JP6732938B2 - Information retrieval method and device - Google Patents

Description

This application claims the priority of Chinese Patent Application No. 2016102140644.0 filed on April 7, 2016, the entire contents of which are incorporated herein by reference.

The present application relates to the technical field of computers, and more specifically to the technical field of search, and more particularly to an information search method and apparatus.

2. Description of the Related Art Currently, the conventional information search technology normally searches a web page that includes content related to a search term by a search term input by a user, and extracts a summary of content related to the search term on the web page. Then, the summary is displayed in the search result.

However, the content of the search result displayed using the conventional technique is relatively single, and generally, the content requested by the user cannot be displayed.

The present application is intended to provide an improved information retrieval method and apparatus to solve the technical problems mentioned in the background art section.

As a first aspect, the embodiment of the present application provides an information search method. The information search method includes a step of receiving a search request including a search term input by a user, acquiring user information of the user, and a pre-trained classification model based on the search term and the user information. comprising the steps of: obtaining a search request of the user via the search request, and knowledge entity, and at least one request related to the knowledge entity, the steps from a previously set of stored knowledge entities , Obtaining at least one attribute information of the knowledge entity, wherein the at least one attribute information and the at least one request have a one-to-one correspondence, and the step of obtaining the obtained attribute information in one search result. Integrating and adding to the search results page.

In some embodiments, the step of obtaining the user's search request through a pre-trained classification model based on the search term and the user information comprises pre-determining the search term and the user information based on the search term and the user information. Obtaining said knowledge entity via a trained knowledge entity classification model, and said at least one request via a pre-trained requirement classification model based on said search term, said user information and said knowledge entity. And a step of acquiring.

In some embodiments, the method uses a multi- pattern matching algorithm after receiving the search request , based on a correspondence between a predetermined matching result and a first knowledge entity and a first request, Obtaining a first knowledge entity matching the search term and a first request, and obtaining the knowledge entity via a pre-trained knowledge entity classification model based on the search term and the user information. Includes obtaining the knowledge entity via a pre-trained knowledge entity classification model based on the search term, the user information, the first knowledge entity and the first request.

In some embodiments, obtaining the at least one request via a pre-trained request classification model based on the search term, the user information, and the knowledge entity includes the search term, the user information. , Obtaining the at least one request via a pre-trained request classification model based on the knowledge entity, the initial knowledge entity and the initial request.

In some embodiments, the method further comprises, after receiving a search request , obtaining an entity word and a request word in the search term via a named entity extraction algorithm based on the search term. , Obtaining the knowledge entity via a pre-trained knowledge entity classification model based on the search term, the user information, the first knowledge entity and the first request, the search term, the user information. , The first knowledge entity, the first request, the word of the entity, and obtaining the knowledge entity via a pretrained knowledge entity classification model based on the words of the request.

In some embodiments, obtaining the at least one request via a pre-trained request classification model based on the search term, the user information, and the knowledge entity includes the search term, the user information. , Said knowledge entity, said first knowledge entity, said first requirement, said entity's word and said requirement's word, and obtaining said at least one requirement via a pre-trained requirement classification model. ..

In some embodiments, the acquired attribute information includes at least one of image information and text information.

As a second aspect, this embodiment provides an information search device. The apparatus acquires a search request receiving unit configured to receive a search request including a search term input by a user, the user information of the user, and based on the search term and the user information, a search request obtaining unit constructed to obtain a search request of the user via the trained classification model, the search request, and knowledge entities, at least one request and associated with the knowledge entity A search request acquisition unit comprising: an attribute information acquisition unit constructed to acquire at least one attribute information of the knowledge entity from a pre-stored set of knowledge entities, wherein the at least one attribute information and the at least one attribute information The at least one request includes a one-to-one corresponding attribute information acquisition unit, and a page generation unit configured to integrate the acquired attribute information into one search result and add the search result page.

In some embodiments, the search request acquisition unit is configured to acquire the knowledge entity via a pre-trained knowledge entity classification model based on the search term and the user information. A sub-unit, and a request acquisition sub-unit configured to acquire the at least one request via a pre-trained request classification model based on the search term, the user information and the knowledge entity.

In some embodiments, the apparatus uses a multi- pattern matching algorithm after receiving the search request , based on a predetermined matching result and a correspondence between the first knowledge entity and the first request. Further comprising a multi- pattern matching unit configured to obtain a first knowledge entity matching the first request and a first request, the knowledge entity obtaining sub-unit comprising the search term, the user information, the first knowledge entity and the first knowledge entity. Further constructed to obtain said knowledge entities via a pre-trained knowledge entity classification model based on the initial request.

In some embodiments, the request acquisition subunit is configured to perform a pre-trained request classification model based on the search term, the user information, the knowledge entity, the first knowledge entity and the first request. Further constructed to obtain the at least one request.

