable storage medium are provided, which can trigger obtaining of corresponding direct content meeting a user information query requirement and associated display of a target query statement according to the target query statement input by a user, so that the user can obtain information accurately meeting the user information query requirement immediately after inputting the target query statement without waiting for an information search process and performing information browsing selection, thereby greatly shortening the time for obtaining information by the user, and reducing the information obtaining cost of the user.

< third embodiment >

In this embodiment, an information acquiring system 7000 is further provided, where the information acquiring system 7000 includes:

the information acquisition device 3000 provided in the first embodiment and the information acquisition device 5000 provided in the second embodiment;

alternatively, the first and second electrodes may be,

the information acquisition apparatus 4000 provided in the first embodiment and the information acquisition apparatus 6000 provided in the second embodiment.

In one example, information acquisition system 7000 may be as information acquisition system 1000 shown in fig. 1, including server 1100 as information acquisition device 4000 and client 1200 as information acquisition device 6000.

< example >

The information acquisition method implemented by the information acquisition system 7000 in this embodiment will be further illustrated with reference to fig. 9, where the information acquisition system 7000 includes a server as the information acquisition device 4000 and a client as the information acquisition device 6000.

As shown in fig. 9, the information acquisition method includes: S301-S312.

S301, the client receives input operation of a user and determines a corresponding target query statement.

S302, the client sends the target query statement to the server.

S303, the server determines a recommended query statement set corresponding to the target query statement according to the received target query statement.

S304, the server obtains the target query statement and the trigger content of each recommended query statement in the recommended query statement set through a preset content trigger mode.

In this example, the content triggering modes comprise four modes of vertical card triggering, fine denier triggering, official website data triggering and vertical skill triggering.

S305, the server judges whether the corresponding target query statement or recommended query statement is a high-frequency query statement or not according to the target query statement and the triggering content of each recommended query statement, if so, the step S306 is carried out, and if not, the step S307 is carried out.

S306, the server calculates click scores according to the trigger contents and carries out confidence judgment according to score confidence conditions.

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

S308, the server obtains a confidence query statement passing the confidence judgment.

S309, the server calculates the relevance score of the target query statement and each recommended query statement according to the GDBT model and the Wide & Deep model.

S310, the server determines the trigger content of the confidence query statement with the relevance score meeting the content direct condition as direct content corresponding to the target query statement.

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

S312, the client side displays the direct content corresponding to the target query sentence and the recommended query sentence set in a correlation mode with the target query sentence.

In this example, assuming that the target query statement is "innominate", the corresponding obtained direct content is a vertical card of the movie of "innominate" and the set of recommended query statements includes "innominate movie", etc., the information query interface for performing the associated display may be as shown in fig. 10, and the user may trigger to display the vertical card by clicking a content item of the vertical card displayed in the content display area above the information query frame; similarly, when the target query statement is the name of a certain star, the through content may be a vertical card of the star, and the information query interface displayed correspondingly and in association is similar to that shown in fig. 10.

Or, assuming that the target query statement is "five-mountain weather," the correspondingly obtained through content is obtained by calling a vertical skill of weather query, the set of recommended query statements includes "five-mountain weather forecast," and the like, the information query interface for performing associated display may be as shown in fig. 11, and a user may directly view the corresponding five-mountain weather through a content entry displayed in a content display area above the information query box, or may click the content entry to enter a more detailed weather forecast page; similarly, when the target query statement is an express bill number, a national exchange rate, or a certain examination, the through content may be express logistics, a real-time exchange rate, an examination time and place, and the like acquired by calling a corresponding vertical skill, and the information query interface displayed correspondingly and in association is similar to that shown in fig. 11.

Or, assuming that the target query statement is "absolutely required," the corresponding acquired direct content is the official website data of the game "absolutely required," the recommended query statement set includes "absolutely required updated announcement" and the like, the information query interface for performing the associated display may be as shown in fig. 12, and the user may trigger a jump to the official website page of "absolutely required" by clicking a content item of the official website data displayed in the content display area above the information query box.

Or, assuming that the target query sentence is "why the sky is" and the corresponding obtained through content is related content in the selected question and answer extracted from the available knowledge map, and the set of recommended query sentences includes "why the sky is blue" and the like, the information query interface for performing the association display may be as shown in fig. 13, and the user may trigger to display the entire content of the corresponding through content by clicking on a content item displayed in a content display area above the information query box.

The specific implementation method of each of the steps S301 to S312 may be as described in the first and second embodiments, and will not be described herein again.

