Resource retrieval method and device, storage medium and electronic device

Abstract

The present invention discloses a resource retrieval method and device, a storage medium and an electronic device. The method comprises: obtaining a target request sent by a target account, and obtaining a target search term from the target request; obtaining target portrait information of the target account, the target portrait information is used to represent the learning result of the target account on the resource learning under the target knowledge point; obtaining knowledge graph information of the target account, the knowledge graph information comprises a first knowledge point related to the target search term in the target knowledge graph and a second knowledge point related to the target knowledge point in the target knowledge graph, and / or a first knowledge point label of the first knowledge point and a second knowledge point label of the second knowledge point; according to the target search term and the knowledge graph information, sending a list of queried target resources or a list of some resources in the target resource list to the target account. The present invention solves the technical problem of low matching between resource retrieval results and target accounts.

Description

Technical Field

[0001] The present invention relates to the field of computers, and in particular to a resource retrieval method and device, a storage medium and an electronic device. Background Art

[0002] In short, a database can be seen as an electronic filing cabinet - a place where electronic files are stored, and users can add, query, update, delete, and other operations on the data in the files. The so-called "database" is a collection of data that is stored together in a certain way, can be shared with multiple users, has as little redundancy as possible, and is independent of the application.

[0003] A database management system (DBMS) is a computer software system designed for managing databases. It generally has basic functions such as storage, retrieval, security, and backup. Database management systems can be classified according to the database model they support, such as relational, XML (Extensible Markup Language); or according to the type of computer they support, such as server clusters, mobile phones; or according to the query language used, such as SQL (Structured Query Language), XQuery; or according to performance focus, such as maximum scale, maximum operating speed; or other classification methods. Regardless of the classification method used, some DBMS can cross categories, for example, supporting multiple query languages ​​at the same time.

[0004] At present, in many resource retrieval scenarios, after the user logs in to the resource retrieval client using the target account, a retrieval request is sent to the corresponding resource retrieval system to obtain the corresponding resources by traversing and searching in the corresponding resource database. Finally, the retrieved resources are returned to the resource retrieval client as retrieval results to be presented to the user. For example, taking the educational resource retrieval system as an example, usually, after receiving the retrieval request, the educational resource retrieval system will determine the text similarity between each resource and the keywords in the retrieval request based on the keywords carried in the retrieval request and the titles of each resource in the educational resource library, so as to facilitate the retrieval of the corresponding resources requested by the retrieval request.

[0005] However, for target accounts with different levels of mastery of the same knowledge point, when searching using the method provided by the above-mentioned related technology, the resource search results obtained are also the same when searching with the same keywords. In other words, in the resource search method provided by the related technology, it is impossible to reflect the personalization of resource search results for target accounts of different levels, so that the detected resource search results are relatively simple, which in turn causes the problem of low matching between the resource search results and the target accounts.

[0006] Currently, no effective solution has been proposed for the above-mentioned problem of low matching degree between resource search results and target accounts. Summary of the invention

[0007] The embodiments of the present invention provide a resource search method and device, a storage medium and an electronic device to at least solve the technical problem that the matching degree between the resource search result and the target account is low.

[0008] According to one aspect of an embodiment of the present invention, a resource retrieval method is provided, comprising: obtaining a target request sent by a target account, and obtaining a target search term from the target request, wherein the target request is used to request a query for resources matching the target search term; obtaining target portrait information of the target account, wherein the target portrait information is used to represent the learning result of the target account on resources under a target knowledge point; obtaining knowledge graph information of the target account, wherein the target knowledge graph includes a group of knowledge points and associations between the group of knowledge points, and the knowledge graph information includes a first knowledge point in the target knowledge graph related to the target search term and a second knowledge point in the target knowledge graph related to the target knowledge point, and / or a first knowledge point label of the first knowledge point and a second knowledge point label of the second knowledge point; according to the target search term and the knowledge graph information, sending a target resource list or a list of some resources in the target resource list to the target account, wherein the target resource list is a list of resources queried in a target resource set, and the resources in the target resource list match the target search term and the knowledge graph information.

[0009] According to another aspect of an embodiment of the present invention, a resource retrieval device is further provided, comprising: a first acquisition module, used to acquire a target request sent by a target account, and to acquire a target search term from the target request, wherein the target request is used to request a query for resources matching the target search term; a second acquisition module, used to acquire target portrait information of the target account, wherein the target portrait information is used to represent a learning result of the target account learning resources under a target knowledge point; a third acquisition module, used to acquire knowledge graph information of the target account, wherein the target knowledge graph includes a group of knowledge points and associations between the group of knowledge points. The above-mentioned knowledge graph information includes the first knowledge point related to the above-mentioned target search term in the above-mentioned target knowledge graph and the second knowledge point related to the above-mentioned target knowledge point in the above-mentioned target knowledge graph, and / or the first knowledge point label of the above-mentioned first knowledge point and the second knowledge point label of the above-mentioned second knowledge point; a sending module is used to send a target resource list or a list of some resources in the above-mentioned target resource list to the above-mentioned target account according to the above-mentioned target search term and the above-mentioned knowledge graph information, wherein the above-mentioned target resource list is a list of resources queried in the target resource set, and the resources in the above-mentioned target resource list match the above-mentioned target search term and the above-mentioned knowledge graph information.

[0010] According to another aspect of the embodiments of the present invention, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the resource retrieval method when running.

[0011] According to another aspect of an embodiment of the present invention, there is provided an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the resource retrieval method through the computer program.

[0012] In an embodiment of the present invention, a target request sent by a target account is obtained, and a target search term is obtained from the target request, wherein the target request is used to request a query for resources matching the target search term; target portrait information of the target account is obtained, wherein the target portrait information is used to represent the learning result of the target account on resources under the target knowledge point; knowledge graph information of the target account is obtained, wherein the target knowledge graph includes a group of knowledge points and associations between the group of knowledge points, and the knowledge graph information includes a first knowledge point related to the target search term in the target knowledge graph and a second knowledge point related to the target knowledge point in the target knowledge graph, and / or a first knowledge point label of the first knowledge point and a second knowledge point label of the second knowledge point; according to the target search term and the knowledge graph information, a target resource list or a list of some resources in the target resource list is sent to the target account, wherein the target resource list is a list of resources queried in the target resource set, and the resources in the target resource list match the target search term and the knowledge graph information. When performing resource retrieval, the target portrait information and the target knowledge graph are combined to obtain the knowledge graph information of the target account, and resource retrieval is performed based on the target search terms and the knowledge graph information, thereby realizing intelligent resource retrieval by combining the target account's own learning results of the target knowledge points and the association between the various knowledge points in the target knowledge graph. As a result, for target accounts with different learning results, resources that are suitable for their level can be retrieved separately, so that the retrieval results reflect the personalized needs of different target accounts, rather than retrieving a single resource retrieval result for the same keyword, enriching the content of the resource retrieval results, and improving the matching degree of the resource retrieval results with the target account. Therefore, the technical problem of low matching degree between the resource retrieval results and the target account is solved, the matching degree between the resource retrieval results and the target account is improved, and the user experience is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0014] Figure 1 is a schematic diagram of an application environment of an optional resource retrieval method according to an embodiment of the present invention;

[0015] Figure 2 is a flow chart of an optional resource retrieval method according to an embodiment of the present invention;