In some embodiments, the apparatus is configured to obtain the entity word and the requested word in the search term via a named entity extraction algorithm based on the search term after receiving a search request. Further including a named entity extraction unit, wherein the knowledge entity acquisition sub-unit is based on the search term, the user information, the first knowledge entity, the first request, the word of the entity and the word of the request in advance. It is further constructed to obtain said knowledge entities via a trained knowledge entity classification model.

In some embodiments, the request acquisition subunit is based on the search term, the user information, the knowledge entity, the first knowledge entity, the first request, the word of the entity and the word of the request, It is further constructed to obtain the at least one requirement via a pre-trained requirement classification model.

In some embodiments, the attribute information acquired by the attribute information acquisition unit includes at least one of image information and character information.

The information retrieval method and apparatus provided in the present application uses a pre-trained classification model to obtain a knowledge entity in a user's search request and at least one request based on a search term and user information, At least one attribute information of the knowledge entity corresponding to the request on a one-to-one basis is acquired from a previously stored knowledge entity information set, and the acquired attribute information is integrated into one search result and added to the search result page. As a result, the content requested by the user can be displayed, and the display content of the search results can be enriched.

Other features, objects and advantages of the present application will become more apparent by reading and referencing the following detailed description of non-limiting examples according to the drawings.
1 is a diagram of an example system architecture to which the present application is applicable. 3 is a flowchart of an embodiment of an information search method according to the present application. FIG. 3 is an exemplary schematic diagram of an applied scene of an information search method according to the present application. 9 is a flowchart of another embodiment of the information search method according to the present application. 1 is a schematic diagram of a structure of an embodiment of an information search device according to the present application. 1 is a schematic diagram of the structure of a computer system of a server suitable for implementing the embodiments of the present application.

Hereinafter, the present application will be described in detail with reference to the drawings and embodiments. It is understood that the specific examples described herein are used only to interpret related inventions and are not limiting to the inventions. It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings.

Note that the embodiments and the features of the embodiments of the present application can be combined with each other as long as no contradiction occurs. Hereinafter, the present application will be described in detail with reference to the drawings together with the embodiments.

FIG. 1 illustrates an exemplary system architecture 100 to which an information retrieval method and information retrieval device embodiment of the present application may be applied.

As shown in FIG. 1, the system architecture 100 can include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used as a medium that provides a communication link between the terminal devices 101, 102, 103 and the server 105. Network 104 can include various connection types such as, for example, wired communication links, wireless communication links, or fiber optic cables.

A user can use the terminal devices 101, 102, 103 to interact with the server 105 via the network 104 to send and receive messages and the like. Various client applications such as a browser application, a search type application, and a shopping type application can be installed on the terminal devices 101, 102 and 103.

The terminal devices 101, 102, and 103 may be various electronic devices that support browser applications and search-type applications, and include smartphones, tablet PCs, laptop computers, desktop computers, and the like. Not limited.

The server 105 may be a server that provides various services, and may be, for example, a database server or a cloud server that provides support for browser applications on the terminal devices 101, 102, 103, search type applications, and the like. Can be The server can analyze the received data, perform a process such as a search, and feed back a process result (for example, a search result) to the terminal device.

The information retrieval method provided in the embodiments of the present application is generally executed by the server 105. In response to this, the information search device is generally installed in the server 105.

It should be understood that the numbers of terminals, networks and servers in FIG. 1 are merely schematic. Any number of terminals, networks, and servers may be included as desired.

Continuing to refer to FIG. 2, FIG. 2 shows a flow 200 of one embodiment of the information retrieval method according to the present application.

As shown in FIG. 2, the information search method of this embodiment includes the following steps.

In step 201, a search request is received.

Here, the search request includes the search term input by the user.

In the present embodiment, the electronic device (for example, the server shown in FIG. 1) on which the information search method is operated is searched from the terminal (for example, the terminal device shown in FIG. 1) by a wired or wireless method. The request can be received. Here, the search term may be text entered by a user in a text search box in a browser search page or a search type application.

In step 202, the user information of the user is acquired, and the search request of the user is acquired through a pretrained classification model based on the search term and the user information. Here, the search request includes a knowledge entity (Intellectual Entities), it may include at least one request related to the knowledge entities.

In the present embodiment, the electronic device can first obtain the user information of the user from the cookie information of the terminal, and can also obtain the user information of the user from the user image data that is constructed in advance. Here, the user information may include one or more of information such as historical search history, sex, age, occupation, and hobby, but is not limited thereto. Next, the user information obtained by the search term is input to a pre-trained classification model (for example, a logistic regression model), and the probability corresponding to each knowledge entity is obtained through the classification algorithm (for example, a logistic regression algorithm). Then, the knowledge entity having the highest probability of being corresponded as the knowledge entity in the search request is taken, and at least one request related to the knowledge entity in the search request is acquired according to a predetermined request related to each knowledge entity. To do. Here, the knowledge entity may be an object corresponding to a knowledge point/proper noun (eg, “Jiuzhaigou”, “arthritis”). The predetermined requirements associated with each of the above knowledge entities may be manually preset based on domain knowledge, or may be obtained through a method of machine learning. For example, a request related to the knowledge entity "arthritis" may include "treatment", "price inquiry", "ok".

