Knowledge tag retrieval method and device, computer equipment and storage medium

Abstract

The invention discloses a knowledge tag retrieval method and device, computer equipment and a storage medium, in the application, at least one first knowledge tag is matched based on retrieval information, and a first tag category corresponding to the first knowledge tag is determined; obtaining a hierarchical relationship between second knowledge tags belonging to each preset tag category and the preset tag categories; then, based on a hierarchical relationship between preset label categories, determining a hierarchical sequence of the first label categories, and according to the hierarchical sequence, taking the first label category in each hierarchy as a target label category; based on the first knowledge tag under the target tag category determined by each level, filtering a second knowledge tag under a preset tag category after the target tag category of the level to obtain the filtered second knowledge tag of each level; and obtaining the retrieval result of the retrieval information on the basis of the filtered second knowledge tag of each level, so that the retrieval efficiency of knowledge retrieval by the user is improved.

Description

Technical Field

[0001] The present application relates to the field of Internet technology, and specifically to a knowledge tag retrieval method, device, computer equipment and storage medium. Background Art

[0002] Knowledge maintenance in the knowledge center requires labeling of knowledge, and users can filter knowledge by label. The external system accesses the knowledge center by passing parameters. The knowledge center will identify the knowledge label according to the received parameters and configuration, and then display it to the user operation page of the knowledge center for users to choose. However, after the label is displayed to the user, the user needs to select the label and then filter the knowledge. In related technologies, users are generally required to filter the label multiple times to see the desired knowledge. The user operation is cumbersome, which increases the user's usage cost and affects the user's knowledge retrieval efficiency. Summary of the invention

[0003] In response to the above technical problems, the embodiments of the present application provide a knowledge tag retrieval method, apparatus, computer device and storage medium to improve the efficiency of knowledge retrieval.

[0004] In a first aspect, an embodiment of the present application provides a knowledge tag retrieval method, comprising:

[0005] At least one first knowledge tag matched based on the search information, and determining a first tag category corresponding to the first knowledge tag;

[0006] Acquire the second knowledge tags belonging to each preset tag category and the hierarchical relationship between the preset tag categories;

[0007] Based on the hierarchical relationship between the preset tag categories, determine the hierarchical order of the first tag categories, and according to the hierarchical order, use the first tag category in each level as the target tag category;

[0008] Based on the first knowledge tags under the target tag category determined at each level, filtering the second knowledge tags under the preset tag category after the target tag category at the level to obtain the filtered second knowledge tags at each level;

[0009] Based on the second knowledge tags after filtering at each level, a search result of the search information is obtained.

[0010] In a second aspect, an embodiment of the present application provides a knowledge tag retrieval device, including:

[0011] A first determination module, configured to determine a first tag category corresponding to at least one first knowledge tag matched based on the search information;

[0012] An acquisition module, used to acquire second knowledge tags belonging to each preset tag category and the hierarchical relationship between the preset tag categories;

[0013] A second determination module is used to determine the hierarchical order of the first tag categories based on the hierarchical relationship between the preset tag categories, and according to the hierarchical order, take the first tag category in each level as the target tag category;

[0014] A filtering module, configured to filter the second knowledge tags under a preset tag category after the target tag category at the level based on the first knowledge tags under the target tag category determined at each level, to obtain the filtered second knowledge tags at each level;

[0015] The retrieval module is used to obtain the retrieval result of the retrieval information based on the second knowledge tags after filtering at each level.

[0016] In a third aspect, an embodiment of the present application further provides a computer device, including a memory storing a plurality of instructions; a processor loads instructions from the memory to execute the steps of any one of the practice knowledge tag retrieval methods provided in the embodiments of the present application.

[0017] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, which stores a plurality of instructions suitable for loading by a processor to execute the steps of any one of the knowledge tag retrieval methods provided in the embodiments of the present application.

[0018] In a fifth aspect, an embodiment of the present application further provides a computer program product, including a computer program or instructions, which, when executed by a processor, implements the steps of any one of the knowledge tag retrieval methods provided in the embodiments of the present application.

[0019] The scheme of the embodiment of the application is adopted, by matching at least one first knowledge tag based on the search information, and determining the first tag category corresponding to the first knowledge tag; obtaining the second knowledge tags belonging to each preset tag category and the hierarchical relationship between the preset tag categories; determining the hierarchical order of the first tag categories based on the hierarchical relationship between the preset tag categories, and taking the first tag category in each level as the target tag category according to the hierarchical order; based on the first knowledge tag under the target tag category determined at each level, filtering the second knowledge tags under the preset tag category after the target tag category at the level to obtain the filtered second knowledge tags at each level; based on the second knowledge tags after filtering at each level, obtaining the knowledge tag retrieval result of the search information, because it is based on the hierarchical relationship between the preset tag categories, and The first knowledge tag and the first tag category determine the second knowledge tag after filtering at each level, so as to realize the targeted determination of the second knowledge tag after filtering at each level according to the first knowledge tag and the corresponding first tag category, thereby improving the accuracy of the second knowledge tag after filtering at each level, and based on the hierarchical relationship between preset tag categories and the first tag category corresponding to each first knowledge tag, compared with the traditional method without distinguishing tag categories, direct screening is performed according to all the first knowledge tags, which reduces unnecessary screening operations and improves the efficiency of determining the second knowledge tag after filtering at each level, and obtains the retrieval results of the retrieval information based on the second knowledge tag after filtering at each level, thereby realizing automatic simulation of knowledge tags of multiple tag categories selected by users and improving the retrieval efficiency of users in knowledge retrieval. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 It is a schematic diagram of the application environment of the knowledge tag retrieval method provided in the embodiment of the present application;

