CN116662534A

CN116662534A - Data content query method, device and storage medium

Info

Publication number: CN116662534A
Application number: CN202210156310.7A
Authority: CN
Inventors: 刘婷; 李良
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2022-02-21
Filing date: 2022-02-21
Publication date: 2023-08-29

Abstract

The application discloses a data content query method, a data content query device and a storage medium. Query information input by a target object is obtained; searching based on the query information to show a plurality of search results matched with the target object; and further, responding to the selection of the target object on the search result, displaying the data content corresponding to the search result in the target interface, and highlighting the key knowledge points in the data content corresponding to the search result. Therefore, a targeted data query process is realized, and the key knowledge points are adopted to query the data content, and the query basis of the search result is reflected through the display of the key knowledge points, so that the relevance of the content obtained by query is improved, the user can quickly acquire the query content, and the accuracy of the data content query is improved.

Description

Data content query method, device and storage medium

Technical Field

The present application relates to the field of computer technologies, and in particular, to a method and an apparatus for querying data content, and a storage medium.

Background

With the rapid development of internet technology, the requirements of people on data content are increasing. Further, the importance of querying and searching data content in the life of people is increasingly prominent.

Generally, the query process of data content matches the results through the query words of the user, matches the related results according to the dimensions of content relevance, authority, content quality and the like, and then displays part of the abstract on the result page for the user to know preliminarily.

However, the query terms input by the user may be generalized, so that the search results are generalized, and the user cannot quickly determine the associated search results, so that the data content of the query is not matched with the requirements, and the accuracy of the data content query is affected.

Disclosure of Invention

In view of the above, the application provides a data content query method, which can effectively improve the accuracy of data content query.

The first aspect of the present application provides a method for querying data content, which can be applied to a system or a program including a query function of data content in a terminal device, and specifically includes:

acquiring query information input by a target object;

content searching is conducted based on the query information so as to display a plurality of search results matched with the target object in a target interface, wherein each search result is configured with a corresponding key knowledge point for display, the search results are obtained by matching the key knowledge point with the query information, and the key knowledge points are obtained by information extraction based on data content corresponding to the search results;

And responding to the selection of the target object to the search result, displaying data content corresponding to the search result in the target interface, and highlighting the key knowledge points in the data content corresponding to the search result.

Optionally, in some possible implementations of the present application, the search result is a data content in the candidate content, and the method further includes:

determining a text start position and a text end position in the candidate content to obtain input information;

inputting the input information into a depth model to obtain the probability that the text start bit belongs to a knowledge point and the probability that the text end bit belongs to the knowledge point;

determining key knowledge points corresponding to the candidate content according to the probability that the text start bit belongs to the knowledge points and the probability that the text end bit belongs to the knowledge points;

and carrying out a content searching process corresponding to the query information based on the key knowledge points corresponding to the candidate content.

Optionally, in some possible implementations of the present application, the method further includes:

acquiring a preset sample;

determining a content title corresponding to the preset sample;

Performing sequence labeling on knowledge points in the preset sample based on the content title to obtain a training sample;

and training the depth model according to the training sample.

Optionally, in some possible implementations of the present application, the searching for content based on the query information to display a plurality of search results matching the target object in a target interface includes:

carrying out knowledge point matching based on the query information to determine candidate knowledge points;

obtaining an object tag corresponding to the target object;

inputting the object label into a recommendation model to obtain a recommendation knowledge point;

matching the recommended knowledge points with the candidate knowledge points to determine the key knowledge points;

and determining a plurality of search results matched with the target object according to the key knowledge points, and displaying the search results in the target interface.

acquiring a query record corresponding to the target object;

counting based on clicking operations of knowledge points in the query records to obtain clicking data corresponding to the target object;

Training the recommendation model based on the click data.

acquiring operation information corresponding to the target object in the target interface of the highlighted key knowledge point;

and if the operation information indicates to stop the operation, displaying an associated window containing associated content in the target interface, wherein the associated content is determined based on the key knowledge point.

Optionally, in some possible implementations of the present application, if the operation information indicates to stop the operation, displaying an association window including association content in the target interface includes:

if the operation information indicates to stop the operation, determining candidate associated content based on the key knowledge points;

acquiring the search quantity of the candidate associated content in a preset period;

ranking based on the search amount to determine the associated content;

the associated window containing the associated content is shown in the target interface.

A second aspect of the present application provides a data content query apparatus, including:

the acquisition unit is used for acquiring query information input by the target object;

The query unit is used for searching contents based on the query information so as to display a plurality of search results matched with the target object in a target interface, wherein each search result is configured with a corresponding key knowledge point for display, the search results are obtained by matching the key knowledge point with the query information, and the key knowledge points are obtained by extracting information based on data contents corresponding to the search results;

and the query unit is also used for responding to the selection of the target object on the search result, displaying the data content corresponding to the search result in the target interface and highlighting the key knowledge points in the data content corresponding to the search result.

Optionally, in some possible implementations of the present application, the search result is a data content in a candidate content, and the query unit is specifically configured to determine a text start bit and a text end bit in the candidate content, so as to obtain input information;

the query unit is specifically configured to input the input information into a depth model, so as to obtain a probability that the text start bit belongs to a knowledge point and a probability that the text end bit belongs to the knowledge point;

The query unit is specifically configured to determine a key knowledge point corresponding to the candidate content according to the probability that the text start bit belongs to the knowledge point and the probability that the text end bit belongs to the knowledge point;

the query unit is specifically configured to perform a content search process corresponding to the query information based on the key knowledge points corresponding to the candidate content.