The classification model may be acquired by learning and training a large amount of training data including entity annotations. Here, the training data may include a search word, user information, a knowledge entity, and a comment, where the comment is for displaying whether the search word is related to the knowledge entity of the training data. is there. The training data can be collected through the content of the page that the user clicked on the search result and entered and the search word used for the current search. For example, if it is assumed that the page that the user has clicked on by clicking on any one search result is related to “Jiuzhaigou”, one training data can be generated, and the search word of the training data can be generated. Is a search word used by the user, the knowledge entity is “Jiuzhaigou”, and the comment is 1.

In step 203, at least one attribute information of the knowledge entity is acquired in the pre-stored set of knowledge entities.

Here, the at least one attribute information and the at least one request have a one-to-one correspondence.

In this embodiment, the set of knowledge entities includes a plurality of attribute information of each knowledge entity, and may include attribute information such as capture, introduction, history, and travel course of the knowledge entity “Jiuzhaigou”. .. The electronic device queries the knowledge entity information matched to the knowledge entity in the search request obtained in step 202 from the set of knowledge entities, and then from the knowledge entity information, at least one of the search requests. At least one attribute information corresponding to the request can be acquired.

Here, the set of knowledge entities can be obtained by crawling already edited structural information from a third party site (eg, encyclopedia type site, medical type site). For example, in the knowledge entity "facial paralysis", attribute information such as introduction, symptom, etiology can be obtained by crawling information from a page related to facial paralysis on a site of a predetermined medical type.

In some selectable embodiments of this example, the acquired attribute information may include at least one of image information and character information. As a result, the display content of the search result can be further enriched.

In step 204, the acquired attribute information is integrated into one search result and added to the search result page.

In this embodiment, the electronic device combines at least one piece of attribute information into one search result and adds the search result to the search result page so that the terminal can display the search result including a plurality of pieces of attribute information. You can

In some selectable embodiments of this example, step 202 comprises obtaining the knowledge entities via a pre-trained knowledge entity classification model based on the search terms and the user information; The method may include obtaining the at least one request via a pre-trained request classification model based on a search term, the user information and the knowledge entity.

Here, the electronic device inputs the search term and the acquired user information into a pre-trained knowledge entity classification model, uses a classification algorithm to acquire the probability corresponding to each knowledge entity, and performs the search. Take the knowledge entity with the highest probability of corresponding as the requesting knowledge entity. Here, the training method of the knowledge entity classification model may refer to the training method of the classification model in step 202, and a duplicated description thereof will be omitted here. Then, the electronic device inputs the search term, the user information, and the knowledge entity in the search request into a pre-trained request classification model to obtain a probability corresponding to each request, and to obtain a probability corresponding to the request. Thus, a predetermined amount of requests can be sequentially selected in descending order as at least one of the search requests. Here, the requirement classification model may be acquired by learning and training a large amount of training data including requirement comments. Here, the training data may include information such as a search word, user information, a knowledge entity, a request, and a comment, where the comment indicates whether the search word is related to the knowledge entity and the request of the training data. Is for displaying. The training data can be collected through the content of the page that the user clicked on the search result and entered and the search word used for the current search. For example, if it is assumed that the page that the user has clicked on by clicking on any one search result is related to the travel strategy of "Jiuzhaigou," one training data can be generated and the training data can be generated. Is a search term used by the user, the knowledge entity is “Jiuzhaigou”, the request is “travel strategy”, and the comment is 1.

In this embodiment, the at least one request related to the knowledge entity in the acquired search request of the user is more accurate, so that the content requested by the user can be displayed more accurately.

Hereinafter, referring to FIG. 3, FIG. 3 shows an exemplary schematic diagram of one application scene of the information retrieval method of the present embodiment. In the applied scene of FIG. 3, the user first inputs the search word “facial paralysis” in the search input window and clicks the search button. Subsequently, the server receives the search request, acquires the search phrase “facial paralysis” in the search request, and uses the information search method provided in the present embodiment to identify the knowledge entity “facial paralysis” as knowledge. The user's search request such as “pathology”, “introduction”, and “symptom” related to the entity “facial paralysis” is acquired. Then, the attribute information corresponding to “pathology”, “introduction”, and “symptom” of “facial paralysis” in the set of knowledge entities is obtained one by one, and these attribute information are combined into one search result, and the search result Add to page. Then, if the search result page is transmitted to the terminal, as shown in FIG. 3, the image and text information of the etiology, introduction, and symptom regarding “facial paralysis” are displayed on the interface of the terminal.