[0022] Figure 2 This is a schematic diagram of an embodiment of the knowledge tag retrieval method provided in the embodiments of the present application;

[0023] Figure 3 It is a schematic diagram of link parameters carried by a user when jumping from an operating system to a middle platform provided in an embodiment of the present application;

[0024] Figure 4 It is a schematic diagram of the association relationship between knowledge and knowledge tags in a knowledge tag tree provided in an embodiment of the present application;

[0025] Figure 5 is a schematic diagram of the second knowledge tags of categories A, B, C, D and E provided in the embodiments of the present application;

[0026] Figure 6 is a schematic diagram of five label trees marked with knowledge provided in an embodiment of the present application;

[0027] Figure 7 is a schematic diagram of a label tree provided as categories B, C, D and E in an embodiment of the present application;

[0028] Figure 8 is a schematic diagram of a label tree of categories C, D and E provided in an embodiment of the present application;

[0029] Fig. 9 is a schematic diagram of a label tree of category E provided in an embodiment of the present application;

[0030] Fig.10 is a schematic diagram of the difference labels under the second label category of each target provided in the embodiment of the present application;

[0031] Fig.11 is a schematic diagram of the structure of the knowledge tag retrieval device provided in an embodiment of the present application;

[0032] Fig.12 It is a schematic diagram of the internal structure of the computer device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0033] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present application. At the same time, in the description of the embodiments of the present application, the terms "first", "second", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more features. In the description of the embodiments of the present application, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0034] In one embodiment of the present application, the knowledge tag retrieval method can be run on a local terminal device or a server. When the knowledge tag retrieval method is run on a server, the method can be implemented and executed based on a cloud interaction system, wherein the cloud interaction system includes a server and a client device.

[0035] In order to better understand the knowledge tag retrieval method, device, electronic device and storage medium provided in the embodiments of the present application, the application environment applicable to the embodiments of the present application is described below.

[0036] See also Figure 1 , Figure 1 FIG. 1 is a schematic diagram showing an application environment of a knowledge tag retrieval method provided by an embodiment of the present application. As an implementation mode, the knowledge tag retrieval method provided by an embodiment of the present application can be applied to an electronic device. The electronic device can be, for example, Figure 1 The server 110 shown in the figure can be connected to the terminal device 120 through a network. The network is used to provide a medium for a communication link between the server 110 and the terminal device 120. The network can include various connection types, such as a wired communication link, a wireless communication link, etc., which are not limited in the embodiments of the present application. Optionally, in other embodiments, the electronic device can also be a smart phone, a laptop computer, etc.

[0037] It should be understood that Figure 1 The server 110, network and terminal device 120 are merely illustrative. Depending on the implementation requirements, there may be any number of servers, networks and terminal devices. For example, the server 110 may be a physical server or a server cluster composed of multiple servers, and the terminal device 120 may be a mobile phone, a tablet, a desktop computer, a laptop computer, and the like. It is understood that the embodiments of the present application may also allow multiple terminal devices 120 to access the server 110 at the same time.

[0038] The following is a detailed description in conjunction with the accompanying drawings. In this embodiment, the execution subject is a server as an example. It should be noted that the description order of the following embodiments is not intended to limit the preferred order of the embodiments. Although the logical order is shown in the flow chart, in some cases, the steps shown or described may be performed in an order different from that shown in the accompanying drawings.

[0039] The knowledge tag retrieval method of this embodiment can be applied to scenarios where a user simulates automatic selection of multiple category tags, including but not limited to scenarios where customer service personnel query the knowledge they want to learn in the knowledge center.

[0040] In related technologies, the operation system can publish task parameters, such as a link for knowledge retrieval. The knowledge platform is a platform for providing knowledge retrieval to users. It includes knowledge tags and corresponding knowledge, so that users can quickly and accurately find the knowledge they need to retrieve based on knowledge tags. Users can use the task parameters of the operation platform, such as clicking on a link for knowledge retrieval, to jump to the knowledge platform for knowledge retrieval. The external system transmits parameters to the knowledge platform. For example, according to the link parameters carried by the user when jumping from the operation system to the knowledge platform by clicking on a link on the operation platform, the link parameters are identified to obtain multiple different categories of pending tags. The user selects the different categories of pending tags in turn according to the identified multiple different categories of pending tags, thereby realizing knowledge retrieval based on knowledge tags.

[0041] However, in the above-mentioned knowledge tag retrieval method, the target tag is determined according to the relationship between the carried link parameters and the knowledge tag, and the target tag is directly selected for knowledge retrieval. This makes it difficult to ensure the accuracy of the target tag, and the user needs to select the target tag multiple times, which reduces the efficiency of knowledge tag retrieval.

[0042] In order to solve the above problems, the present application provides a knowledge tag retrieval method, which can simultaneously determine the difference tags of multiple tag categories, simulate the user's selection of knowledge tags of multiple tag categories, and thus improve the user's knowledge retrieval efficiency.