[0016] Figure 3 is a schematic diagram of an optional account portrait according to an embodiment of the present invention;

[0017] Figure 4 is a schematic diagram of an optional target knowledge graph according to an embodiment of the present invention;

[0018] Figure 5 is a schematic diagram of an optional target resource set according to an embodiment of the present invention;

[0019] Figure 6 is a schematic diagram of an optional display target resource list according to an embodiment of the present invention;

[0020] Figure 7 is a schematic diagram of an application environment of another optional resource retrieval method according to an embodiment of the present invention;

[0021] Figure 8 is a timing diagram of another optional resource retrieval method according to an embodiment of the present invention;

[0022] Fig. 9 is a structural block diagram of an optional resource retrieval device according to an embodiment of the present invention;

[0023] Fig.10 It is a schematic structural diagram of an optional electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0024] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0025] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0026] According to one aspect of an embodiment of the present invention, a resource retrieval method is provided. Optionally, as an optional implementation, the resource retrieval method can be but is not limited to being applied to: Figure 1 The resource retrieval system in the application environment shown. The resource retrieval system includes a terminal device 102, a server 104 and multiple storage devices, and the multiple storage devices respectively store an account portrait 106, a target knowledge graph 108 and a target resource set 110. A resource retrieval client runs in the terminal device 102, which is used to obtain a target request triggered by a human-computer interaction operation, and the target request will carry a search keyword Key. The server 104 is used to receive the target request sent by the terminal device 102, and respond to the target request to retrieve the corresponding resource in the target resource set 110.

[0027] Specifically, the resource retrieval method to be implemented by the resource retrieval system may include the following steps: using the target account to log in to the resource retrieval client (such as Figure 1 The search term, such as Key, can be obtained in the resource search interface presented by the resource search client shown. After that, as in step S102, the target account sends a target request to the server 104 (optionally, the target account sends the target request through the terminal device 102 logged in by the target account). After receiving the target request, the server 104 executes steps S104-1 to S104-3: obtain the target portrait information of the target account from the account portrait 106, and obtain the knowledge graph information from the target knowledge graph 108 according to the target search term obtained from the target request and the target knowledge point in the target portrait information, wherein the knowledge graph information includes a first knowledge point related to the target search term and a second knowledge point related to the target knowledge point, and / or a first knowledge point label of the first knowledge point and a second knowledge point label of the second knowledge point, retrieve resources in the target resource set 110 according to the target search term and the knowledge graph information to obtain a target resource list, and send the target resource list or a list of some resources in the target resource list to the resource search client logged in using the target account, as in step S106.

[0028] Optionally, in this embodiment, the terminal device may be a terminal device configured with a resource retrieval client, which may include but is not limited to at least one of the following: a mobile phone (such as an Android phone, an iOS phone, etc.), a laptop, a tablet computer, a PDA, a MID (Mobile Internet Devices), a PAD, a desktop computer, a smart TV, etc. The terminal device may also be configured with a target client such as a video client, an instant messaging client, a browser client, an education client, etc. The terminal device sends a target request to the server through a network, and the network may include but is not limited to: a wired network, a wireless network, wherein the wired network includes: a local area network, a metropolitan area network, and a wide area network, and the wireless network includes: Bluetooth, WIFI, and other networks that implement wireless communication. The server may be a single server, or a server cluster consisting of multiple servers, or a cloud server. The above is only an example, and this embodiment does not make any limitation to this.

[0029] As an optional implementation, Figure 2 As shown, the resource retrieval method includes:

[0030] Step S102, obtaining a target request sent by a target account, and obtaining a target search term from the target request, wherein the target request is used to request a query for resources matching the target search term;

[0031] Step S104, obtaining target portrait information of the target account, wherein the target portrait information is used to represent the learning result of the target account on the resource learning under the target knowledge point;

[0032] Step S106, obtaining the knowledge graph information of the target account, wherein the target knowledge graph includes a group of knowledge points and the association relationship between the group of knowledge points, and the knowledge graph information includes a first knowledge point related to the target search term in the target knowledge graph and a second knowledge point related to the target knowledge point in the target knowledge graph, and / or a first knowledge point label of the first knowledge point and a second knowledge point label of the second knowledge point;

[0033] Step S108, based on the target search terms and knowledge graph information, sending a target resource list or a list of some resources in the target resource list to the target account, wherein the target resource list is a list of resources queried in the target resource set, and the resources in the target resource list match the target search terms and knowledge graph information.

[0034] In an embodiment of the present invention, a target request sent by a target account is obtained, and a target search term is obtained from the target request, wherein the target request is used to request a query for resources matching the target search term; target portrait information of the target account is obtained, wherein the target portrait information is used to represent the learning result of the target account on resources under the target knowledge point; knowledge graph information of the target account is obtained, wherein the target knowledge graph includes a group of knowledge points and associations between the group of knowledge points, and the knowledge graph information includes a first knowledge point related to the target search term in the target knowledge graph and a second knowledge point related to the target knowledge point in the target knowledge graph, and / or a first knowledge point label of the first knowledge point and a second knowledge point label of the second knowledge point; a target resource list or a list of some resources in the target resource list is sent to the target account according to the target search term and the knowledge graph information, wherein the target resource list is a list of resources queried in the target resource set, and the resources in the target resource list match the target search term and the knowledge graph information. When performing resource retrieval, the target portrait information and the target knowledge graph are combined to obtain the knowledge graph information of the target account, and resource retrieval is performed based on the target search terms and the knowledge graph information, thereby realizing intelligent resource retrieval by combining the target account's own learning results of the target knowledge points and the association between the various knowledge points in the target knowledge graph. As a result, for target accounts with different learning results, resources that are suitable for their level can be retrieved separately, so that the retrieval results reflect the personalized needs of different target accounts, rather than retrieving a single resource retrieval result for the same keyword, enriching the content of the resource retrieval results, and improving the matching degree of the resource retrieval results with the target account. Therefore, the technical problem of low matching degree between the resource retrieval results and the target account is solved, the matching degree between the resource retrieval results and the target account is improved, and the user experience is improved.

[0035] Optionally, Figure 3 FIG. 1 is a schematic diagram of an optional account portrait according to an embodiment of the present invention. Figure 3 As shown, the account portrait 106 includes the learning results of resource learning corresponding to multiple knowledge points for multiple accounts. For example, for account a, the account portrait 106 stores the learning results a1, a2, and aN of account a for knowledge point 1, knowledge point 2, ..., knowledge point N. The learning results are used to indicate the mastery of the account for the corresponding knowledge point, for example, the learning results are the mastery level.

[0036] Optionally, Figure 4 FIG. 1 is a schematic diagram of an optional target knowledge graph according to an embodiment of the present invention. Figure 4 As shown, the target knowledge graph 108 includes a set of knowledge points (as an example, Figure 4 Only some of the knowledge points in a group of knowledge points are shown) and the association relationship between a group of knowledge points. In an optional embodiment, the above-mentioned group of knowledge points in the target knowledge graph includes but is not limited to all knowledge points corresponding to all educational resources in the educational resource library. For example, the target knowledge graph may include knowledge points such as "factorization", "quadratic equations", "linear equations", "combining like terms", "translation and rotation of graphics", and the association relationship between these knowledge points. The association relationship between the above-mentioned group of knowledge points includes a pre- and post-position relationship, wherein each knowledge point has a corresponding sequence identifier and a knowledge point label, and the sequence identifier is used to represent the sequence number of the corresponding knowledge point in the target knowledge graph.