The information search method provided in this embodiment uses a pre-trained classification model based on a search term and user information to obtain a knowledge entity and at least one request in a search request of a user, Acquiring at least one attribute information of the knowledge entity corresponding to the request one-to-one in the stored set of knowledge entities, integrating the acquired attribute information into one search result, and adding it to the search result page. Thus, the content requested by the user can be displayed, and the display content of the search result can be enriched.

Continuing to refer to FIG. 4, FIG. 4 shows a flow 400 of another embodiment of the information retrieval method according to the present application.

As shown in FIG. 4, the information retrieval method of this embodiment includes the following steps.

In step 401, a search request is received.

Here, the search request includes the search term input by the user.

In the present exemplary embodiment, the specific processing of step 401 may be referred to the related description of step 201 in the corresponding exemplary embodiment of FIG. 2, and duplicate description thereof will be omitted.

In step 402, a first knowledge entity and a first request that match the search term are obtained based on a predetermined matching result using a multi- pattern matching algorithm and a correspondence relationship between the first knowledge entity and the first request. ..

In this embodiment, the multi-pattern matching algorithm (Multi-pattern matching algorithm) can be an algorithm for matching such as through regular expressions or suffix tree. The electronic device uses a multi- pattern matching algorithm to obtain a mode string (expression) that matches the search term as a matching result, and based on the predetermined matching result and the correspondence between the first knowledge entity and the first request. , The first knowledge entity and the first request that match the above search terms can be obtained. Here, the predetermined matching result and the correspondence between the first knowledge entity and the first request may have been manually preset based on the domain knowledge, and may have been obtained through the method of machine learning. ..

For example, taking matching using a regular expression as an example, when the search term is “is the Great Wall of Beijing fun?”, the matched regular expression is “Beijing. How is it?)”. Assuming that the given first knowledge entity corresponding to the formula is “Beijing Travel” and the first requests are “Introduction” and “Cheat”, the search term “Great Wall of Beijing” It can be obtained that the first knowledge entity that is matched to "is it fun" is "Travel in Beijing" and the first requests are "Introduction" and "Cheat".

In step 403, the user information of the user is obtained and the user's user information is acquired using a pre-trained knowledge entity classification model based on the search term, the user information, the first knowledge entity and the first request. Get the knowledge entity in the search request.

In the present embodiment, the specific processing of acquiring the user information of the user can refer to the related description of step 202 in the corresponding embodiment of FIG. 2, and the duplicated description thereof will be omitted. To do. The electronic device inputs the search term, the user information, the first knowledge entity and the first request into a pre-trained knowledge entity classification model before using the classification algorithm before acquiring the user information. Then, the probability corresponding to each knowledge entity is acquired, and the knowledge entity having the highest probability of corresponding as the knowledge entity in the user's search request can be taken.

Here, the knowledge entity classification model according to the present embodiment may be acquired by learning and training a large amount of training data including entity annotations. Here, the training data may include information such as a search word, user information, a first knowledge entity, a first request, a knowledge entity, and a comment, where a comment is a knowledge entity whose search word is the training data. It is for displaying whether or not it is related to.

In step 404, the at least one request is obtained via a pre-trained request classification model based on the search term, the user information and the knowledge entity.

In the present embodiment, the specific processing of step 404 can refer to the related description of the related selectable embodiment in the corresponding embodiment of FIG. 2, and the duplicated description thereof will be omitted. ..

In step 405, at least one attribute information of the knowledge entity is acquired in the pre-stored set of knowledge entities.

Here, the at least one attribute information and the at least one request have a one-to-one correspondence.

In the present embodiment, the specific processing of step 405 can refer to the related description of step 203 in the corresponding embodiment of FIG. 2, and the duplicated description thereof will be omitted.

In step 406, the acquired attribute information is integrated into one search result and added to the search result page.

In the present embodiment, the specific processing of step 406 can refer to the related description of step 204 in the corresponding embodiment of FIG. 2, and the duplicated description thereof will be omitted.

In some alternative embodiments of this example, step 404 includes pre-trained request classification based on the search term, the user information, the knowledge entity, the first knowledge entity and the first request. The method may include using a model to obtain the at least one request. Here, the electronic device inputs the search term, the user information, the knowledge entity in the search request acquired in step 403, the first knowledge entity, and the first request into a pretrained request classification model. Then, the probability corresponding to each request can be obtained, and a predetermined amount of requests can be sequentially selected in descending order as at least one request among the search requests according to the corresponding probability. Here, the requirement classification model may be acquired by learning and training a large amount of training data including requirement comments. Here, the training data may include information such as a search word, user information, a knowledge entity, a first knowledge entity, a first request, a request, and a comment, where a comment is a search word of the training data. It is for displaying whether or not it is related to the knowledge entity and the request.

In this embodiment, the at least one request related to the knowledge entity in the retrieved search request of the user may be more accurate and scientific so that the content requested by the user can be displayed more accurately.