Optionally, in some possible implementations of the present application, the query unit is specifically configured to obtain a preset sample;

the query unit is specifically configured to determine a content title corresponding to the preset sample;

the query unit is specifically configured to perform sequence labeling on knowledge points in the preset sample based on the content title, so as to obtain a training sample;

the query unit is specifically configured to train the depth model according to the training sample.

Optionally, in some possible implementations of the present application, the query unit is specifically configured to perform knowledge point matching based on the query information to determine candidate knowledge points;

the query unit is specifically configured to obtain an object tag corresponding to the target object;

the query unit is specifically configured to input the object tag into a recommendation model to obtain a recommendation knowledge point;

The query unit is specifically configured to match the recommended knowledge points with the candidate knowledge points to determine the key knowledge points;

the query unit is specifically configured to determine a plurality of search results matched with the target object according to the key knowledge points, and display the search results in the target interface.

Optionally, in some possible implementation manners of the present application, the query unit is specifically configured to obtain a query record corresponding to the target object;

the query unit is specifically configured to perform statistics based on click operations of knowledge points in the query record, so as to obtain click data corresponding to the target object;

the query unit is specifically configured to train the recommendation model based on the click data.

the query unit is specifically configured to obtain, in the target interface of the highlighted key knowledge point, operation information corresponding to the target object;

and the query unit is specifically configured to display an association window containing association content in the target interface if the operation information indicates to stop the operation, where the association content is determined based on the key knowledge point.

Optionally, in some possible implementations of the present application, the query unit is specifically configured to determine candidate associated content based on the key knowledge point if the operation information indicates to stop the operation;

the query unit is specifically configured to obtain a search amount of the candidate associated content in a preset period;

the query unit is specifically configured to sort based on the search amount to determine the associated content;

the query unit is specifically configured to display the association window containing the association content in the target interface.

A third aspect of the present application provides a computer apparatus comprising: a memory, a processor, and a bus system; the memory is used for storing program codes; the processor is configured to execute the query method of the data content according to the first aspect or any one of the first aspects according to an instruction in the program code.

A fourth aspect of the application provides a computer readable storage medium having instructions stored therein which, when run on a computer, cause the computer to perform the method of querying data content of the first aspect or any of the first aspects described above.

According to one aspect of the present application, there is provided a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The computer instructions are read from a computer-readable storage medium by a processor of a computer device, which executes the computer instructions, causing the computer device to perform the method of querying data content provided in the above-described first aspect or various alternative implementations of the first aspect.

From the above technical solutions, the embodiment of the present application has the following advantages:

query information input by a target object is obtained; then searching content based on the query information to display a plurality of search results matched with the target object in a target interface, wherein each search result is configured with a corresponding key knowledge point for display, the search result is obtained by matching the key knowledge point with the query information, and the key knowledge point is obtained by extracting information based on the data content corresponding to the search result; and further, responding to the selection of the target object on the search result, displaying the data content corresponding to the search result in the target interface, and highlighting the key knowledge points in the data content corresponding to the search result. Therefore, a targeted data query process is realized, and the key knowledge points are adopted to query the data content, and the query basis of the search result is reflected through the display of the key knowledge points, so that the relevance of the content obtained by query is improved, the user can quickly acquire the query content, and the accuracy of the data content query is improved.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present application, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.

FIG. 1 is a diagram of a network architecture in which a query system for data content operates;

FIG. 2 is a flow chart of a query of data content according to an embodiment of the present application;

FIG. 3 is a flowchart of a method for querying data content according to an embodiment of the present application;

fig. 4 is a schematic view of a scenario of a data content query method according to an embodiment of the present application;

fig. 5 is a schematic view of a scenario of another data content query method according to an embodiment of the present application;

FIG. 6 is a flowchart of another method for querying data content according to an embodiment of the present application;

FIG. 7 is a flowchart of another method for querying data content according to an embodiment of the present application;

fig. 8 is a schematic view of a scenario of another data content query method according to an embodiment of the present application;

FIG. 9 is a flowchart of another method for querying data content according to an embodiment of the present application;

FIG. 10 is a flowchart of another method for querying data content according to an embodiment of the present application;

fig. 11 is a schematic structural diagram of a query device for data content according to an embodiment of the present application;

fig. 12 is a schematic structural diagram of a terminal device according to an embodiment of the present application;

fig. 13 is a schematic structural diagram of a server according to an embodiment of the present application.

Detailed Description

The embodiment of the application provides a data content query method and a related device, which can be applied to a system or a program containing a data content query function in terminal equipment, and query information input by a target object is acquired; then searching content based on the query information to display a plurality of search results matched with the target object in a target interface, wherein each search result is configured with a corresponding key knowledge point for display, the search result is obtained by matching the key knowledge point with the query information, and the key knowledge point is obtained by extracting information based on the data content corresponding to the search result; and further, responding to the selection of the target object on the search result, displaying the data content corresponding to the search result in the target interface, and highlighting the key knowledge points in the data content corresponding to the search result. Therefore, a targeted data query process is realized, and the key knowledge points are adopted to query the data content, and the query basis of the search result is reflected through the display of the key knowledge points, so that the relevance of the content obtained by query is improved, the user can quickly acquire the query content, and the accuracy of the data content query is improved.