[0037] Optionally, Figure 5 FIG. 1 is a schematic diagram of an optional target resource set according to an embodiment of the present invention. Figure 5 As shown, the target resource set 110 includes multiple resources, wherein each resource has one or more corresponding knowledge points and a corresponding resource tag. Optionally, the resource tag includes: the chapter where the resource is located, the title of the resource, the text content of the resource, and the resource link.

[0038] In the above embodiment, after obtaining the target request sent by the target account, the target account is determined according to the target request, and the target portrait information corresponding to the target account is obtained from the account portrait 106. The target portrait information includes the target knowledge point corresponding to the target account, and the learning result of the target account corresponding to each knowledge point in the target knowledge point. The learning result here can be but is not limited to the learning result of the target account for the resource learning under the corresponding knowledge point. As an optional implementation, the target knowledge point includes all the knowledge points corresponding to the target account in the account portrait 106.

[0039] Among them, the knowledge graph information of the target account can be queried from the target knowledge graph based on the target search term obtained from the target request and the target knowledge point involved in the target portrait information. The knowledge graph information includes the first knowledge point related to the target search term in the target knowledge graph and the second knowledge point related to the target knowledge point in the target knowledge graph, and / or the first knowledge point label of the first knowledge point and the second knowledge point label of the second knowledge point.

[0040] Among them, the knowledge point in the above embodiment can be but is limited to a relatively independent minimum unit in the knowledge involved in the educational resource. For example, the educational resource is a courseware named "Detailed Explanation of Quadratic Equations", and the knowledge involved in the educational resource is the solution of quadratic equations in mathematics. The corresponding knowledge point can be the knowledge point of "quadratic equations". The knowledge point label includes but is not limited to the attributes of the knowledge point, which is used to describe the knowledge point. For example, the knowledge point label is used to indicate the chapter where the knowledge point is located, or the examination range corresponding to the knowledge point. In the above embodiment, the first knowledge point label can be used to indicate the chapter where the above first knowledge point is located, or the examination range corresponding to the above first knowledge point; the above second knowledge point label can be used to indicate the chapter where the above second knowledge point is located, or the examination range corresponding to the above second knowledge point. Among them, the chapter where the knowledge point is located can be the chapter where the knowledge point is located in the target teaching material of the educational resource library.

[0041] Optionally, in this embodiment, the above resource retrieval method can be used in but is not limited to various resource retrieval scenarios, such as educational resource retrieval scenarios.

[0042] In an optional embodiment, obtaining the knowledge graph information of the target account includes: querying the target knowledge graph for knowledge points related to the target search term to obtain a first knowledge point; querying the target knowledge graph for knowledge points related to the target knowledge point to obtain a second knowledge point; and / or querying the target knowledge graph for the knowledge point label of the first knowledge point to obtain a first knowledge point label; querying the target knowledge graph for the knowledge point label of the second knowledge point to obtain a second knowledge point label.

[0043] In the above embodiment, since the acquired knowledge graph information includes the first knowledge point related to the target search term, the second knowledge point related to the target knowledge point, and / or the knowledge point label of the first knowledge point and the knowledge point label of the second knowledge point, when resource retrieval is performed based on the target search term and the knowledge graph information, the retrieved resources are resources related to the target account's mastery of the knowledge points, that is, for target accounts with different mastery of the same knowledge point, or for target accounts with different mastery of the same knowledge point at different stages, the retrieved resources are different, thereby achieving personalized resource recommendations to the target account and improving the matching degree between the resource retrieval results and the target account. In an optional embodiment, the above-mentioned querying of knowledge points related to the above-mentioned target knowledge point in the above-mentioned target knowledge graph to obtain the above-mentioned second knowledge point includes: querying the above-mentioned target knowledge graph for the preceding first-level knowledge points or preceding multi-level knowledge points of some or all of the above-mentioned target knowledge points to obtain the third knowledge point, wherein the above-mentioned second knowledge point includes the above-mentioned third knowledge point; and / or querying the above-mentioned target knowledge graph for the post-first-level knowledge points or post-multi-level knowledge points of some or all of the above-mentioned target knowledge points to obtain the fourth knowledge point, wherein the above-mentioned second knowledge point includes the above-mentioned fourth knowledge point.

[0044] It should be noted that in the above embodiment, the preceding knowledge points and / or succeeding knowledge points of the target knowledge point are queried from the target knowledge graph, so that resources under other knowledge points associated with the target knowledge point can be retrieved based on the preceding knowledge points and / or succeeding knowledge points, thereby improving the richness of the search results.

[0045] Optionally, the preceding and following relationships between knowledge points are determined based on the sequential identifiers of the knowledge points. For example, for an adjacent knowledge point in the target knowledge graph that has an association relationship with the target knowledge point and is directly connected to the target knowledge point, the first sequential identifier of the adjacent knowledge point and the second sequential identifier of the target knowledge point are obtained. When the value represented by the first sequential identifier is less than the value represented by the second sequential identifier, the adjacent knowledge point is determined to be a preceding first-level knowledge point of the target knowledge point; when the value represented by the first sequential identifier is greater than the value represented by the second sequential identifier, the adjacent knowledge point is determined to be a succeeding first-level knowledge point of the target knowledge point.

[0046] Optionally, after obtaining the preceding first-level knowledge point of the target knowledge point, a similar method as described above is used to continue to determine the preceding first-level knowledge point of the preceding first-level knowledge point (i.e. the preceding second-level knowledge point of the target knowledge point); and / or, determine the succeeding first-level knowledge point of the succeeding first-level knowledge point (i.e. the succeeding second-level knowledge point of the target knowledge point).

[0047] Optionally, since the learning process of the target account is a gradual process, a set of sequence identifiers is also used to indicate the learning order of the target account for a set of knowledge points corresponding to the set of sequence identifiers. For example, for a set of knowledge points 1, knowledge point 2, and knowledge point 3, where the sequence identifier corresponding to knowledge point 1 is 1, the sequence identifier corresponding to knowledge point 2 is 3, and the sequence identifier corresponding to knowledge point 3 is 2, the sequence identifier corresponding to the set of knowledge points indicates that when the target account learns the set of knowledge points, the corresponding learning order is: knowledge point 1, knowledge point 3, knowledge point 2, that is, the target account needs to first learn the content related to knowledge point 1, then learn the content related to knowledge point 3, and then learn the content related to knowledge point 2.

[0048] In an optional embodiment, the above-mentioned querying the knowledge points related to the above-mentioned target knowledge point in the above-mentioned target knowledge graph to obtain the above-mentioned second knowledge point includes: in a case where the above-mentioned target knowledge point includes the fifth knowledge point and the sixth knowledge point, querying the knowledge points related to the above-mentioned fifth knowledge point in the above-mentioned target knowledge graph, wherein the above-mentioned target portrait information indicates that: the learning result of the above-mentioned target account on the resources under the above-mentioned fifth knowledge point does not meet the preset conditions, and the learning result of the above-mentioned target account on the resources under the above-mentioned sixth knowledge point meets the above-mentioned preset conditions.