In some selectable embodiments of the present embodiment, the information search method of the present embodiment, after receiving a search request , uses the named expression recognition (Named Entity Recognition) algorithm to perform the above-mentioned search. The method may further include retrieving the entity word and the requested word in the search term. Here, the specific expression extraction algorithm may be a CRF (Conditional Random Field) algorithm.

Also, step 403 is based on the search term, the user information, the first knowledge entity, the first request, the entity word, and the word of the requirement, through the pretrained knowledge entity classification model. The step of obtaining a knowledge entity may be included. Here, the knowledge entity classification model of the method of the present embodiment may be obtained by learning and training a large amount of training data provided with entity annotations. Here, the training data of the method of the present embodiment may include information such as a search word, user information, a first knowledge entity, a first request, a word of the entity, a word of the request, a knowledge entity, and a comment. Is for displaying whether the search term is related to the knowledge entity of the training data.

This realization makes the acquired knowledge entity more scientific by adding the entity word and the requested word in the above search phrase obtained through the recognition algorithm of the name entity to the criterion factors of the classification of the knowledge entity. By doing so, the content requested by the user is displayed more accurately.

Further, in an embodiment in which a part of this embodiment can be selected based on the above embodiment, step 404 includes the search term, the user information, the knowledge entity, the first knowledge entity, the first request, The method may include obtaining the at least one request via a pre-trained request classification model based on the entity word and the request word. Here, the electronic device preliminarily sets the search term, the user information, the knowledge entity in the search request acquired in step 403, the first knowledge entity, the first request, the word of the entity, and the request word in advance. It is possible to input to the trained requirement classification model, obtain a probability corresponding to each requirement, and sequentially select a predetermined amount of requirements in descending order as at least one requirement among the search requirements according to the corresponding probability. it can. Here, the requirement classification model may be acquired by performing learning and training on a large amount of training data including requirement comments. Here, the training data may include information such as a search word, user information, a knowledge entity, a first knowledge entity, a first request, an entity word, a request word, a request, and a comment, where a comment Is for displaying whether the search term is related to the knowledge entity and request of the training data.

This realization relates to the entity's words in the search phrase obtained through the name entity's recognition algorithm and the request word in addition to the criteria factors for the classification, as well as to the knowledge entities in the retrieved user's search request. By making at least one request more accurate and scientific, the content requested by the user can be displayed more accurately.

As can be seen from FIG. 4, as compared with the corresponding embodiment of FIG. 2, the information retrieval method flow 400 in this embodiment is similar to the first knowledge entity that matches the search term using the multi- pattern matching algorithm. Add the step of obtaining the first requirement of, and add the first knowledge entity and the first requirement to the criterion factor of the classification of the knowledge entity. Thus, the method described in this embodiment accurately displays the content requested by the user by making the acquired knowledge entity more scientific.

Still referring to FIG. 5, as an implementation of the method shown in each of the above figures, the present application provides an embodiment of the information retrieval apparatus, which embodiment of the device implements the method shown in FIG. Corresponding to an example, this device can be applied in particular to a server.

As shown in FIG. 5, the information search system 500 of the present embodiment, the search according receiving unit 501, the search request obtaining unit 502 includes an attribute information acquisition unit 503 and the page generation unit 504. Here, the search request receiving unit 501 is configured to receive the search request including the search term input by the user. The search request acquisition unit 502 is configured to acquire the user information of the user and acquire the search request of the user through a pre-trained classification model based on the search term and the user information. , The search request includes a knowledge entity, at least one request associated with the knowledge entity. The attribute information acquisition unit 503 is constructed to acquire at least one attribute information of the knowledge entity from a pre-stored set of knowledge entities, the at least one attribute information and the at least one request comprising: One-to-one correspondence. The page generation unit 504 is constructed to integrate the acquired attribute information into one search result and add it to the search result page.

In this embodiment, the specific processing of the search request reception unit 501, the search request acquisition unit 502, the attribute information acquisition unit 503, and the page generation unit 504 is as follows: Step 201, Step 202, Step in the corresponding embodiment of FIG. Reference may be made to the related description of step 203 and step 204, and redundant description thereof will be omitted.

In some selectable embodiments of this example, the search request acquisition unit 502 may acquire the knowledge entities via a pre-trained knowledge entity classification model based on the search terms and the user information. A knowledge entity acquisition subunit 5021 constructed according to the above-mentioned search phrase, said user information and said knowledge entity, and is constructed to acquire said at least one request via a pre-trained request classification model. The request acquisition subunit 5022 may be included. Here, for the specific processing of the knowledge entity acquisition subunit 5021 and the request acquisition subunit 5022 and the technical effect acting on their behalf, refer to the related description of the corresponding embodiment in the corresponding example of FIG. A duplicate description will be omitted.