The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the application described herein may be implemented, for example, in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "includes" and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus.

First, some terms that may appear in the embodiments of the present application will be explained.

And (3) data marking: the data annotation is the process of annotating metadata such as text, video, images and the like, and the marked data trains a machine learning model for a user.

Key knowledge points: key knowledge points refer to a generalization of the core views of authors in articles. Such as: ketogenic weight-reducing method. An article may extract multiple knowledge points.

Text segment (Span): a "sentence" may be considered a particular "segment of text" of a continuous piece of text, typically one or more continuous word compositions, of an article or paragraph of equal length text.

Sequence labeling: from a given length of text, one or more "text segments" therein are marked manually or by means of a computer program.

Object representation: through carrying out multi-dimension depiction on a large amount of object behavior data for each user of the current service through means of machine learning, data mining and the like, common dimensions comprise: age, gender, academy, point of interest markers, etc.

Information extraction: and extracting the target fragment from the target text.

Inverted index: the web pages (articles) recorded by the search engine are stored according to the data structure of the inverted chain. An index is a special computer file format that can accelerate a computer program (search program) to obtain articles related to a query by a query entered by a user.

Semantic vector index: the semantics of the natural language text are expressed in a vector mode through a machine learning mode, and the vector is stored in a file system or a memory through a special data structure, wherein the data structure is mainly convenient for subsequent inquiry. The scene of the daily contact angle is 'face recognition', the main logic of the scene is to establish an index for vector representation of an image, the user face samples the image in real time to be converted into a vector, and the final task is to find the vector closest to the input vector 'distance' of the user face in the index.

Landing page: among the results returned by the search engine, the user clicks on one of the results and then enters a new web page, which is referred to as a "landing page".

Training set: machine "learning" typically requires the use of a certain scale of data to ultimately output a model with some ability, a process called a "training process" and the data used in the process for learning is called a "training set".

It should be understood that the method for querying the data content provided by the application can be applied to a system or a program containing a query function of the data content in the terminal device, for example, a search application, specifically, the query system of the data content can be operated in a network architecture shown in fig. 1, as shown in fig. 1, a network architecture diagram operated by the query system of the data content, as can be known from the figure, the query system of the data content can provide a query process of the data content with a plurality of information sources, namely, corresponding query information is issued to a server through a query operation at a terminal side, so that the server queries the corresponding data content and displays an interface at the terminal; it will be appreciated that various terminal devices are shown in fig. 1, the terminal devices may be computer devices, in an actual scenario, there may be more or less terminal devices participating in the process of querying the data content, and the specific number and types are not limited herein, and in addition, one server is shown in fig. 1, but in an actual scenario, there may also be participation of multiple servers, where the specific number of servers is determined by the actual scenario.

In this embodiment, the server may be an independent physical server, or may be a server cluster or a distributed system formed by a plurality of physical servers, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDNs, and basic cloud computing services such as big data and artificial intelligence platforms. The terminal may be, but is not limited to, a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart speaker, a smart watch, a smart voice interaction device, a smart home appliance, a vehicle-mounted terminal, and the like. The terminals and servers may be directly or indirectly connected by wired or wireless communication, and the terminals and servers may be connected to form a blockchain network, which is not limited herein.

It will be appreciated that the above described data content querying system may be operated on a personal mobile terminal, for example: the application can be used as a search application, can also be run on a server, and can also be used as a query which is run on third-party equipment to provide data content so as to obtain a query processing result of the data content of the information source; the specific data content query system may be in a program form, may also be operated as a system component in the device, and may also be used as a cloud service program, where the specific operation mode is determined by an actual scenario and is not limited herein.

In order to solve the above problems, the present application provides a data content query method, which is applied to a flow frame of data content query shown in fig. 2, as shown in fig. 2, and is a flow frame of data content query provided in an embodiment of the present application, a user performs knowledge point matching on a server through a query operation on a terminal, and further performs targeted screening according to the user, so as to determine a search result including knowledge point display.

It can be appreciated that, because the query terms of the user refer generally to text answers with more content are given, the reading cost is high, and the user may find out undesired results finally, so that the information acquisition efficiency is low. Therefore, the embodiment extracts key knowledge points for answering the user questions through the content in the article, matches personalized information of the user according to the extracted knowledge points, gives out the optimal knowledge and knowledge of the user, and can sort the knowledge points according to the current search amount to preferentially display popular knowledge.

It can be understood that the method provided by the application can be a program writing method, which can be used as a processing logic in a hardware system, and can also be used as a data content query device, and the processing logic can be realized in an integrated or external mode. As one implementation manner, the query device of the data content obtains query information input by the target object; then searching content based on the query information to display a plurality of search results matched with the target object in a target interface, wherein each search result is configured with a corresponding key knowledge point for display, the search result is obtained by matching the key knowledge point with the query information, and the key knowledge point is obtained by extracting information based on the data content corresponding to the search result; and further, responding to the selection of the target object on the search result, displaying the data content corresponding to the search result in the target interface, and highlighting the key knowledge points in the data content corresponding to the search result. Therefore, a targeted data query process is realized, and the key knowledge points are adopted to query the data content, and the query basis of the search result is reflected through the display of the key knowledge points, so that the relevance of the content obtained by query is improved, the user can quickly acquire the query content, and the accuracy of the data content query is improved.