[0049] Optionally, the preset condition includes: the mastery degree corresponding to the learning result is greater than a preset degree threshold. For example, the learning result of the target account for the resource learning under the fifth knowledge point is: mastery degree 5, and the preset degree threshold is 6. Since the mastery degree corresponding to the learning result is less than the preset degree threshold, it is determined that the learning result of the target account for the resource learning under the fifth knowledge point does not meet the preset condition, that is, the target account has a weak grasp of the fifth knowledge point.

[0050] In the above embodiment, the second knowledge points obtained from the target knowledge graph include knowledge points related to the knowledge points whose learning results of the target account do not meet the preset conditions (i.e., knowledge points related to the knowledge points that the target account has weak grasp of), so that the resources retrieved based on the second knowledge points are resources that are helpful in improving the learning results of the target account, that is, the retrieved resources are more in line with the individual situation of the target account, thereby improving the matching degree between the resource retrieval results and the target account.

[0051] Optionally, the above-mentioned querying of knowledge points related to the above-mentioned target knowledge point in the above-mentioned target knowledge graph to obtain the above-mentioned second knowledge point includes: querying the preceding first-level knowledge points or preceding multi-level knowledge points of some or all of the above-mentioned fifth knowledge point in the above-mentioned target knowledge graph to obtain a seventh knowledge point, wherein the above-mentioned second knowledge point includes the above-mentioned seventh knowledge point; and / or querying the post-first-level knowledge points or post-multi-level knowledge points of some or all of the above-mentioned fifth knowledge point in the above-mentioned target knowledge graph to obtain an eighth knowledge point, wherein the above-mentioned second knowledge point includes the above-mentioned eighth knowledge point.

[0052] In an optional embodiment, before sending a target resource list or a list of some resources in the target resource list to the target account based on the target search term and the knowledge graph information, the method further includes: in a case where the knowledge graph information includes the first knowledge point and the second knowledge point, querying the target resource set for resources matching the target search term under the first knowledge point to obtain a first resource, wherein the target resource set includes resources under multiple knowledge points, and the multiple knowledge points include the first knowledge point and the second knowledge point; querying the target resource set for resources matching the target search term under the second knowledge point to obtain a second resource, wherein the target resource list includes the first resource and the second resource.

[0053] Among them, the resources matching the target search term under the first knowledge point and the resources matching the target search term under the second knowledge point are queried in the target resource set to obtain the second resource, so that the retrieved resources are more in line with the actual learning needs of the target account, more helpful to the learning of the target account, and further improve the user experience.

[0054] In an optional embodiment, before sending a target resource list or a list of some resources in the target resource list to the target account according to the target search term and the knowledge graph information, the method further includes: in a case where the knowledge graph information includes the first knowledge point tag and the second knowledge point tag, querying the target resource set for resources matching the target search term under the first knowledge point tag to obtain a third resource, wherein the target resource set includes resources under multiple knowledge point tags, the multiple knowledge point tags include the first knowledge point tag and the second knowledge point tag, and each of the multiple knowledge point tags has one or more knowledge points; querying the target resource set for resources matching the target search term under the second knowledge point tag to obtain a fourth resource, wherein the target resource list includes the third resource and the fourth resource.

[0055] Among them, the resources matching the target search term under the first knowledge point label are queried in the target resource set, and the resources matching the target search term under the second knowledge point label are queried in the target resource set, so that the retrieved resources are more in line with the actual learning needs of the target account, are more helpful to the learning of the target account, and further improve the user experience.

[0056] In an optional embodiment, according to the target search term and the knowledge graph information, a target resource list or a list of some resources in the target resource list is sent to the target account: in the case of sending the target resource list to the target account, the resources in the target resource list are sorted according to the mastery of the corresponding knowledge point represented by the first learning result to obtain a first resource list, wherein the first learning result is the learning result of the target account learning the resources under the first group of knowledge points, the learning result represented by the target portrait information includes the first learning result, and the first group of knowledge points are the knowledge points to which the resources included in the target resource list belong; the first resource list is sent to the target account; or in the case of sending a list of some resources in the target resource list to the target account, the resources in the list of some resources are sorted according to the mastery of the corresponding knowledge point represented by the second learning result to obtain a second resource list, wherein the second learning result is the learning result of the target account learning the resources under the second group of knowledge points, the learning result represented by the target portrait information includes the second learning result, and the second group of knowledge points are the knowledge points to which the resources included in the list of some resources belong; the second resource list is sent to the target account.

[0057] Optionally, in the case of sending the above-mentioned target resource list to the above-mentioned target account, all resources in the target resource list are sorted according to the target account's learning results for the knowledge points to which all resources in the target resource list belong, to obtain a first resource list. For example, the resources in the target resource list are sorted in the order of the numerical values ​​represented by the mastery degree corresponding to the above-mentioned set of knowledge points from small to large to obtain the first resource list, that is, the resources related to the knowledge points that the target account has a weaker mastery degree are placed in front, thereby realizing the priority display of the resources related to the knowledge points that the target account has a weaker mastery degree to the target account; or, in the case of sending part of the resources in the above-mentioned target resource list to the above-mentioned target account, according to the target account's learning results for the knowledge points to which some of the resources in the target resource list belong, the resources in the target resource list are sorted to obtain the first resource list.

[0058] In an optional embodiment, the method further includes: in the case of sending the target resource list to the target account, sending a first learning result to the target account, wherein the first learning result is the learning result of the target account learning the resources under the first group of knowledge points, the learning result represented by the target portrait information includes the first learning result, and the first group of knowledge points are the knowledge points to which the resources included in the target resource list belong; or in the case of sending a list of partial resources in the target resource list to the target account, sending a second learning result to the target account, wherein the second learning result is the learning result of the target account learning the resources under the second group of knowledge points, the learning result represented by the target portrait information includes the second learning result, and the second group of knowledge points are the knowledge points to which the resources included in the partial resource list belong.

[0059] In the above embodiment, when the target resource list is sent to the target account, the first learning result is sent to the target account, including: generating a first display page for displaying the target resource list and the first learning result, wherein the first display page is used to display a learning result corresponding to each resource in the display area for displaying each resource in the target resource list, and the first learning result includes a learning result corresponding to each resource; sending the first display page to the target account.

[0060] Optionally, in the case of sending a list of some resources in the above-mentioned target resource list to the above-mentioned target account, sending a second learning result to the above-mentioned target account includes: generating a second display page for displaying the list of some resources in the above-mentioned target resource list and the above-mentioned second learning result, wherein the above-mentioned second display page is used to display a learning result corresponding to each resource in the above-mentioned partial resource list in a display area displaying each resource in the above-mentioned partial resource list, and the above-mentioned second learning result includes a learning result corresponding to each resource in the partial resource list; sending the above-mentioned second display page to the above-mentioned target account.

[0061] Optionally, the learning results are displayed in the form of icons and / or text. Figure 6 As shown, when the first display page is displayed in the terminal device logged in by the target account, the learning result corresponding to the resource (i.e., the mastery degree represented by the learning result) is displayed in the area of ​​each resource displayed on the first display page at the same time in the form of an icon, wherein the name of the knowledge point associated with the resource is displayed in the area 1 corresponding to each resource, and the learning result of the target account for the corresponding knowledge point is displayed in the form of an icon in the area 2 corresponding to each resource; wherein the first graphic (i.e., Figure 6 In ) is positively correlated with the numerical value corresponding to the degree of mastery, that is, the larger the numerical value corresponding to the degree of mastery is, the larger the area of ​​the first graphic is; optionally, in the first display page, the numerical value corresponding to the degree of mastery is displayed at the position where the degree of mastery is displayed.