[0043] Please refer to Figure 2 The specific process of the knowledge tag retrieval method can be as follows: Step 201 to Step 205, wherein:

[0044] Step 201: at least one first knowledge tag is matched based on the search information, and a first tag category corresponding to the first knowledge tag is determined.

[0045] The search information is information related to knowledge search. The first knowledge tag is a knowledge tag that matches the search information.

[0046] The first tag category is the tag category corresponding to the first knowledge tag, and the corresponding tag category can be determined according to the tag name of the first knowledge tag. Specifically, the relationship between the preset search information and the first knowledge tag is stored in the computer device, and at least one first knowledge tag that is matched can be determined according to the search information.

[0047] like Figure 3As shown, in one example, the search information is: user tag: white-collar; contract type: installment; user level: level 4. According to the preset relationship between the search information and the first knowledge tag, the first knowledge tags corresponding to the search information "user tag: white-collar; contract type: installment; user level: level 4" are determined to be D21, B21, and A1. The first tag categories of D21, B21, and A1 are: D, D, B, and A, respectively.

[0048] Step 202: Obtain the second knowledge tags belonging to each preset tag category and the hierarchical relationship between the preset tag categories.

[0049] The preset tag categories are multiple pre-set tag categories with a tag category hierarchy, and each preset tag category is configured with a number of second knowledge tags, and the corresponding preset tag category can be determined by the prefix identifier carried in the second knowledge tag. There is a hierarchical relationship between each preset tag category, and the hierarchical relationship can be determined according to the tag category of the preset tag category.

[0050] Exemplarily, the plurality of preset tag categories include five preset tag categories, namely A, B, C, D and E, and the tag category levels are A, B, C, D and E. The prefix identifier of the second knowledge tag A21 is A, and it can be determined that the preset tag category of A21 is category A.

[0051] The multiple preset tag categories at least include the first tag categories corresponding to all the first knowledge tags. Accordingly, the first tag category corresponding to the first knowledge tag can be determined by the prefix identifier carried in the first knowledge tag. Continuing with the three first knowledge tags D21, B21, and A1 in step 201 as an example, it can be determined that the first tag categories of D21, B21, and A1 are: D category, B category, and A category, respectively.

[0052] The second knowledge tag is a knowledge tag under each preset tag category. For example, the second knowledge tag under the A preset tag category can be A1, A2, and the second knowledge tag under the B preset tag category can be B1, B12. The hierarchical relationship between the A preset tag category and the B preset tag category is, for example, that the A level is higher than the B level.

[0053] Step 203: Determine the hierarchical order of the first tag categories based on the hierarchical relationship between the preset tag categories, and use the first tag category in each level as the target tag category according to the hierarchical order.

[0054] Among them, the hierarchical order is the hierarchical order of the first label category in the hierarchical relationship between preset label categories. By way of example, the first label categories in the step are: D category, B category, A category. Since the label category hierarchies of the preset label categories are A level, B level, C level, D level, and E level, their hierarchical order is A level-B level-D level.

[0055] The target label category refers to the first label category of the same level. For example, the first knowledge labels are A11, A1, D21, B21, B2, and D21, and their corresponding label levels are A level, A level, D level, B level, and B level. Since the hierarchy is A level-B level-D level, the target label categories are Category A (having first knowledge labels A11 and A1), Category B (having first knowledge labels B21 and B2), and Category D (having first knowledge label D21).

[0056] Specifically, the hierarchical order of each first label category in the hierarchical relationship between the preset label categories can be determined according to the hierarchical relationship between the preset label categories, and then the first label category in each level can be used as the target label category in turn according to the hierarchical order of the first label categories, so as to facilitate the subsequent knowledge label retrieval for the first knowledge label under the target label category of each level. Since the subsequent knowledge label retrieval is performed according to the hierarchical order of the first label category, the influence of the hierarchical order of the first label category on determining the efficiency of the retrieval label is fully considered, which reduces redundant calculations and is conducive to improving the retrieval speed of subsequent knowledge labels.

[0057] Step 204, based on the first knowledge tags under the target tag category determined at each level, the second knowledge tags under the preset tag category after the target tag category at the level are filtered to obtain the filtered second knowledge tags at each level.

[0058] Among them, the second knowledge tag after filtering at each level refers to the second knowledge tag under the preset tag category before the target tag category, and the second knowledge tag after filtering at each level after filtering the second knowledge tag under the preset tag category after the target tag category, that is, the retained second knowledge tag under the preset tag category of each level after filtering. The second knowledge tag after filtering at each level can be a difference tag of the second knowledge tag, that is, the difference tag is the second knowledge tag or part of the second knowledge tag, and the difference tag includes the knowledge tags in the second knowledge tags corresponding to each preset tag category. All the knowledge contained in each difference tag under the preset tag category is different from all the knowledge under the target first tag category in the first tag category, the level of the target first tag category is before the level of the preset tag category, and all the knowledge under the target first tag category is the knowledge contained in the first knowledge tag under the target first tag category. All the knowledge contained in each difference tag under the preset tag category is different from all the knowledge under the target first tag category in the first tag category.