With reference to fig. 3, fig. 3 is a flowchart of a data content query method provided in an embodiment of the present application, where the management method may be executed by a terminal or a server, and the embodiment of the present application at least includes the following steps:

301. and acquiring query information input by the target object.

In this embodiment, the target object may be a user, a terminal, or other functional entities that may perform query or search operations, which is not limited herein.

In some possible scenarios, the target object may input the query information through a keyboard, through voice, or through other somatosensory interaction modes, where the specific input mode depends on the actual scenario and is not limited herein.

Specifically, the query information may be a knowledge point extracted through the input information of the target object, or may be a combination of a plurality of knowledge points, and the efficiency of performing subsequent knowledge point matching may be improved through analysis of the query information.

302. Content searching is performed based on the query information to present a plurality of search results in the target interface that match the target object.

In this embodiment, each search result is configured with a corresponding key knowledge point for display, which is obtained by matching the search result with the query information through the key knowledge point, and the key knowledge point is obtained by extracting information from the data content corresponding to the search result, that is, the key knowledge point is obtained by automatically labeling or manually labeling the candidate content in the database in advance.

It should be appreciated that the search results may be in the form of articles, web pages, or other media content, and the following embodiments are described by way of example and not limitation.

Specifically, through configuration of key knowledge points, a query process in this embodiment is shown in fig. 4, and fig. 4 is a schematic scene diagram of a data content query method provided in the embodiment of the present application; firstly, a user inputs a query word for searching; then, a plurality of search results (result 1 to result N) are returned, and comprehensive sorting is performed; further users can first know the solutions contained in the articles according to the key knowledge points extracted by recognition, and can choose to click to enter a detail page to read the details (for example, the users prefer to choose the solutions 2 and 4, and can directly choose the results 2 and N to view the details), so that information acquisition is more efficient; in addition, the detail page can be accessed to read the detailed information, and a new search can be directly initiated through the detail page entry click to know the relevant content of the solution.

Therefore, through the configuration of the key knowledge points, the key viewpoints in the article can be identified, the key knowledge points can be extracted, and the key knowledge points are displayed in a structured mode before the user reads the content, so that the user can refer to the key knowledge points, the user knows the content explained in the article in advance, the user intuitively experiences the content, the reading cost is saved, and the information acquisition efficiency is improved.

303. And responding to the selection of the target object on the search result, displaying the data content corresponding to the search result in the target interface, and highlighting the key knowledge points in the data content corresponding to the search result.

In the embodiment, the key knowledge points are highlighted in the data content corresponding to the search result, so that the user can know the content explained in the article in advance, the reading cost is saved through visual experience, and the accuracy of the search result to the user is improved.

In one possible scenario, the above-mentioned query process is shown in fig. 5, and fig. 5 is a schematic view of a scenario of another query method for data content according to an embodiment of the present application; the figure shows how thin legs a user inputs a query term search in a target interface A1; so as to obtain a plurality of search results (result 1: what is blown and exploded leg-thinning method; result 2: fat non-uniformity, how leg-thinning can be successful; result 3: how leg-thinning is crazy in one month), and meanwhile, the lower right corner of each result shows the key knowledge point A2 of the content; so that the user knows that the result 2 is the lean leg through the correct walking gesture according to the extracted key knowledge points, and selects the content (the result 2) to click the detailed reading content. Further, the user enters the detail page to read the detailed information, and can click through the knowledge point A3 at the head of the detail page to initiate a new search to know the relevant content of the solution.

Furthermore, in order to highlight the relevance effect of the key knowledge points on the user, pushing of relevant information can be performed, namely, operation information corresponding to the target object is obtained in a target interface of the highlighted key knowledge points; and if the operation information indicates to stop the operation, displaying an associated window containing associated content in the target interface, wherein the associated content is determined based on the key knowledge points. Specifically, the associated content may be a problem focused by the user, and may be specifically represented by a search amount, that is, if the operation information indicates to stop the operation, candidate associated content is determined based on the key knowledge point; then obtaining the search quantity of the candidate associated content in a preset period; and sorting based on the search amount to determine associated content; and further displaying the associated window containing the associated content in the target interface. In one possible scenario, as shown in fig. 6, fig. 6 is a flowchart of another data content query method provided by an embodiment of the present application; that is, when the user slides down to read the content, the "knowledge point keyword" mentioned in the article performs highlighting display "correct walking" (highlighting display) when the first occurrence in the article, when the screen is stationary (operation information indicates stopping operation), the bottom of the screen slides up into the recommended elastic layer "how the correct walking gesture is forced" (associated window B1), the display is performed for 3s, and no click slides down to disappear. The recommended bullet layer matches the result with the highest searching amount by using a high amount of key knowledge points in the article, thereby being convenient for the user to know.

The above embodiment describes the related interface display process in the query process based on the key knowledge points, but for the configuration of the key knowledge points, the configuration process of the key knowledge points is described below, as shown in fig. 7, fig. 7 is a flowchart of another query method for data content provided by the embodiment of the present application; the figure shows the query flow at the user searching end, namely, the user can obtain the related text index by initiating the search, further recalling the matched knowledge points and corresponding articles according to the object portrait, specifically, calculating the indication points matched with the object (user) portrait from the article set related to the query, and sequencing the articles related to the knowledge points. After clicking the article, the user can browse the details of the article, and when sliding knowledge points in the text, the user can also highlight the knowledge points, and the user can inquire and recommend the knowledge points.