[0062] The resource retrieval method in the above embodiment is explained below with reference to an example, but is not intended to limit the technical solution of the embodiment of the present invention.

[0063] Figure 7 FIG. 1 is a schematic diagram of a resource retrieval method according to another optional embodiment of the present invention. Taking the retrieval of educational resources as an example, Figure 7 As shown, the method comprises the following steps:

[0064] Step S701, knowledge construction, extraction and fusion of knowledge points, and establishment of target knowledge graph;

[0065] Among them, in the knowledge construction, and the steps of extracting and integrating knowledge points, the knowledge points to which each resource in the educational resource library belongs, as well as the association relationship between knowledge points, are determined; based on the determined knowledge points and the association key between knowledge points, the target knowledge graph is constructed;

[0066] Optionally, the target knowledge graph includes: the names of knowledge points of each subject knowledge point and the association relationship between each knowledge point (wherein the association relationship includes a front-end relationship and a back-end relationship, and may also include a parent-child relationship), the chapter data of the textbook version where each knowledge point is located, and the subject test point data corresponding to each knowledge point, the examination scope data of the subject corresponding to the knowledge point, etc.;

[0067] Optionally, the target knowledge graph is stored in a graph database such as JanusGraph or Neo4j.

[0068] Step S702, constructing a user portrait (i.e., the account portrait in the above embodiment);

[0069] Among them, building a user portrait specifically includes the following steps:

[0070] Step S7021, data collection;

[0071] The behavior record uploaded by the target account is obtained, and the behavior record includes the first resource (such as question q1) that the target account has learned;

[0072] Step S7022: querying the data factory for relevant data; wherein querying the data factory for relevant data includes:

[0073] According to the behavior record uploaded by the target account, query the target resource associated with the first resource in the behavior record of the target account, for example, the target resource is a high-quality question (such as q2, q3) corresponding to question q1, wherein the target resource has a corresponding relationship with the knowledge point;

[0074] Determine the knowledge points corresponding to questions q2 and q3, remove duplicates from these knowledge points, and obtain a set of knowledge points after removal of duplicates (e.g., knowledge point kp21, knowledge point kp22, knowledge point kp23);

[0075] Obtain a set of resources corresponding to the set of knowledge points after deduplication (i.e., a set of high-quality questions corresponding to the set of knowledge points after deduplication, such as high-quality questions q1-q10 corresponding to knowledge point kp21, high-quality questions q20-q25 corresponding to knowledge point kp22, and high-quality questions q100-q110 corresponding to knowledge point kp23);

[0076] Obtaining the target account's learning results for the above set of resources (for example, the target account's probability of correctly answering questions under the above knowledge points kp21, kp22, and kp23);

[0077] Data analysis and calculation: Specifically, the target account's mastery probability (i.e., mastery level) of each knowledge point is calculated by using a normal distribution model (or conditional probability model). Optionally, based on the number a1 of questions correctly answered by the target account in the excellent questions q1-q10 under knowledge point kp21, and the total number of excellent questions q1-q10, the target account's correct answer probability for questions under knowledge point kp21 is obtained: The method for determining the probability of the target account answering the questions under knowledge point kp22 and knowledge point kp23 correctly is similar. In particular, a normal distribution model is used to calculate the mastery of each knowledge point by the target account, including: determining the mastery probability of each knowledge point by the target account according to the following formula:

[0078]

[0079] Among them, x represents the knowledge point, μ represents the expectation of x, and σ represents the variance of x;

[0080] According to the normal distribution model, target profile information of the target account is obtained. Optionally, the profile information corresponding to multiple accounts is determined in a similar manner to obtain account profile 106, and the account profile 106 is stored in a relational database, including but not limited to a NoSQL database.

[0081] Step S703, receiving a target request sent by the target account via the terminal device 102;

[0082] Step S704, in response to the target request, retrieve corresponding resources from the educational resource library (i.e., the target resource set in the above embodiment);

[0083] Among them, retrieving the corresponding resources from the educational resource library through a search engine includes the following four steps: query understanding, recall, sorting, and re-arrangement. The retrieval process involves knowledge graphs and user portraits. Optionally, the search engine is built based on educational resource data, such as a full-text search engine.

[0084] Alternatively, if Figure 7 As shown, educational resource data may be stored in a relational data and / or object storage database.

[0085] Figure 8 FIG. 1 is a schematic diagram of a resource retrieval method according to another optional embodiment of the present invention. Figure 8 As shown, the method comprises the following steps:

[0086] Step S801, the target account sends a target request to the server 104 through the logged-in terminal device 102;

[0087] Step S802, the server 104 obtains the target search term;

[0088] Optionally, obtaining the target search term includes: parsing and understanding the query text in the user search request (i.e. parsing and understanding the query text in the target request to extract the target search term), which involves entity recognition, search category recognition and query keyword rewriting;

[0089] Optionally, the target account can be searched for different categories of resources, e.g. Figure 6 As shown in , the optional categories include: courseware, video, lesson plan, material and other categories; after receiving the target request, the search category in the target request is identified, so as to search for resources in this category;

[0090] Step S803: querying the account portrait 106 for the user portrait (i.e., the target portrait information of the target account in the above embodiment);

[0091] Step S804, returning target portrait information, wherein the target portrait information includes the target account's mastery of the target knowledge point (i.e., the learning result of the target account's learning of resources under the target knowledge point in the above embodiment);

[0092] Step S805, querying the knowledge graph information corresponding to the target account in the target knowledge graph 108;

[0093] Optionally, according to the target knowledge points that the target account is weak in, and the target search term, the target knowledge graph is queried to obtain knowledge graph information, wherein the knowledge graph information includes the preceding / successive knowledge points (i.e., the second knowledge point in the above embodiment) of the knowledge point that the target account is weak in, and the first knowledge point corresponding to the target search term, and / or the first knowledge point label of the first knowledge point and the second knowledge point label of the above second knowledge point;

[0094] Step S806, returning knowledge graph information;

[0095] Step S807, generating a recall condition based on the target search term and the acquired knowledge graph information;

[0096] Optionally, the recall condition carries the target search term, the first knowledge point, the second knowledge point, and / or the first knowledge point label and the second knowledge point label.

[0097] Step S808, the server 104 sends the recall condition to the search engine 112, and the search engine 112 searches for the corresponding resource from the educational resource library;

[0098] Step S809: the search engine 112 returns the search results (i.e., the target resource list in the above embodiment);

[0099] Optionally, the search results may include but are not limited to at least one of the following: data such as knowledge points, chapters, titles, texts or resource links corresponding to the resource;

[0100] Step S810: sorting the resources in the search results according to the target account's mastery of the knowledge points to obtain a sorted resource list (ie, the first resource list or the second resource list in the above embodiment);

[0101] Rearrange resources according to the operation rules and real-time feedback from the target account (i.e., re-arrange the sorted resource list) to obtain the final resource list;

[0102] Among them, the resources are rearranged according to the operation rules and the real-time feedback of the target account, including: adding the operation data (such as promotion resources) to the sorted resource list and removing the resources that the target account has accessed within a predetermined time period to obtain a final resource list;

[0103] Step S811: Send the final resource list to the target account.