[0059] For each difference tag under a preset tag category, all the knowledge contained in its difference tag is different from the knowledge contained in the first knowledge tag under the corresponding target first tag category, that is, the difference tag is a second knowledge tag in the second knowledge tag under the preset tag category that does not simultaneously have all the knowledge corresponding to the first knowledge tag, that is, a knowledge tag obtained by removing the second knowledge tag that simultaneously has all the knowledge corresponding to the first knowledge tag from the second knowledge tag under the preset tag category. Exemplarily, the knowledge contained in the difference tag under the B level is different from all the knowledge under the first knowledge tag under the A level. For example, all the knowledge contained in the first knowledge tag under the target first tag category is 1 and 2, and all the knowledge contained in the second knowledge tag under the B level is 1 and 3.

[0060] Specifically, the second knowledge tags under the preset tag category after the target tag category at each level can be filtered according to the first knowledge tags under the target tag category determined at the level, wherein the filtering rule can be to obtain the second knowledge tags after filtering at each level by filtering out the second knowledge tags under the preset tag category that simultaneously have all the knowledge corresponding to the first knowledge tags, thereby achieving targeted determination of the second knowledge tags after filtering at each level according to the first knowledge tags and the corresponding first tag categories, thereby improving the accuracy of the second knowledge tags after filtering at each level, and based on the tag category hierarchy between the preset tag categories and the first tag categories corresponding to each first knowledge tag, compared with the traditional method without distinguishing tag categories, directly filtering according to all the first knowledge tags reduces unnecessary screening operations, improves the efficiency of determining the second knowledge tags after filtering at each level, reduces subsequent redundant searches based on all the second knowledge tags, and is conducive to improving subsequent search efficiency.

[0061] In an example, the level of the target second label category is level A, all knowledge contained in the first knowledge label A1 under level A is 1 and 2, all knowledge contained in the second knowledge label B21 under level B is 1 and 4, and all knowledge contained in the second knowledge label B22 under level B is 1 and 3. Obviously, all knowledge of the second knowledge label B21 and the second knowledge label B22 is different from all knowledge contained in the first knowledge label A1, therefore, the second knowledge label B21 and the second knowledge label B22 are both difference labels.

[0062] In another example, the target second label category is at level B, and all knowledge contained in the first knowledge label B1 at level B is 1 and 2, and all knowledge contained in the second knowledge label C11 at level C is 1 and 3, and all knowledge contained in the second knowledge label C22 at level C is 1 and 2. Obviously, all knowledge contained in the second knowledge label C22 is no different from all knowledge contained in the first knowledge label B1. Therefore, the second knowledge label C22 is eliminated, and the second knowledge label C11 is a difference label.

[0063] Step 205, obtaining the search result of the search information based on the second knowledge tags after filtering at each level.

[0064] The second knowledge tag after filtering at each level is used as a computer device to simulate the tag selected by the user to perform knowledge retrieval.

[0065] Specifically, the computer device simulates the user selecting part or all of the second knowledge tags filtered at each level to perform knowledge retrieval based on the second knowledge tags filtered at each level, thereby obtaining the retrieval results of the retrieval information, realizing the automatic simulation of the user selecting the knowledge tags of the multi-tag category, and improving the user's retrieval efficiency. It can be understood that since the unfiltered tags in the second knowledge tags do not have a screening effect on knowledge retrieval, in this embodiment, after determining the second knowledge tags filtered at each level, the knowledge retrieval is performed according to the second knowledge tags filtered at each level, and the retrieval results of the retrieval information are obtained, thereby improving the retrieval efficiency of the user's knowledge retrieval.

[0066] The knowledge tag retrieval method provided in the embodiment of the present application,

[0067] By matching at least one first knowledge tag based on the search information, and determining the first tag category corresponding to the first knowledge tag; obtaining the second knowledge tags belonging to each preset tag category and the hierarchical relationship between the preset tag categories; determining the hierarchical order of the first tag categories based on the hierarchical relationship between the preset tag categories, and taking the first tag category in each level as the target tag category according to the hierarchical order; based on the first knowledge tag under the target tag category determined at each level, filtering the second knowledge tags under the preset tag category after the target tag category at that level, and obtaining the filtered second knowledge tags at each level; based on the second knowledge tags after filtering at each level, obtaining the knowledge tag retrieval result of the search information, because it is based on the hierarchical relationship between the preset tag categories and the first knowledge tags The second knowledge label after filtering at each level is determined by the label and the first label category, so as to realize the targeted determination of the second knowledge label after filtering at each level according to the first knowledge label and the corresponding first label category, thereby improving the accuracy of the second knowledge label after filtering at each level, and based on the hierarchical relationship between the preset label categories and the first label category corresponding to each first knowledge label, compared with the traditional method without distinguishing label categories, direct screening is performed according to all the first knowledge labels, which reduces unnecessary screening operations and improves the efficiency of determining the second knowledge label after filtering at each level, and obtains the retrieval results of the retrieval information based on the second knowledge label after filtering at each level, realizes automatic simulation of the knowledge label of multiple label categories selected by the user, and improves the retrieval efficiency of the user's knowledge retrieval.

[0068] In one embodiment, the first knowledge tag under the target tag category determined based on each level filters the second knowledge tag under the preset tag category after the target tag category at that level to obtain the second knowledge tag after filtering at each level, including: determining the current target first tag category to be processed based on the hierarchical order of the target tag category; updating the second knowledge tag for each preset tag category whose hierarchical order is after the target first tag category based on the first knowledge tag under the target first tag category; determining the preset tag category that is the same as the target first tag category and the preset tag category whose hierarchical order is before the target first tag category as the target second tag category, and determining the second knowledge tag under the target second tag category as a difference tag; returning to execute the step of determining the current target first tag category to be processed based on the hierarchical order of the first tag category until the current target first tag category to be processed is empty.