The process of article indexing is the extraction of articles configured with key knowledge points, namely, information extraction is performed by a machine learning mode (for example, a deep learning model BERT-MRC) based on key domains such as article titles, paragraphs, texts and the like, and the extracted Span is the knowledge point.

In addition, the knowledge points matched according to the object portrait recall and corresponding articles are recommended to the user through personalized knowledge points. When a user initiates a search, knowledge points associated with and personalized with the result-corresponding articles are returned in the search results. Personalization refers to recommending knowledge points for a user to match based on an object representation.

And recommending relevant queries based on knowledge points, namely recommending popular relevant queries for the user based on the knowledge points when the user slides to a 'knowledge point' area of the text in the landing page.

Specifically, the labeling process of the key knowledge points in the article indexing process can be performed through a depth model, namely, firstly determining a text start position and a text end position in candidate contents to obtain input information, wherein a search result is the data content in the candidate contents, model input can be represented as { article title, article text }, and Label is the start position and the end position of the knowledge points; then inputting the input information into a depth model to obtain the probability that the text start bit belongs to the knowledge point and the probability that the text end bit belongs to the knowledge point, wherein the knowledge point can be extracted by training one or more deep learning models; determining key knowledge points corresponding to candidate contents according to the probability that the text start bit belongs to the knowledge points and the probability that the text end bit belongs to the knowledge points; and then carrying out a content searching process corresponding to the query information based on the key knowledge points corresponding to the candidate content. For example, the model outputs the starting and ending positions of the knowledge point text in the text, specifically the probability P (i, j) that the position combination spans the text as the knowledge point, such as P (5, 18) >0.5, and the text with the text character position between 5 and 18 is represented as the knowledge point.

In addition, for the training process of the depth model, the model training set source is involved, so that the training set source is pretrained in a large scale, the training set scale required for extracting the knowledge points is smaller, the training set is expected to be 3-5 ten thousand (the order of magnitude is that the manual labeling can be achieved), and the model has high requirements on the data quality of the training set and can be carried out in a manual 'sequence labeling' mode. Firstly, acquiring a preset sample; then determining a content title corresponding to the preset sample; performing sequence labeling on knowledge points in a preset sample based on the content title to obtain a training sample; and further training the depth model according to the training samples.

The specific labeling scene is shown in fig. 8, and fig. 8 is a flowchart of another data content query method provided by the embodiment of the application; the question (article title) is shown: how to lose weight locally, so the knowledge points are manually marked from the text: "effective exercise", "liposuction operation", "frozen lipolysis".

In this embodiment, a Loss function (Loss) of the depth model may support Loss extracted from multiple knowledge points. Specifically, a general method of MRC model information extraction is to predict the start position and end position of Span, which corresponds to 2 n classifications, to predict the start position and end position among n characters, respectively. In this embodiment, there may be many knowledge points in the text, and even nesting (overlapping) is possible, so this method is not applicable. Based on this, 2 classifications can be employed: there are 2 prediction results for each character, indicating the probability that each character is a start position and an end position, i.e., whether it is "possible" to become a start position and whether it is "possible" to become an end position.

In addition, the depth model may be a single model, such as BERT, or a combination of multiple models, such as lstm+crf, BERT-BiLSTM-CRF, etc., with the configuration of a particular model depending on the actual scenario.

Next, a description will be given of user personalized knowledge point recommendation, i.e., a recommendation process based on step 302. I.e. when the user initiates a search, knowledge points associated with the articles corresponding to the results and personalized are returned in the search results. The individuation refers to recommending knowledge points matched with the object portrait for users based on the object portrait, so that thousands of people and thousands of faces are realized, namely, for the same query, different users show different knowledge points and articles.

Specifically, the implementation of the personalized recommendation process is shown in fig. 9, and fig. 9 is a schematic view of a scenario of another data content query method provided by the embodiment of the present application; the process of determining a plurality of search results matching a target object is shown by first performing knowledge point matching based on query information to determine candidate knowledge points; then obtaining an object label corresponding to the target object; inputting the object labels into a recommendation model to obtain recommendation knowledge points; then matching the recommended knowledge points with candidate knowledge points to determine key knowledge points; and then determining a plurality of search results matched with the target object according to the key knowledge points, and displaying the search results in the target interface.

Specifically, for the training process of the recommendation model, a query record corresponding to the target object can be obtained first, and specific query can be obtained through collaborative filtering, wide & Deep and the like; counting based on clicking operation of knowledge points in the query records to obtain clicking data corresponding to the target object; the recommendation model is then trained based on the click data.

Specifically, according to the articles related to the query input by the user, the knowledge points (corresponding to a group of articles) matched with the object portrait are sequenced;

in one possible scenario, a 2-phase online scheme may be employed due to the lack of a large-scale training set at an early stage. Stage 1: and in the cold start online stage, collecting user clicks as a training set in the stage 2. Knowledge point recommendations at this stage are not thousands of people and thousands of faces, but rather mainly employ a strategy of random exposure. And the 2 nd stage is the online stage of the recommended strategy. Based on the user click log collected in the cold start stage, click data such as the knowledge points of the user and the click can be obtained, and based on the mining algorithm and the strategy, knowledge point data of interest of the user can be obtained and used as a training set of the recommendation model, so that the quality of training samples of the recommendation model is improved, and the accuracy of knowledge point determination is improved.