[0104] Through the above embodiment, according to the target knowledge graph of educational resources, combined with the behavior information of the target account, the target account's mastery of knowledge points in the educational scenario is analyzed. When the target account retrieves resources, the target account's mastery of knowledge points and the target knowledge graph are combined to retrieve educational resources that are helpful to the target account, and through the relationship between resources, other related resources can be expanded to be retrieved, and the retrieved resources are related to the user's mastery of knowledge points, thereby realizing personalized recommendations for user searches and improving the user experience of educational resource searches.

[0105] It should be noted that the aforementioned method embodiments are briefly described, so they are all expressed as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0106] According to another aspect of the embodiment of the present invention, a resource retrieval device for implementing the above resource retrieval method is also provided. Fig. 9 As shown, the device comprises:

[0107] A first acquisition module 902 is used to acquire a target request sent by a target account, and to acquire a target search term from the target request, wherein the target request is used to request a query for resources matching the target search term;

[0108] The second acquisition module 904 is used to acquire the target portrait information of the target account, wherein the target portrait information is used to represent the learning result of the target account on the resource learning under the target knowledge point;

[0109] The third acquisition module 906 is used to acquire the knowledge graph information of the target account, wherein the target knowledge graph includes a group of knowledge points and the association relationship between the group of knowledge points, and the knowledge graph information includes a first knowledge point related to the target search term in the target knowledge graph and a second knowledge point related to the target knowledge point in the target knowledge graph, and / or a first knowledge point label of the first knowledge point and a second knowledge point label of the second knowledge point;

[0110] The sending module 908 is used to send a target resource list or a list of some resources in the target resource list to the target account according to the target search term and knowledge graph information, wherein the target resource list is a list of resources queried in the target resource collection, and the resources in the target resource list match the target search term and knowledge graph information.

[0111] In an embodiment of the present invention, a target request sent by a target account is obtained, and a target search term is obtained from the target request, wherein the target request is used to request a query for resources matching the target search term; target portrait information of the target account is obtained, wherein the target portrait information is used to represent the learning result of the target account on resources under the target knowledge point; knowledge graph information of the target account is obtained, wherein the target knowledge graph includes a group of knowledge points and associations between the group of knowledge points, and the knowledge graph information includes a first knowledge point related to the target search term in the target knowledge graph and a second knowledge point related to the target knowledge point in the target knowledge graph, and / or a first knowledge point label of the first knowledge point and a second knowledge point label of the second knowledge point; a target resource list or a list of some resources in the target resource list is sent to the target account according to the target search term and the knowledge graph information, wherein the target resource list is a list of resources queried in the target resource set, and the resources in the target resource list match the target search term and the knowledge graph information. When performing resource retrieval, the target portrait information and the target knowledge graph are combined to obtain the knowledge graph information of the target account, and resource retrieval is performed based on the target search terms and the knowledge graph information, thereby realizing intelligent resource retrieval by combining the target account's own learning results of the target knowledge points and the association between the various knowledge points in the target knowledge graph. As a result, for target accounts with different learning results, resources that are suitable for their level can be retrieved separately, so that the retrieval results reflect the personalized needs of different target accounts, rather than retrieving a single resource retrieval result for the same keyword, enriching the content of the resource retrieval results, and improving the matching degree of the resource retrieval results with the target account. Therefore, the technical problem of low matching degree between the resource retrieval results and the target account is solved, the matching degree between the resource retrieval results and the target account is improved, and the user experience is improved.

[0112] Optionally, the above-mentioned third acquisition module is also used to: query the knowledge points related to the above-mentioned target search term in the above-mentioned target knowledge graph to obtain the above-mentioned first knowledge point; query the knowledge points related to the above-mentioned target knowledge point in the above-mentioned target knowledge graph to obtain the above-mentioned second knowledge point; and / or query the knowledge point label of the above-mentioned first knowledge point in the above-mentioned target knowledge graph to obtain the above-mentioned first knowledge point label; query the knowledge point label of the above-mentioned second knowledge point in the above-mentioned target knowledge graph to obtain the above-mentioned second knowledge point label.

[0113] Optionally, the above-mentioned third acquisition module is also used to: query the preceding first-level knowledge points or preceding multi-level knowledge points of some or all of the above-mentioned target knowledge points in the above-mentioned target knowledge graph to obtain a third knowledge point, wherein the above-mentioned second knowledge point includes the above-mentioned third knowledge point; and / or query the post-first-level knowledge points or post-multi-level knowledge points of some or all of the above-mentioned target knowledge points in the above-mentioned target knowledge graph to obtain a fourth knowledge point, wherein the above-mentioned second knowledge point includes the above-mentioned fourth knowledge point.

[0114] Optionally, the third acquisition module is also used to: when the target knowledge point includes a fifth knowledge point and a sixth knowledge point, query the knowledge points related to the fifth knowledge point in the target knowledge graph, wherein the target portrait information indicates that the learning result of the target account on the resources under the fifth knowledge point does not meet the preset conditions, and the learning result of the target account on the resources under the sixth knowledge point meets the preset conditions.

[0115] Optionally, the above-mentioned device also includes a retrieval module, which is used to: when the above-mentioned knowledge graph information includes the above-mentioned first knowledge point and the above-mentioned second knowledge point, query the resources matching the above-mentioned target search term under the above-mentioned first knowledge point in the above-mentioned target resource set to obtain the first resource, wherein the above-mentioned target resource set includes resources under multiple knowledge points, and the above-mentioned multiple knowledge points include the above-mentioned first knowledge point and the above-mentioned second knowledge point; query the resources matching the above-mentioned target search term under the above-mentioned second knowledge point in the above-mentioned target resource set to obtain the second resource, wherein the above-mentioned target resource list includes the above-mentioned first resource and the above-mentioned second resource.

[0116] Optionally, the above-mentioned device also includes a retrieval module, which is used to: when the above-mentioned knowledge graph information includes the above-mentioned first knowledge point label and the above-mentioned second knowledge point label, query the resources matching the above-mentioned target search term under the above-mentioned first knowledge point label in the above-mentioned target resource set to obtain a third resource, wherein the above-mentioned target resource set includes resources under multiple knowledge point labels, the above-mentioned multiple knowledge point labels include the above-mentioned first knowledge point label and the above-mentioned second knowledge point label, and each of the above-mentioned multiple knowledge point labels has one or more knowledge points; query the resources matching the above-mentioned target search term under the above-mentioned second knowledge point label in the above-mentioned target resource set to obtain a fourth resource, wherein the above-mentioned target resource list includes the above-mentioned third resource and the above-mentioned fourth resource.

[0117] Optionally, the sending module is further used for: in the case of sending the target resource list to the target account, sorting the resources in the target resource list according to the mastery of the corresponding knowledge points represented by the first learning result to obtain a first resource list, wherein the first learning result is the learning result of the target account learning the resources under the first group of knowledge points, the learning result represented by the target portrait information includes the first learning result, and the first group of knowledge points are the knowledge points to which the resources included in the target resource list belong; sending the first resource list to the target account; or in the case of sending a list of some resources in the target resource list to the target account, sorting the resources in the list of some resources according to the mastery of the corresponding knowledge points represented by the second learning result to obtain a second resource list, wherein the second learning result is the learning result of the target account learning the resources under the second group of knowledge points, the learning result represented by the target portrait information includes the second learning result, and the second group of knowledge points are the knowledge points to which the resources included in the list of some resources belong; sending the second resource list to the target account.