[0069] Among them, the target first label category can be the first label category that ranks first in the current hierarchical order. Continuing with the hierarchical order of A level-B level-D level in the above embodiment as an example, in the first process of determining the difference label, the corresponding target first label category is A category, in the second process of determining the difference label, the corresponding target first label category is B category, and in the third process of determining the difference label, the corresponding target first label category is D category. After three times of difference label determination, the determination of the second knowledge label after filtering at each level is completed.

[0070] The target second label category is a preset label category that is the same as the target first label category, and a preset label category that is before the target first label category in the hierarchical order. Continuing with the above embodiment, the first label categories are: Category D, Category B, Category A, and the target first label category is Category B as an example. Since Category B is the same as the target first label category, and the hierarchical order of Category A is before the target first label category Category B, it is determined that the target second label category is Category A and Category B.

[0071] Specifically, based on the hierarchical order of the first tag category, the target first tag category to be processed is determined. Then, based on the first knowledge tag under the target first tag category, the second knowledge tags are updated for each preset tag category whose hierarchical order is after the target first tag category, and the second knowledge tags are updated in this way according to the hierarchical order of the first tag category and the first knowledge tags. Next, the preset label category that is the same as the target first label category and the preset label category that is before the target first label category in the hierarchical order are determined as the target second label category, and the second knowledge label under the target second label category is determined as the second knowledge label after hierarchical filtering to obtain the second knowledge label after hierarchical filtering, until the current target first label category to be processed is empty, thereby realizing the screening of the difference labels in the second knowledge labels under all preset label categories, that is, the difference labels under the preset label category with a later hierarchical order are determined according to the difference labels in the second knowledge labels under the preset label category with a previous hierarchical order. There is no need to determine the second knowledge label after hierarchical filtering according to the second knowledge labels under each preset label category for the first knowledge label under each first label category, which reduces the calculation scope and avoids redundant calculations. At the same time, combined with the hierarchical order, it has the function of characterizing the inclusion relationship between the second knowledge labels, which greatly improves the accuracy of the calculation of the second knowledge label after hierarchical filtering.

[0072] In one embodiment, before obtaining a number of second knowledge tags belonging to each preset tag category, it includes: obtaining a knowledge tag relationship table for each preset tag category; for each preset tag category, building a tag tree based on the knowledge tag relationship table, and configuring knowledge for each tag in the tag tree to obtain a second knowledge tag.

[0073] Specifically, a knowledge label relationship table of each preset label category is obtained, and for each preset label category, a label tree is constructed based on the knowledge label relationship table, and knowledge is configured for each label in the label tree to obtain a second knowledge label, so that each second knowledge label is configured with knowledge, ensuring the validity of the second knowledge label, so as to improve the accuracy of the second knowledge label after hierarchical filtering based on the second knowledge label.

[0074] In a specific implementation method, the preset tag categories include 5 categories, namely A, B, C, D and E. The relationship between knowledge and tags is loaded from the database and initialized into the memory. A knowledge tag relationship table of each preset tag category is established. The knowledge tag relationship table of each preset tag category is shown in Table 1.

[0075] Table 1. Knowledge tag relationship table for each preset tag category

[0076] Knowledge Knowledge Tags 1 A1, B21, C21, D21, E11, E21 2 A1, B21, C21, D21, D22, E12, E22 3 A11, A2, B22, C3, D22, D31 4 A11, A2, B22, C3, D31

[0077] like Figure 4 As shown, it is a schematic diagram of the association relationship between knowledge and labels in a label tree, wherein the preset label category is category A, wherein the knowledge includes 1, 2, 3, 4, and the knowledge labels include A, A1, A2, A11, and A12, wherein A includes A1 and A2, and A1 includes A11 and A12.

[0078] According to the knowledge tag relationship table of each preset tag category, for each preset tag category, a tag tree is constructed based on the knowledge tag relationship table. Figure 5 The labels of the five label trees shown in the figure respectively indicate the corresponding knowledge, and five label trees marked with knowledge are obtained, namely, label trees A, B, C, D and E, and the labels on the label trees are the second knowledge labels. Figure 6 As shown, it is a schematic diagram of 5 label trees marked with knowledge.

[0079] In one embodiment, based on the first knowledge tag under the target first tag category, the second knowledge tag is updated for each preset tag category whose hierarchical order is after the target first tag category, including: obtaining the first knowledge from all the first knowledge tags under the target first tag category; determining the preset tag category whose hierarchical order is after the target first tag category; determining a set of second knowledge tags matching each of the first knowledge under the same preset tag category based on the first knowledge and the determined second knowledge tags under the preset tag category, wherein the second knowledge tags in the same second knowledge tag set contain the same first knowledge; finding the intersection and union of the second knowledge tag set under the same preset tag category, and obtaining a candidate difference tag by subtracting the intersection from the union, and updating the second knowledge tag under the preset tag category based on the candidate difference tag.