In some selectable embodiments of this embodiment, the information retrieval device 500 of this embodiment uses the multi- pattern matching algorithm after receiving the search request to determine the predetermined matching result and the first knowledge entity. The method may further include a multi- pattern matching unit 505 configured to obtain the first knowledge entity that matches the search term and the first request based on the correspondence relationship of the first request. In addition, the knowledge entity acquisition subunit 5021 may acquire the knowledge entity via a pre-trained knowledge entity classification model based on the search term, the user information, the first knowledge entity, and the first request. Can be further constructed. Here, the specific processing of the multi- pattern matching unit 505 can refer to the related description of step 402 in the corresponding embodiment of FIG. 4, and the duplicated description thereof will be omitted. The specific processing of the knowledge entity acquisition subunit 5021 of this embodiment can refer to the related description of step 403 in the corresponding example of FIG. 4, and a duplicate description thereof will be omitted.

Based on the above embodiment, in an embodiment in which a part of this embodiment can be selected, the request acquisition subunit 5022 includes the search term, the user information, the knowledge entity, the first knowledge entity, and the first request. Can be further constructed to obtain the at least one request via a pre-trained request classification model based on For the specific processing of the embodiment and the technical effect to perform these substitutions, refer to the related description of the corresponding embodiment in the corresponding example of FIG. 4, and the duplicated description thereof will be omitted.

In some selectable embodiments of the present embodiment, the information search device 500 of the present embodiment receives the search request , and then, through the named entity extraction algorithm based on the search term, It may further include a named entity extraction unit 506 constructed to obtain the entity word and the request word. In addition, the knowledge entity acquisition sub-unit 5021 uses the search term, the user information, the first knowledge entity, the first request, the word of the entity, and the word of the request, based on a pre-trained knowledge entity classification model. It can be further constructed to obtain the knowledge entity via For the specific processing of the embodiment and the technical effect to perform these substitutions, refer to the related description of the corresponding embodiment in the corresponding example of FIG. 4, and the duplicated description thereof will be omitted.

Based on the above embodiment, in an embodiment in which a part of this embodiment can be selected, the request acquisition subunit 5022 includes the search term, the user information, the knowledge entity, the first knowledge entity, and the first request. , And may be further configured to obtain the at least one requirement via a pre-trained requirement classification model based on the entity word and the requirement word. For the specific processing of the embodiment and the technical effect to perform these substitutions, refer to the related description of the corresponding embodiment in the corresponding example of FIG. 4, and the duplicated description thereof will be omitted.

In some selectable embodiments of this example, the attribute information acquired by the attribute information acquisition unit 503 includes at least one of image information and character information. For specific processing of the embodiment and these substitute technical effects, refer to the related description of the selectable embodiment of step 203 in the corresponding embodiment of FIG. 2, and duplicate description thereof will be omitted. To do.

The apparatus for searching information provided in this embodiment uses a pre-trained classification model based on the search term and user information in the search request acquisition unit 502 and at least one of the knowledge entities in the user's search request. One request to obtain at least one attribute information of the knowledge entity corresponding to the request in the set of knowledge entities stored in advance in the attribute information acquisition unit 503, and then to the page generation unit 504. The attribute information acquired in step 1 is integrated into one search result and added to the search result page. As a result, the content requested by the user can be displayed, and the display content of the search results can be enriched.

With reference to FIG. 6 below, FIG. 6 shows a structural schematic diagram of a computer system 600 suitable for implementing the server of an embodiment of the present application.

As shown in FIG. 6, the computer system 600 includes a central processing unit (CPU) 601. The CPU 601 stores a program stored in a read-only memory device (ROM) 602 or a random access memory device (ROM) from a storage unit 606. Various appropriate operations and processes can be executed by the program loaded in the RAM) 603. The RAM 603 stores various programs and data necessary for operating the system 600. The CPU 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. Input/output (I/O) interface 605 is also connected to bus 604.

The members connected to the I/O interface 605 include a storage unit 606 including a hard drive and the like, and a communication unit 607 including a network interface card such as a LAN card and a modem. The communication unit 607 executes communication processing via a network such as the Internet. The drive unit 608 is also connected to the I/O interface 605 according to demand. A removable medium 609 such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory device is provided to the drive unit 608 in response to a request to install the computer program read from such a medium in the storage unit 606 according to demand. It is installed.

In particular, according to the embodiments of the present disclosure, the processes described above with reference to the flowcharts can be implemented as a computer software program. For example, embodiments of the present disclosure include a computer program product, the computer program product comprising a computer program tangibly included in a machine-readable medium, the computer program executing a method illustrated in a flowchart. Includes computer code to do. In these examples, the computer program can be downloaded and installed from the network via communication unit 607 and/or installed from removable media 609. When the computer program is executed by the central processing unit (CPU) 601, it executes the functions limited to the method of the present application.