Through the information acquisition system in the embodiment, after receiving a target query sentence input by a user at a client, the target query sentence input by the user is sent to a server, the trigger server respectively acquires trigger contents which are pre-associated with the target query sentence input by the user and each recommended query sentence corresponding to the target query sentence in a preset content trigger mode, then according to the trigger contents of the target query sentence and each recommended query sentence, direct contents which correspond to the target query sentence and can accurately meet the information query requirement of the user are determined, then the direct contents are returned to the client by the server, the direct contents and the target query sentence are associated and displayed by the client, and the information which can accurately meet the information query requirement of the user can be immediately acquired by the user without waiting for the information search process and performing information browsing selection after the target query sentence is input by the user, the time for the user to acquire the information is greatly shortened, and the information acquisition cost of the user is reduced.

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

The computer readable storage medium may be a tangible device that can hold and store the instructions for use by the instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic memory device, a magnetic memory device, an optical memory device, an electromagnetic memory device, a semiconductor memory device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a Static Random Access Memory (SRAM), a portable compact disc read-only memory (CD-ROM), a Digital Versatile Disc (DVD), a memory stick, a floppy disk, a mechanical coding device, such as punch cards or in-groove projection structures having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media as used herein is not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., optical pulses through a fiber optic cable), or electrical signals transmitted through electrical wires.

The computer-readable program instructions described herein may be downloaded from a computer-readable storage medium to a respective computing/processing device, or 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 may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers. The network adapter card or network interface in each computing/processing device receives computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in the respective computing/processing device.

The computer program instructions for carrying out operations of the present invention may be assembler instructions, Instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, aspects of the present invention are implemented by personalizing an electronic circuit, such as a programmable logic circuit, a Field Programmable Gate Array (FPGA), or a Programmable Logic Array (PLA), with state information of computer-readable program instructions, which can execute the computer-readable program instructions.

Aspects of the present invention are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.

These computer-readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer-readable program instructions may also be stored in a computer-readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer-readable medium storing the instructions comprises an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.

The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions. It is well known to those skilled in the art that implementation by hardware, by software, and by a combination of software and hardware are equivalent.

Having described embodiments of the present invention, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the embodiments disclosed. 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 terminology used herein is chosen in order to best explain the principles of the embodiments, the practical application, or improvements made to the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein. The scope of the invention is defined by the appended claims.

Claims

1. An information acquisition method, comprising:

2. The method of claim 1, wherein the step of determining, according to the target query statement and the trigger content of each of the recommended query statements, the direct content corresponding to the target query statement comprises:

3. The method according to claim 2, wherein the step of performing confidence judgment on the query statement according to the trigger content of the query statement to obtain a confidence query statement passing the confidence judgment comprises:

4. The method of claim 3,

when the query statement is determined to be a high-frequency query statement, the step of obtaining the click score of the trigger content of the query statement comprises:

and the number of the first and second groups,

5. The method of claim 2, wherein the step of obtaining a relevance score for the target query statement and each of the confidence query statements separately comprises:

alternatively, the first and second electrodes may be,

6. The method of claim 1,

the preset content triggering mode at least comprises one of four modes of vertical card triggering, choice question and answer triggering, official website data triggering and vertical skill triggering.

7. An information acquisition method, comprising:

triggering and acquiring direct content corresponding to the target query statement according to the target query statement; the direct content is acquired according to the information acquisition method as claimed in any one of claims 1 to 6;

8. The method of claim 7,

the method further comprises the following steps:

when the input operation is detected to be changed, re-determining the target query sentence corresponding to the changed input operation, and executing the steps of triggering to acquire the direct content and displaying the direct content and the target query sentence in a correlated manner according to the target query sentence;

and/or the presence of a gas in the gas,

the target query statement is displayed after receiving the input operation through an information query column arranged in an information query interface;

the step of displaying the direct content and the target query statement in a correlated manner comprises:

9. An information acquisition apparatus characterized by comprising:

10. An information acquisition apparatus characterized by comprising:

a direct obtaining unit, configured to trigger obtaining of direct content corresponding to the target query statement according to the target query statement; the direct content is acquired according to the information acquisition method as claimed in any one of claims 1 to 6;

11. An information acquisition apparatus characterized by comprising:

a memory for storing executable instructions;

a processor, configured to execute the information acquisition device to perform the information acquisition method according to any one of claims 1 to 6 according to the executable instruction.

12. An information acquisition apparatus characterized by comprising:

a display device;

a memory for storing executable instructions;

a processor configured to execute the information acquisition apparatus to perform the information acquisition method according to the executable instruction, according to claim 7 or 8.

13. A readable storage medium comprising, in combination,

the readable storage medium stores a computer program readable and executable by a computer, which when read by the computer, executes the information acquisition method according to any one of claims 1 to 6 or the information acquisition method according to claim 7 or 8.

14. An information acquisition system, comprising:

the information acquisition apparatus according to claim 9 and the information acquisition apparatus according to claim 10;

alternatively, the first and second electrodes may be,

an information acquisition apparatus according to claim 11 and an information acquisition apparatus according to claim 12.