In addition, a process is recommended for knowledge point based queries. I.e. as in fig. 6 the user slides in the landing page to the "knowledge point" area of the text, the popular related queries (association window B1) are recommended to the user based on this knowledge point.

Specifically, the determining of the associated content may also be performed through an associated recommendation model, where the implementation process is shown in fig. 10, and fig. 10 is a flowchart of another data content query method provided in the embodiment of the present application; specifically, knowledge points (text snippets) are input to the recommendation model and the output is articles (recalled from historically occurring queries). For the use of the associated recommendation model, firstly, an inverted index and a semantic vector index are established through historical queries (Query) in a search engine. And performing inverted index, namely performing word segmentation, word importance calculation and the like on the Query, and establishing the inverted index. Semantic vector indexing is then performed. The query is vectorized using a semantic representation model of the search engine, converting the search problem into a neighborhood query problem in space (e.g., using HNSW, etc.). And further carrying out recall and sequencing based on the index in the last step.

Specifically, for the recall process, combining the results of the inverted index and the semantic vector index recall as candidate sets; for the ranking process, i.e., one or more rounds of ranking the recalled candidate set, the ranking model aspect may be trained using manual labeling and clicking on the data results.

Through the configuration of the associated recommendation model, the user can directly click to further know the related content of the knowledge point, and the interaction frequency of the user and the data content is improved.

As can be seen from the above embodiments, query information input by a target object is obtained; then searching content based on the query information to display a plurality of search results matched with the target object in a target interface, wherein each search result is configured with a corresponding key knowledge point for display, the search result is obtained by matching the key knowledge point with the query information, and the key knowledge point is obtained by extracting information based on the data content corresponding to the search result; and further, responding to the selection of the target object on the search result, displaying the data content corresponding to the search result in the target interface, and highlighting the key knowledge points in the data content corresponding to the search result. Therefore, a targeted data query process is realized, and the key knowledge points are adopted to query the data content, and the query basis of the search result is reflected through the display of the key knowledge points, so that the relevance of the content obtained by query is improved, the user can quickly acquire the query content, and the accuracy of the data content query is improved.

In order to better implement the above-described aspects of the embodiments of the present application, the following provides related apparatuses for implementing the above-described aspects. Referring to fig. 11, fig. 11 is a schematic structural diagram of a data content query device according to an embodiment of the present application, and a data content query device 1100 includes:

an obtaining unit 1101, configured to obtain query information input by a target object;

the query unit 1102 is configured to perform content search based on the query information, so as to display a plurality of search results matched with the target object in a target interface, where each search result is configured with a corresponding key knowledge point for display, the search result is obtained by matching the key knowledge point with the query information, and the key knowledge point is obtained by extracting information based on data content corresponding to the search result;

the query unit 1102 is further configured to, in response to selection of the search result by the target object, display data content corresponding to the search result in the target interface, and highlight the key knowledge point in the data content corresponding to the search result.

Optionally, in some possible implementations of the present application, the search result is a data content in a candidate content, and the query unit 1102 is specifically configured to determine a text start bit and a text end bit in the candidate content, so as to obtain input information;

The query unit 1102 is specifically configured to input the input information into a depth model, so as to obtain a probability that the text start bit belongs to a knowledge point and a probability that the text end bit belongs to the knowledge point;

the query unit 1102 is specifically configured to determine a key knowledge point corresponding to the candidate content according to the probability that the text start bit belongs to the knowledge point and the probability that the text end bit belongs to the knowledge point;

the query unit 1102 is specifically configured to perform a content search process corresponding to the query information based on the key knowledge points corresponding to the candidate content.

Optionally, in some possible implementations of the present application, the query unit 1102 is specifically configured to obtain a preset sample;

the query unit 1102 is specifically configured to determine a content title corresponding to the preset sample;

the query unit 1102 is specifically configured to perform sequence labeling on knowledge points in the preset sample based on the content title, so as to obtain a training sample;

the query unit 1102 is specifically configured to train the depth model according to the training sample.

Optionally, in some possible implementations of the present application, the query unit 1102 is specifically configured to perform knowledge point matching based on the query information to determine candidate knowledge points;

The query unit 1102 is specifically configured to obtain an object tag corresponding to the target object;

the query unit 1102 is specifically configured to input the object tag into a recommendation model to obtain a recommendation knowledge point;

the query unit 1102 is specifically configured to determine the key knowledge points by matching the recommended knowledge points with the candidate knowledge points;

the query unit 1102 is specifically configured to determine, according to the key knowledge points, a plurality of search results that match the target object, and display the search results in the target interface.

Optionally, in some possible implementations of the present application, the query unit 1102 is specifically configured to obtain a query record corresponding to the target object;

the query unit 1102 is specifically configured to perform statistics based on click operations of knowledge points in the query record, so as to obtain click data corresponding to the target object;

the query unit 1102 is specifically configured to train the recommendation model based on the click data.

the query unit 1102 is specifically configured to obtain, in the target interface of the highlighted key knowledge point, operation information corresponding to the target object;

The query unit 1102 is specifically configured to display, in the target interface, an association window including association content if the operation information indicates to stop the operation, where the association content is determined based on the key knowledge point.