[0118] Optionally, the sending module is further used to: when sending the target resource list to the target account, send a first learning result to the target account, wherein the first learning result is the learning result of the target account learning the resources under the first group of knowledge points, the learning result represented by the target portrait information includes the first learning result, and the first group of knowledge points are the knowledge points to which the resources included in the target resource list belong; or when sending a list of some resources in the target resource list to the target account, send a second learning result to the target account, wherein the second learning result is the learning result of the target account learning the resources under the second group of knowledge points, the learning result represented by the target portrait information includes the second learning result, and the second group of knowledge points are the knowledge points to which the resources included in the list of some resources belong.

[0119] Optionally, the first knowledge point label is used to indicate the chapter where the first knowledge point is located, or the examination scope corresponding to the first knowledge point; the second knowledge point label is used to indicate the chapter where the second knowledge point is located, or the examination scope corresponding to the second knowledge point.

[0120] According to another aspect of the embodiment of the present invention, an electronic device for implementing the above resource retrieval method is also provided. The electronic device may be Figure 1 The server 104 shown in FIG. 1 is shown in FIG. 104. This embodiment is described by taking the electronic device as a server as an example. Fig.10As shown, the electronic device includes a memory 1102 and a processor 1104. The memory 1102 stores a computer program, and the processor 1104 is configured to execute the steps in any of the above method embodiments through the computer program.

[0121] Optionally, in this embodiment, the electronic device may be located in at least one network device among a plurality of network devices of a computer network.

[0122] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0123] S1, obtaining a target request sent by a target account, and obtaining a target search term from the target request, wherein the target request is used to request a query for resources matching the target search term;

[0124] S2, obtaining target portrait information of the target account, wherein the target portrait information is used to represent the learning result of the target account on the resource learning under the target knowledge point;

[0125] S3, obtaining the knowledge graph information of the target account, wherein the target knowledge graph includes a group of knowledge points and the association relationship between the group of knowledge points, and the knowledge graph information includes a first knowledge point related to the target search term in the target knowledge graph and a second knowledge point related to the target knowledge point in the target knowledge graph, and / or a first knowledge point label of the first knowledge point and a second knowledge point label of the second knowledge point;

[0126] S4, based on the target search terms and knowledge graph information, sending a target resource list or a list of some resources in the target resource list to the target account, wherein the target resource list is a list of resources queried in the target resource set, and the resources in the target resource list match the target search terms and knowledge graph information.

[0127] Alternatively, a person skilled in the art may understand that: Fig.10 The structure shown is for illustration only, and the electronic device may also be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a PDA, a mobile Internet device (MID), a PAD, and other terminal devices. Fig.10 The electronic device and the electronic equipment described above are not limited in structure. Fig.10 More or fewer components (such as network interfaces, etc.) as shown in, or with Fig.10 Different configurations are shown.

[0128] Among them, the memory 1102 can be used to store software programs and modules, such as the program instructions / modules corresponding to the resource retrieval method and device in the embodiment of the present invention. The processor 1104 executes various functional applications and data processing by running the software programs and modules stored in the memory 1102, that is, to implement the above-mentioned resource retrieval method. The memory 1102 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 1102 may further include a memory remotely located relative to the processor 1104, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. Among them, the memory 1102 can be specifically, but not limited to, used for information such as target portrait information, target knowledge graphs, and target resource collections. As an example, if Fig.10 As shown, the memory 1102 may include but is not limited to the first acquisition module 902, the second acquisition module 904, the third acquisition module 906 and the sending module 908 in the resource search device. In addition, it may also include but is not limited to other module units in the resource search device, which will not be repeated in this example.

[0129] Optionally, the transmission device 1106 is used to receive or send data via a network. Specific examples of the network may include a wired network and a wireless network. In one example, the transmission device 1106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices and routers via a network cable so as to communicate with the Internet or a local area network. In one example, the transmission device 1106 is a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0130] In addition, the electronic device further includes: a display 1108 for displaying data; and a connection bus 1110 for connecting various module components in the electronic device.

[0131] In other embodiments, the terminal device or server may be a node in a distributed system, wherein the distributed system may be a blockchain system, and the blockchain system may be a distributed system formed by connecting the multiple nodes through network communication. Among them, the nodes may form a peer-to-peer (P2P, Peer To Peer) network, and any form of computing device, such as a server, terminal and other electronic devices, may become a node in the blockchain system by joining the peer-to-peer network.

[0132] According to one aspect of the present application, a computer program product or computer program is provided, the computer program product or computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the resource retrieval method provided in the above various optional implementations. Wherein, the computer program is configured to execute the steps of any of the above method embodiments when running.

[0133] Optionally, in this embodiment, the computer-readable storage medium may be configured to store a computer program for performing the following steps:

[0134] S1, obtaining a target request sent by a target account, and obtaining a target search term from the target request, wherein the target request is used to request a query for resources matching the target search term;

[0135] S2, obtaining target portrait information of the target account, wherein the target portrait information is used to represent the learning result of the target account on the resource learning under the target knowledge point;

[0136] S3, obtaining the knowledge graph information of the target account, wherein the target knowledge graph includes a group of knowledge points and the association relationship between the group of knowledge points, and the knowledge graph information includes a first knowledge point related to the target search term in the target knowledge graph and a second knowledge point related to the target knowledge point in the target knowledge graph, and / or a first knowledge point label of the first knowledge point and a second knowledge point label of the second knowledge point;

[0137] S4, based on the target search terms and knowledge graph information, sending a target resource list or a list of some resources in the target resource list to the target account, wherein the target resource list is a list of resources queried in the target resource set, and the resources in the target resource list match the target search terms and knowledge graph information.

[0138] Optionally, in this embodiment, a person of ordinary skill in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by instructing hardware related to the terminal device through a program, and the program may be stored in a computer-readable storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc.

[0139] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0140] If the integrated units in the above embodiments are implemented in the form of software functional units and sold or used as independent products, they can be stored in the above computer-readable storage medium. Based on such understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling one or more computer devices (which can be personal computers, servers or network devices, etc.) to perform all or part of the steps of the above methods of various embodiments of the present invention.

[0141] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0142] In the several embodiments provided in the present application, it should be understood that the disclosed client can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0143] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple 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.

[0144] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0145] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A resource retrieval method, characterized in that: include: Obtaining a target request sent by a target account, and obtaining a target search term from the target request, wherein the target request is used to request a query for resources matching the target search term; Acquire target profile information of the target account, wherein the target profile information is used to represent the learning result of the target account on the resource learning under the target knowledge point; Acquire the knowledge graph information of the target account, wherein the target knowledge graph includes a group of knowledge points and associations between the group of knowledge points, and the knowledge graph information includes a first knowledge point related to the target search term in the target knowledge graph and a second knowledge point related to the target knowledge point in the target knowledge graph, and / or a first knowledge point label of the first knowledge point and a second knowledge point label of the second knowledge point; Based on the target search term and the knowledge graph information, a target resource list or a list of some resources in the target resource list is sent to the target account, wherein the target resource list is a list of resources queried in a target resource set, and the resources in the target resource list match the target search term and the knowledge graph information.