[0080] Specifically, the first knowledge is obtained from all the first knowledge tags under the target first tag category, and a preset tag category whose hierarchical order is after the target first tag category is determined. Based on the first knowledge and the second knowledge tags under the determined preset tag category, a set of second knowledge tags matching each first knowledge under the same preset tag category is determined, wherein the second knowledge tags in the same second knowledge tag set contain the same first knowledge. The intersection and union of the second knowledge tag sets under the same preset tag category are calculated, and a candidate difference tag is obtained by subtracting the intersection from the union, and the second knowledge tag under the preset tag category is updated based on the candidate difference tag. The calculation of the difference tag between the first knowledge tag and the second knowledge tag is realized, ensuring the accuracy of the difference tag calculation. It can be understood that in this embodiment, the intersection and union of the second knowledge label set under the same preset label category are calculated, and the candidate difference label is obtained by subtracting the intersection from the union. The second knowledge label under the preset label category is updated according to the candidate difference label, so that the updated second knowledge label filters out the intersection with the second knowledge label set under the same preset label category, that is, the knowledge label in which the second knowledge in the second knowledge label is the same as the first knowledge is filtered out, ensuring that all knowledge contained in the updated second knowledge label is different from all knowledge under the target first label category in the first label category, thereby ensuring that the updated second knowledge label is a second knowledge label after hierarchical filtering.

[0081] In a specific embodiment, according to Table 1, Figure 4-Figure 6 Taking the five label trees marked with knowledge and the first knowledge labels D21, B21, and A1 as examples, the process of updating the second knowledge label is explained: the hierarchical order is A level-B level-D level. First, the target first label category is category A, and the corresponding first knowledge is 1, 2, 3, and 4, so the determined preset label category is the preset label category after category A, that is, the determined preset label category is category B, category C, category D, and category E, and the corresponding second knowledge labels are category B, category C, category D, and category E. The corresponding four label trees marked with knowledge, according to the first knowledge 1, 2, 3, 4, from category B, category C, category D, and category E Among the 4 label trees marked with knowledge, the intersection of the second knowledge labels in the first knowledge 1, 2, 3 and 4 is calculated, that is, the set {C21, D21, E11, E21} corresponding to the second knowledge label with the second knowledge being 1, the set {C21, D21, D22, E12, E22} corresponding to the second knowledge label with the second knowledge being 2, the set {C3, D22, D31} corresponding to the second knowledge label with the second knowledge being 3, and the set {C3, D31} corresponding to the second knowledge label with the second knowledge being 4. Obviously, their intersection is empty. Therefore, the updated second knowledge labels are the 4 label trees marked with knowledge corresponding to category B, category C, category D and category E.

[0082] In one embodiment, based on the first knowledge tag under the target first tag category, the second knowledge tag is updated for each preset tag category that follows the target first tag category in a hierarchical order, including: if there is no second knowledge tag that is the same as the first knowledge tag of the target first tag category under the same preset tag category as the target first tag category, the first knowledge tag is deleted; based on the remaining first knowledge tags under the target first tag category, the second knowledge tags are updated for each preset tag category that follows the target first tag category in a hierarchical order.

[0083] Specifically, for the first knowledge tag under the target first label category, if there is no second knowledge tag that is the same as the first knowledge tag of the target first label category under the same preset label category as the target first label category, it indicates that the first knowledge tag under the target first label category has no second knowledge tag. Therefore, the first knowledge tag is deleted without determining the second knowledge tag after hierarchical filtering. Then, based on the remaining first knowledge tags under the target first label category, the second knowledge tags are updated for each preset label category that is after the target first label category in the hierarchical order.

[0084] In one embodiment, if the current target first label category to be processed is empty, there is still a preset label category, the preset label category is determined as the target second label category, and the second knowledge label under the target second label category is used as the second knowledge label after hierarchical filtering.

[0085] Specifically, when the current target first label category to be processed is empty and there is a preset label category, the preset label category is determined as the target second label category, and the second knowledge label under the target second label category is used as the second knowledge label after filtering at each level, thereby avoiding the omission of difference labels and ensuring the complete accuracy of the second knowledge labels after hierarchical filtering.

[0086] In one embodiment, after obtaining the retrieval results of the retrieval information based on each of the difference tags, it also includes: displaying the retrieval results through a client interface corresponding to the retrieval information; wherein, on the client interface, the first knowledge tag in the second knowledge tag after the hierarchical filtering is displayed in a target display style, wherein the target display style is used to indicate that the corresponding first knowledge tag is in a selected state.

[0087] Specifically, the search results are displayed through the client interface corresponding to the search information, and the first knowledge tag in the second knowledge tag after hierarchical filtering can also be displayed in the client interface in a target display style, wherein the target display style is used to indicate that the corresponding first knowledge tag is in a selected state. For example, the first knowledge tag in the difference tag can be marked with a set color, so that the user can intuitively view the knowledge tag search results and improve the user experience.

[0088] In a specific embodiment, the first knowledge tags are D21, B21, A1, the preset tag categories include A category, B category, C category, D category and E category, and Figure 5 Take the second knowledge labels of categories A, B, C, D and E in the example, where the hierarchical order of each preset label category is A-B-C-D and E, and the hierarchical order of the first label category is A-B-D. Based on the hierarchical order of the first label category and the first knowledge label, the implementation process of determining the second knowledge label (difference label) after hierarchical filtering is as follows:

[0089] Step S1: Determine that the target first label category to be processed is category A, and set the preset label category that is the same as the target first label category to category A, and the preset label category before the target first label category in the hierarchical order is empty. Therefore, the target second label category is category A, and the second knowledge label under category A is determined as a difference label.