Optionally, in some possible implementations of the present application, the query unit 1102 is specifically configured to determine candidate associated content based on the key knowledge point if the operation information indicates to stop the operation;

the query unit 1102 is specifically configured to obtain a search amount of the candidate associated content in a preset period;

the query unit 1102 is specifically configured to sort based on the search amount to determine the associated content;

the query unit 1102 is specifically configured to display the association window containing the association content in the target interface.

The embodiment of the present application further provides a terminal device, as shown in fig. 12, which is a schematic structural diagram of another terminal device provided in the embodiment of the present application, for convenience of explanation, only the portion related to the embodiment of the present application is shown, and specific technical details are not disclosed, please refer to the method portion of the embodiment of the present application. The terminal may be any terminal device including a mobile phone, a tablet computer, a personal digital assistant (personal digital assistant, PDA), a point of sale (POS), a vehicle-mounted computer, and the like, taking the terminal as an example of the mobile phone:

fig. 12 is a block diagram showing a part of the structure of a mobile phone related to a terminal provided by an embodiment of the present application. Referring to fig. 12, the mobile phone includes: radio Frequency (RF) circuitry 1210, memory 1220, input unit 1230, display unit 1240, sensor 1250, audio circuitry 1260, wireless fidelity (wireless fidelity, wiFi) module 1270, processor 1280, and power supply 1290. Those skilled in the art will appreciate that the handset configuration shown in fig. 12 is not limiting of the handset and may include more or fewer components than shown, or may combine certain components, or a different arrangement of components.

The following describes the components of the mobile phone in detail with reference to fig. 12:

the RF circuit 1210 may be used for receiving and transmitting signals during a message or a call, and in particular, after receiving downlink information of a base station, the signal is processed by the processor 1280; in addition, the data of the design uplink is sent to the base station. Typically, RF circuitry 1210 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier (low noise amplifier, LNA), a duplexer, and the like. In addition, RF circuitry 1210 may also communicate with networks and other devices through wireless communication. The wireless communications may use any communication standard or protocol including, but not limited to, global system for mobile communications (global system of mobile communication, GSM), general packet radio service (general packet radio service, GPRS), code division multiple access (code division multiple access, CDMA), wideband code division multiple access (wideband code division multiple access, WCDMA), long term evolution (long term evolution, LTE), email, short message service (short messaging service, SMS), and the like.

Memory 1220 may be used to store software programs and modules, and processor 1280 may perform various functional applications and data processing for the cellular phone by executing the software programs and modules stored in memory 1220. The memory 1220 may mainly include a storage program area that may store an operating system, application programs required for at least one function (such as a sound playing function, an image playing function, etc.), and a storage data area; the storage data area may store data (such as audio data, phonebook, etc.) created according to the use of the handset, etc. In addition, memory 1220 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage device.

The input unit 1230 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function control of the mobile phone. In particular, the input unit 1230 may include a touch panel 1231 and other input devices 1232. The touch panel 1231, also referred to as a touch screen, may collect touch operations thereon or thereabout (e.g., operations of a user using any suitable object or accessory such as a finger, a stylus, etc. on the touch panel 1231 or thereabout, and spaced touch operations within a certain range on the touch panel 1231) and drive the corresponding connection device according to a predetermined program. Alternatively, the touch panel 1231 may include two parts, a touch detection device and a touch controller. The touch detection device detects the touch azimuth of a user, detects a signal brought by touch operation and transmits the signal to the touch controller; the touch controller receives touch information from the touch detection device and converts it into touch point coordinates, which are then sent to the processor 1280, and can receive commands from the processor 1280 and execute them. In addition, the touch panel 1231 may be implemented in various types such as resistive, capacitive, infrared, and surface acoustic wave. The input unit 1230 may include other input devices 1232 in addition to the touch panel 1231. In particular, other input devices 1232 may include, but are not limited to, one or more of a physical keyboard, function keys (e.g., volume control keys, switch keys, etc.), a trackball, mouse, joystick, etc.

The display unit 1240 may be used to display information input by a user or information provided to the user and various menus of the mobile phone. The display unit 1240 may include a display panel 1241, and alternatively, the display panel 1241 may be configured in the form of a liquid crystal display (liquid crystal display, LCD), an organic light-emitting diode (OLED), or the like. Further, the touch panel 1231 may overlay the display panel 1241, and when the touch panel 1231 detects a touch operation thereon or nearby, the touch operation is transmitted to the processor 1280 to determine the type of touch event, and then the processor 1280 provides a corresponding visual output on the display panel 1241 according to the type of touch event. Although in fig. 12, the touch panel 1231 and the display panel 1241 are two separate components to implement the input and input functions of the mobile phone, in some embodiments, the touch panel 1231 may be integrated with the display panel 1241 to implement the input and output functions of the mobile phone.

The handset can also include at least one sensor 1250, such as a light sensor, a motion sensor, and other sensors. Specifically, the light sensor may include an ambient light sensor and a proximity sensor, wherein the ambient light sensor may adjust the brightness of the display panel 1241 according to the brightness of ambient light, and the proximity sensor may turn off the display panel 1241 and/or the backlight when the mobile phone moves to the ear. As one of the motion sensors, the accelerometer sensor can detect the acceleration in all directions (generally three axes), and can detect the gravity and direction when stationary, and can be used for applications of recognizing the gesture of a mobile phone (such as horizontal and vertical screen switching, related games, magnetometer gesture calibration), vibration recognition related functions (such as pedometer and knocking), and the like; other sensors such as gyroscopes, barometers, hygrometers, thermometers, infrared sensors, etc. that may also be configured with the handset are not described in detail herein.