The flowcharts and block diagrams in the accompanying drawings illustrate the possible system structures, functions, and operations of systems, methods, and computer program products according to embodiments of the present application. In these respects, each block in the flowcharts or block diagrams is such that one module can represent a segment of the program or part of the code, and the module defines a segment of the program or part of the code. And includes one or more executable commands for implementing the specified logic function. It should be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the accompanying drawings. For example, two blocks displayed sequentially can actually be executed at about the same time, and in some cases also in a reversed order, which is determined by the function involved. It Each block in the block diagrams and/or flowcharts and any combination of blocks in the block diagrams and/or flowcharts may be implemented as a dedicated hardware-based system that performs a specified function or operation, or may be combined with dedicated hardware. It should be noted that it may be realized by a combination of computer commands.

The related units described in the embodiments of the present application can be realized by a software method and can also be realized by a hardware method. The described units may also be installed on the processor, for example, the processor searches claims receiver unit, the search request obtaining unit, the attribute information acquisition unit may be described as including a page generation unit. Here, the names of these units do not constitute a limitation of the unit itself in some cases, for example, a search request receiving unit can also be described as a “unit receiving a search request ”.

In another aspect, the application further provides a non-volatile computer storage medium, which may be the non-volatile computer storage medium included in the device described in the above embodiments. It can also be a non-volatile computer storage media to be independently present not mounted on the terminal. One or more programs are stored in the non-volatile computer storage medium, and when the one or more programs are executed by one device, a search term input by a user is input to the device. Receiving a search request including the user information of the user, based on the search term and the user information, to obtain the search request of the user through a pre-trained classification model, the search request is , and knowledge entities, including at least one request related to the knowledge entities in advance a set of stored knowledge entity, but to obtain at least one attribute information of the knowledge entity, the at least one attribute information The above-mentioned at least one request has a one-to-one correspondence, and the acquired attribute information is integrated into one search result and added to the search result page.

The above description is merely a description of the preferred embodiments of the present application and the technical principles used. A person skilled in the art should not limit the scope of protection according to the present application to a technical solution consisting of a specific combination of the above-mentioned technical features, and any of the above-mentioned technical features or equivalent features without departing from the spirit of the present invention. It is understood that other technical solutions consisting of combinations of For example, a technical scheme in which the above features and the technical features having similar functions disclosed in the present application (but not limited to these) are replaced with each other are also included.

Claims (13)