[0090] According to the A1 label, the second knowledge label is updated for each preset label category that is after the A category, namely, the B category, the C category, the D category, and the E category. The updating process is as follows: the first knowledge is obtained from the first knowledge label under the target first label category, the preset label category that is after the target first label category in the hierarchical order is determined, and the first knowledge is obtained as 1, 2, 3, and 4 according to A1 and its corresponding leaf node A11, and the second knowledge label that contains the first knowledge 1, 2, 3, and 4 is deleted from the label tree of the B category, the C category, the D category, and the E category. Figure 7 As shown, they are schematic diagrams of label trees for category B, category C, category D, and category E, respectively, and the labels in the corresponding label trees are all second knowledge labels.

[0091] Step S2: Determine that the current target first label category to be processed is category B, and set the preset label category B, which is the same as the target first label category, and the preset label category before the target first label category in the hierarchical order to category A. Therefore, the target second label category is category A and category B, and the second knowledge label under category A and category B is determined as the difference label.

[0092] According to the B21 label, the second knowledge label is updated for each preset label category that is after the B category, namely, the C category, the D category, and the E category. The updating process is as follows: the first knowledge is obtained from the first knowledge label under the target first label category, the preset label category that is after the target first label category in the hierarchical order is determined, and according to B21, the first knowledge is obtained as 1 and 2, and the second knowledge label that contains both the first knowledge 1 and 2 is deleted from the label tree of the C category, the D category, and the E category. Figure 8 As shown, they are schematic diagrams of label trees of categories C, D and E, respectively, and the labels in the corresponding label trees are all second knowledge labels.

[0093] Step S3: Determine that the current target first label category to be processed is category D, and the preset label category D that is the same as the target first label category, and the preset label categories before the target first label category in the hierarchical order are category A and category B. Therefore, the target second label categories are category A, category B, category C and category D, and the second knowledge labels under category A, category B, category C and category D are determined as difference labels.

[0094] According to the D21 label, the second knowledge label is updated for each preset label category that is after the D category, that is, the E category. The updating process is as follows: obtain the first knowledge from the first knowledge label under the target first label category, determine the preset label category that is after the target first label category, obtain the first knowledge as 1 and 2 according to D21, and delete the second knowledge label that contains both the first knowledge 1 and 2 from the label tree of the E category. Fig. 9 As shown, it is a schematic diagram of the label tree of category E, and the labels in the corresponding label tree are all second knowledge labels.

[0095] It is worth noting that after step S3, when the current target first label category to be processed is empty, there is still an unfiltered preset label category E, the preset label category E is determined as the target second label category, and the second knowledge label under the target second label category is used as the second knowledge label after hierarchical filtering, that is, the difference label. Fig.10 , which is a schematic diagram of the difference labels under the second label category of each target.

[0096] It should be understood that, although each step in the flowcharts involved in the above embodiments is displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0097] Based on the same inventive concept, the embodiment of the present application also provides a knowledge tag retrieval device for implementing the above-mentioned knowledge tag retrieval method, and a knowledge tag retrieval device for implementing the above-mentioned knowledge tag retrieval method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in the embodiments of one or more knowledge tag retrieval devices provided below can refer to the limitations of the knowledge tag retrieval method above, and the specific limitations will not be repeated here.

[0098] This embodiment also provides a knowledge tag retrieval device, which can be integrated into a terminal device. Fig.11 As shown, the knowledge tag retrieval device 1200 may include:

[0099] A first determination module 1201 is configured to determine a first tag category corresponding to at least one first knowledge tag matched based on the search information;

[0100] An acquisition module 1202 is used to acquire second knowledge tags belonging to each preset tag category and the hierarchical relationship between the preset tag categories;

[0101] A second determination module 1203 is used to determine the hierarchical order of the first tag categories based on the hierarchical relationship between the preset tag categories, and according to the hierarchical order, take the first tag category in each level as the target tag category;

[0102] A filtering module 1204 is configured to filter the second knowledge tags under the preset tag category after the target tag category at the level based on the first knowledge tags under the target tag category determined at each level, to obtain the filtered second knowledge tags at each level;

[0103] The retrieval module 1204 is used to obtain the retrieval result of the retrieval information based on the second knowledge tags after filtering at each level.

[0104] The above-mentioned knowledge tag retrieval device matches at least one first knowledge tag based on the retrieval information and determines the first tag category corresponding to the first knowledge tag; obtains the second knowledge tags belonging to each preset tag category and the hierarchical relationship between the preset tag categories; determines the hierarchical order of the first tag categories based on the hierarchical relationship between the preset tag categories, and uses the first tag category in each level as the target tag category according to the hierarchical order; based on the first knowledge tag under the target tag category determined at each level, filters the second knowledge tags under the preset tag category after the target tag category at the level to obtain the filtered second knowledge tags at each level; based on the second knowledge tags after filtering at each level, obtains the knowledge tag retrieval result of the retrieval information, because it is based on the hierarchical relationship between the preset tag categories, and The first knowledge tag and the first tag category determine the second knowledge tag after filtering at each level, so as to realize the targeted determination of the second knowledge tag after filtering at each level according to the first knowledge tag and the corresponding first tag category, thereby improving the accuracy of the second knowledge tag after filtering at each level, and based on the hierarchical relationship between preset tag categories and the first tag category corresponding to each first knowledge tag, compared with the traditional method without distinguishing tag categories, direct screening is performed according to all the first knowledge tags, which reduces unnecessary screening operations and improves the efficiency of determining the second knowledge tag after filtering at each level, and obtains the retrieval results of the retrieval information based on the second knowledge tag after filtering at each level, thereby realizing automatic simulation of knowledge tags of multiple tag categories selected by users and improving the retrieval efficiency of users in knowledge retrieval.