Audio circuitry 1260, speaker 1261, microphone 1262 may provide an audio interface between the user and the handset. Audio circuit 1260 may transmit the received electrical signal after audio data conversion to speaker 1261, where the electrical signal is converted to a sound signal by speaker 1261 for output; on the other hand, microphone 1262 converts the collected sound signals into electrical signals, which are received by audio circuit 1260 and converted into audio data, which are processed by audio data output processor 1280 for transmission to, for example, another cell phone via RF circuit 1210, or which are output to memory 1220 for further processing.

WiFi belongs to a short-distance wireless transmission technology, and a mobile phone can help a user to send and receive emails, browse webpages, access streaming media and the like through a WiFi module 1270, so that wireless broadband Internet access is provided for the user. Although fig. 12 shows the WiFi module 1270, it is understood that it does not belong to the necessary constitution of the mobile phone, and can be omitted entirely as required within the scope of not changing the essence of the invention.

Processor 1280 is a control center of the handset, connects various parts of the entire handset using various interfaces and lines, and performs various functions and processes of the handset by running or executing software programs and/or modules stored in memory 1220, and invoking data stored in memory 1220, thereby performing overall monitoring of the handset. In the alternative, processor 1280 may include one or more processing units; alternatively, the processor 1280 may integrate an application processor and a modem processor, wherein the application processor primarily processes operating systems, user interfaces, application programs, etc., and the modem processor primarily processes wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 1280.

The handset further includes a power supply 1290 (e.g., a battery) for powering the various components, optionally in logical communication with the processor 1280 through a power management system so as to perform charge, discharge, and power management functions via the power management system.

Although not shown, the mobile phone may further include a camera, a bluetooth module, etc., which will not be described herein.

In an embodiment of the present application, the processor 1280 included in the terminal further has a function of performing each step of the page processing method as described above.

Referring to fig. 13, fig. 13 is a schematic structural diagram of a server according to an embodiment of the present application, where the server 1300 may have a relatively large difference due to different configurations or performances, and may include one or more central processing units (central processing units, CPU) 1322 (e.g., one or more processors) and a memory 1332, and one or more storage media 1330 (e.g., one or more mass storage devices) storing application programs 1342 or data 1344. Wherein the memory 1332 and storage medium 1330 may be transitory or persistent. The program stored on the storage medium 1330 may include one or more modules (not shown), each of which may include a series of instruction operations on a server. Further, the central processor 1322 may be configured to communicate with the storage medium 1330, and execute a series of instruction operations in the storage medium 1330 on the server 1300.

The server 1300 may also include one or more power supplies 1326, one or more wired or wireless network interfaces 1350, one or more input/output interfaces 1358, and/or one or more operating systems 1341, such as Windows server (tm), mac OS XTM, unixTM, linuxTM, freeBSDTM, and so forth.

The steps performed by the management apparatus in the above-described embodiments may be based on the server structure shown in fig. 13.

In an embodiment of the present application, there is further provided a computer readable storage medium having stored therein query instructions for data content, which when executed on a computer, cause the computer to perform the steps performed by the query apparatus for data content in the method described in the embodiment shown in fig. 3 to 10.

There is also provided in an embodiment of the application a computer program product comprising query instructions for data content, which when run on a computer causes the computer to perform the steps performed by the query means for data content in the method described in the embodiment of figures 3 to 10 described above.

The embodiment of the application also provides a data content query system, which can comprise a data content query device in the embodiment shown in fig. 11, or a terminal device in the embodiment shown in fig. 12, or a server shown in fig. 13.

It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.

In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.

The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.

The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on this understanding, the technical solution of the present application may be embodied essentially or partly in the form of a software product, or all or part of the technical solution, which is stored in a storage medium, and includes several instructions for causing a computer device (which may be a personal computer, a query device for data content, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (random access memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.

The above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for querying data content, comprising:

acquiring query information input by a target object;

2. The method of claim 1, wherein the search result is a data content in a candidate content, the method further comprising:

3. The method according to claim 2, wherein the method further comprises:

acquiring a preset sample;

determining a content title corresponding to the preset sample;

and training the depth model according to the training sample.

4. The method of claim 1, wherein the performing a content search based on the query information to present a plurality of search results in a target interface that match the target object comprises:

obtaining an object tag corresponding to the target object;

5. The method according to claim 4, wherein the method further comprises:

acquiring a query record corresponding to the target object;

training the recommendation model based on the click data.

6. The method according to claim 1, wherein the method further comprises:

7. The method according to claim 6, wherein if the operation information indicates to stop the operation, displaying an associated window containing associated content in the target interface includes:

ranking based on the search amount to determine the associated content;

8. A data content querying device, comprising:

9. A computer device, the computer device comprising a processor and a memory:

the memory is used for storing program codes; the processor is configured to execute the method of querying data content according to any of claims 1 to 7 according to instructions in the program code.

10. A computer program product comprising computer programs/instructions stored on a computer readable storage medium, characterized in that the computer programs/instructions in the computer readable storage medium, when executed by a processor, implement the steps of the data content querying method according to any of the preceding claims 1 to 7.