A search request receiving step of receiving a search request including a search term input by a user,
A multi-pattern matching algorithm is used to obtain a regular expression matching the search term as a matching result, and match the search term based on a predetermined correspondence between the regular expression and the first knowledge entity and the first request. A multi-pattern matching step to get the first knowledge entity and the first request to
A search request obtaining step of obtaining user information of the user and obtaining the search request of the user through a pre-trained classification model based on the search phrase and the user information; and the search request is a knowledge entity. (Intellectual Entities) and at least one requirement associated with the knowledge entity, the knowledge entity being a point or proper noun of knowledge,
The search request acquisition step,
Obtaining a knowledge entity included in the search request via a pre-trained knowledge entity classification model based on the search term, the user information, the first knowledge entity and the first request;
Obtaining at least one request included in the search request via a pre-trained request classification model based on the search term, the user information and the knowledge entity,
An attribute information acquisition step of acquiring at least one attribute information of the knowledge entity acquired in the search request acquisition step from a set of knowledge entities stored in advance, and the at least one attribute information and the search request are included. At least one request has a one-to-one correspondence,
A page generation step of integrating the acquired attribute information into one search result and adding it to the search result page. Obtaining at least one request included in the search request via a pre-trained request classification model based on the search term, the user information and the knowledge entity,
Obtaining at least one request contained in the search request via a pre-trained request classification model based on the search term, the user information, the knowledge entity, the first knowledge entity and the first request. The information search method according to claim 1, further comprising: After receiving the search request in the search request receiving step, the method further comprises the step of obtaining the word of the entity and the request word in the search word through a named expression recognition algorithm based on the search word. Including,
Obtaining knowledge entities included in the search request via a pre-trained knowledge entity classification model based on the search phrase, the user information, the first knowledge entity and the first request,
Knowledge contained in the search request via a pre-trained knowledge entity classification model based on the search phrase, the user information, the first knowledge entity, the first request, the entity word and the request word The information retrieval method according to claim 1, further comprising a step of acquiring an entity. Obtaining at least one request included in the search request via a pre-trained request classification model based on the search term, the user information and the knowledge entity,
Based on the search term, the user information, the knowledge entity, the first knowledge entity, the first request, the word of the entity, and the word of the request, the search request to the search request via a pre-trained request classification model. The information retrieval method according to claim 3, further comprising the step of obtaining at least one request included. The information retrieval method according to claim 1, wherein the acquired attribute information includes at least one of image information and character information. A search request receiving unit configured to receive a search request including a search term entered by a user;
A multi-pattern matching algorithm is used to obtain a regular expression matching the search term as a matching result, and match the search term based on a predetermined correspondence between the regular expression and the first knowledge entity and the first request. A multi-pattern matching unit to get the first knowledge entity and the first request to
A search request obtaining unit constructed to obtain user information of the user and obtain the search request of the user via a pre-trained classification model based on the search term and the user information; The request includes a knowledge entity and at least one request associated with the knowledge entity, the knowledge entity being a point or proper noun of knowledge,
The search request acquisition unit,
A knowledge entity acquisition subunit for acquiring a knowledge entity included in the search request through a pre-trained knowledge entity classification model based on the search phrase, the user information, the first knowledge entity, and the first request; ,
A request acquisition subunit for acquiring at least one request included in the search request via a pre-trained request classification model based on the search term, the user information and the knowledge entity,
An attribute information acquisition unit constructed to acquire at least one attribute information of the knowledge entity acquired by the search request acquisition unit from a pre-stored set of knowledge entities, the at least one attribute information And at least one request included in the search request have a one-to-one correspondence with an attribute information acquisition unit,
An information search device comprising a page generation unit constructed to integrate the acquired attribute information into one search result and add the search result page. The request acquisition subunit is
Obtaining at least one request included in the search request via a pre-trained request classification model based on the search phrase, the user information, the knowledge entity, the first knowledge entity and the first request. The information retrieving apparatus according to claim 6, further comprising: After receiving a search request in the search request receiving unit, a unique expression extraction unit constructed to obtain a word of an entity in the search phrase and a requested word through a unique expression extraction algorithm based on the search phrase. Further including,
The knowledge entity acquisition subunit is based on the search term, the user information, the first knowledge entity, the first request, the word of the entity, and the word of the request based on a pre-trained knowledge entity classification model. The information retrieving apparatus according to claim 6, further configured to obtain a knowledge entity included in the retrieval request. The request acquisition sub-unit is a pre-trained request classification model based on the search term, the user information, the knowledge entity, the first knowledge entity, the first request, the word of the entity and the word of the request. 9. The information search device according to claim 8, further configured to acquire at least one request included in the search request via. 10. The information search device according to claim 6, wherein the attribute information acquired by the attribute information acquisition unit includes at least one of image information and character information. A processor,
Including storage,
The storage device stores a computer-readable command that can be executed by the processor, and when the computer-readable command is executed, the processor executes an information search method, and the information search method, ,
A search request receiving step of receiving a search request including a search term input by a user,
A multi-pattern matching algorithm is used to obtain a regular expression matching the search term as a matching result, and match the search term based on a predetermined correspondence between the regular expression and the first knowledge entity and the first request. A multi-pattern matching step to get the first knowledge entity and the first request to
A search request obtaining step of obtaining user information of the user and obtaining the search request of the user through a pre-trained classification model based on the search phrase and the user information; and the search request is a knowledge entity. And at least one requirement associated with the knowledge entity, the knowledge entity being a point or proper noun of knowledge,
The search request acquisition step,
Obtaining a knowledge entity included in the search request via a pre-trained knowledge entity classification model based on the search term, the user information, the first knowledge entity and the first request;
Obtaining at least one request included in the search request via a pre-trained request classification model based on the search term, the user information, and the knowledge entity;
A step of acquiring at least one attribute information of the knowledge entity acquired in the search request acquisition step from a set of knowledge entities stored in advance, the at least one attribute information being included in the search request; One request is a one-to-one correspondence with steps,
Integrating the acquired attribute information into one search result and adding it to the search result page. A non-volatile computer storage medium storing computer-readable commands executable by a processor,
When the computer-readable command is executed by a processor, the processor executes an information retrieval method, and the information retrieval method comprises
A search request receiving step of receiving a search request including a search term input by a user,
A multi-pattern matching algorithm is used to obtain a regular expression matching the search term as a matching result, and match the search term based on a predetermined correspondence between the regular expression and the first knowledge entity and the first request. A multi-pattern matching step to get the first knowledge entity and the first request to
A search request obtaining step of obtaining user information of the user and obtaining the search request of the user through a pre-trained classification model based on the search phrase and the user information; and the search request is a knowledge entity. And at least one requirement associated with the knowledge entity, the knowledge entity being a point or proper noun of knowledge,
The search request acquisition step,
Obtaining a knowledge entity included in the search request via a pre-trained knowledge entity classification model based on the search term, the user information, the first knowledge entity and the first request;
Obtaining at least one request included in the search request via a pre-trained request classification model based on the search term, the user information, and the knowledge entity,
A step of acquiring at least one attribute information of the knowledge entity acquired in the search request acquisition step from a set of knowledge entities stored in advance, the at least one attribute information being included in the search request; One request is a one-to-one correspondence with steps,
Integrating the acquired attribute information into one search result and adding it to the search result page. A computer program that, when executed by a processor, implements a method according to any one of claims 1-5.