2. The method according to claim 1, characterized in that The obtaining of the knowledge graph information of the target account includes: Querying the target knowledge graph for knowledge points related to the target search term to obtain the first knowledge point; querying the target knowledge graph for knowledge points related to the target knowledge point to obtain the second knowledge point; and / or The knowledge point label of the first knowledge point is queried in the target knowledge graph to obtain the first knowledge point label; the knowledge point label of the second knowledge point is queried in the target knowledge graph to obtain the second knowledge point label.

3. The method according to claim 2, characterized in that The step of searching the target knowledge graph for knowledge points related to the target knowledge point to obtain the second knowledge point includes: Searching the target knowledge graph for the preceding first-level knowledge points or preceding multi-level knowledge points of some or all of the target knowledge points to obtain a third knowledge point, wherein the second knowledge point includes the third knowledge point; and / or The target knowledge graph is queried for post-first-level knowledge points or post-multi-level knowledge points of some or all of the target knowledge points to obtain a fourth knowledge point, wherein the second knowledge point includes the fourth knowledge point.

4. The method according to claim 2, characterized in that: The step of searching the target knowledge graph for knowledge points related to the target knowledge point to obtain the second knowledge point includes: In the case that the target knowledge point includes the fifth knowledge point and the sixth knowledge point, the knowledge points related to the fifth knowledge point are queried in the target knowledge graph, wherein the target portrait information indicates that the learning result of the target account on the resources under the fifth knowledge point does not meet the preset conditions, and the learning result of the target account on the resources under the sixth knowledge point meets the preset conditions.

5. The method according to claim 1, characterized in that Before sending a target resource list or a list of some resources in the target resource list to the target account according to the target search term and the knowledge graph information, the method further includes: In the case where the knowledge graph information includes the first knowledge point and the second knowledge point, searching the target resource set for resources matching the target search term under the first knowledge point to obtain a first resource, wherein the target resource set includes resources under multiple knowledge points, and the multiple knowledge points include the first knowledge point and the second knowledge point; The target resource set is searched for resources matching the target search term under the second knowledge point to obtain second resources, wherein the target resource list includes the first resources and the second resources.

6. The method according to claim 1, characterized in that Before sending a target resource list or a list of some resources in the target resource list to the target account according to the target search term and the knowledge graph information, the method further includes: In the case where the knowledge graph information includes the first knowledge point label and the second knowledge point label, searching the target resource set for resources matching the target search term under the first knowledge point label to obtain a third resource, wherein the target resource set includes resources under multiple knowledge point labels, the multiple knowledge point labels include the first knowledge point label and the second knowledge point label, and each of the multiple knowledge point labels has one or more knowledge points; The target resource set is searched for resources matching the target search term under the second knowledge point tag to obtain a fourth resource, wherein the target resource list includes the third resource and the fourth resource.

7. The method according to claim 1, characterized in that The sending a target resource list or a list of some resources in the target resource list to the target account according to the target search term and the knowledge graph information includes: In the case of sending the target resource list to the target account, sorting the resources in the target resource list according to the mastery of the corresponding knowledge points represented by the first learning result to obtain a first resource list, wherein the first learning result is the learning result of the target account learning the resources under the first group of knowledge points, the learning results represented by the target portrait information include the first learning result, and the first group of knowledge points are the knowledge points to which the resources included in the target resource list belong; sending the first resource list to the target account; or In the case of sending a list of some resources in the target resource list to the target account, sort the resources in the list of some resources according to the mastery of the corresponding knowledge points represented by the second learning result to obtain a second resource list, wherein the second learning result is the learning result of the target account learning the resources under the second group of knowledge points, the learning results represented by the target portrait information include the second learning result, and the second group of knowledge points are the knowledge points to which the resources included in the list of some resources belong; sending the second resource list to the target account.

8. The method according to claim 1, characterized in that The method further comprises: In the case of sending the target resource list to the target account, sending a first learning result to the target account, wherein the first learning result is a learning result of the target account learning resources under a first group of knowledge points, the learning results represented by the target portrait information include the first learning result, and the first group of knowledge points are knowledge points to which the resources included in the target resource list belong; or In the case of sending a list of some resources in the target resource list to the target account, a second learning result is sent to the target account, wherein the second learning result is a learning result of the target account learning the resources under a second group of knowledge points, the learning results represented by the target portrait information include the second learning result, and the second group of knowledge points are the knowledge points to which the resources included in the list of some resources belong.

9. The method according to claim 1, characterized in that: The first knowledge point label is used to indicate the chapter where the first knowledge point is located, or the examination scope corresponding to the first knowledge point; the second knowledge point label is used to indicate the chapter where the second knowledge point is located, or the examination scope corresponding to the second knowledge point.

10. A resource search device, characterized in that: include: A first acquisition module is used to acquire a target request sent by a target account, and to acquire a target search term from the target request, wherein the target request is used to request a query for resources matching the target search term; A second acquisition module is used to acquire target portrait information of the target account, wherein the target portrait information is used to represent the learning result of the target account on the resource learning under the target knowledge point; A third acquisition module is used to acquire knowledge graph information of the target account, wherein the target knowledge graph includes a group of knowledge points and associations between the group of knowledge points, and the knowledge graph information includes a first knowledge point related to the target search term in the target knowledge graph and a second knowledge point related to the target knowledge point in the target knowledge graph, and / or a first knowledge point label of the first knowledge point and a second knowledge point label of the second knowledge point; A sending module is used to send a target resource list or a list of some resources in the target resource list to the target account according to the target search term and the knowledge graph information, wherein the target resource list is a list of resources queried in the target resource set, and the resources in the target resource list match the target search term and the knowledge graph information.

11. The device according to claim 10, characterized in that The obtaining of the third obtaining module is further used for: Searching the target knowledge graph for knowledge points related to the target search term to obtain the first knowledge point; searching the target knowledge graph for knowledge points related to the target knowledge point to obtain the second knowledge point; and / or Querying the knowledge point label of the first knowledge point in the target knowledge graph to obtain the first knowledge point label; The knowledge point label of the second knowledge point is queried in the target knowledge graph to obtain the second knowledge point label.

12. The device according to claim 11, characterized in that The third acquisition module is further used for: Searching the target knowledge graph for the preceding first-level knowledge points or preceding multi-level knowledge points of some or all of the target knowledge points to obtain a third knowledge point, wherein the second knowledge point includes the third knowledge point; and / or The target knowledge graph is queried for post-first-level knowledge points or post-multi-level knowledge points of some or all of the target knowledge points to obtain a fourth knowledge point, wherein the second knowledge point includes the fourth knowledge point.

13. The device according to claim 11, characterized in that The third acquisition module is further used for: In the case that the target knowledge point includes the fifth knowledge point and the sixth knowledge point, the knowledge points related to the fifth knowledge point are queried in the target knowledge graph, wherein the target portrait information indicates that the learning result of the target account on the resources under the fifth knowledge point does not meet the preset conditions, and the learning result of the target account on the resources under the sixth knowledge point meets the preset conditions.

14. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein the program executes the method described in any one of claims 1 to 9 when executed.

15. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 9 through the computer program.

Images