[0105] In some embodiments, the filtering module 1204 is specifically used to:

[0106] Based on the hierarchical order of the target label categories, determining the first label category of the target to be processed currently;

[0107] Based on the first knowledge tag under the target first tag category, updating the second knowledge tag for each preset tag category that is after the target first tag category in hierarchical order;

[0108] Determine the preset tag category that is the same as the target first tag category and the preset tag category that is before the target first tag category in hierarchical order as the target second tag category, and determine the second knowledge tag under the target second tag category as the second knowledge tag after hierarchical filtering;

[0109] Return to the step of determining the target first tag category currently to be processed based on the hierarchical order of the first tag category until the target first tag category currently to be processed is empty.

[0110] In some embodiments, the filtering module 1204 is further configured to:

[0111] Acquire first knowledge from all first knowledge tags under the target first tag category;

[0112] Determine a preset tag category that is subsequent to the target first tag category in hierarchical order;

[0113] Based on the first knowledge and the determined second knowledge tags under the preset tag category, determine a second knowledge tag set matching each of the first knowledge under the same preset tag category, wherein the second knowledge tags in the same second knowledge tag set contain the same first knowledge;

[0114] The intersection and union of the second knowledge tag sets under the same preset tag category are calculated, and a candidate difference tag is obtained by subtracting the intersection from the union, and the second knowledge tag under the preset tag category is updated based on the candidate difference tag.

[0115] In some embodiments, the filtering module 1204 is further configured to:

[0116] If there is no second knowledge tag that is the same as the first knowledge tag of the target first tag category under the same preset tag category as the target first tag category, the first knowledge tag is deleted;

[0117] Based on the remaining first knowledge tags under the target first tag category, the second knowledge tags are updated for each preset tag category that follows the target first tag category in a hierarchical order.

[0118] In some embodiments, the knowledge tag retrieval device further includes:

[0119] The third determination module is used to, if the current target first label category to be processed is empty, there is a preset label category, determine the preset label category as the target second label category, and use the second knowledge label under the target second label category as the second knowledge label after hierarchical filtering.

[0120] In some embodiments, the knowledge tag retrieval device further includes:

[0121] A display module, used to display the search results through a client interface corresponding to the search information;

[0122] Among them, on the client interface, the first knowledge tag in the second knowledge tags after the hierarchical filtering is displayed in a target display style, wherein the target display style is used to indicate that the corresponding first knowledge tag is in a selected state.

[0123] In some embodiments, the knowledge tag retrieval device further includes:

[0124] A first acquisition module is used to acquire a knowledge tag relationship table of each preset tag category;

[0125] The construction module is used to construct a tag tree for each preset tag category based on the knowledge tag relationship table, and configure knowledge for each tag in the tag tree to obtain a second knowledge tag.

[0126] The knowledge tag retrieval method in this embodiment is based on at least one first knowledge tag matched to the search information, and determines the first tag category corresponding to the first knowledge tag; obtains the second knowledge tags belonging to each preset tag category and the hierarchical relationship between the preset tag categories; determines the hierarchical order of the first tag categories based on the hierarchical relationship between the preset tag categories, and uses the first tag category in each level as the target tag category according to the hierarchical order; based on the first knowledge tag under the target tag category determined at each level, filters the second knowledge tags under the preset tag category after the target tag category at that level to obtain the filtered second knowledge tags at each level; based on the filtered second knowledge tags at each level, obtains the knowledge tag retrieval result of the search information. Since it is based on the hierarchical relationship between the preset tag categories, As well as the first knowledge label and the first label category, the second knowledge label after filtering at each level is determined, thereby realizing targeted determination of the second knowledge label after filtering at each level according to the first knowledge label and the corresponding first label category, improving the accuracy of the second knowledge label after filtering at each level, and based on the hierarchical relationship between preset label categories, and the first label category corresponding to each first knowledge label, compared with the traditional method without distinguishing label categories, direct screening is performed based on all the first knowledge labels, which reduces unnecessary screening operations and improves the efficiency of determining the second knowledge label after filtering at each level, and based on the second knowledge label after filtering at each level, the retrieval results of the retrieval information are obtained, realizing automatic simulation of knowledge labels of multiple label categories selected by users, and improving the retrieval efficiency of users' knowledge retrieval.

[0127] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0128] In one embodiment, the computer device is a terminal device, for example, its internal structure diagram can be as follows: Fig.12As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface, the display unit and the input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a knowledge tag retrieval method is implemented. The display unit of the computer device is used to form a visually visible image, and can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covered on the display screen, or a button, trackball or touchpad set on the computer device casing, or an external keyboard, touchpad or mouse, etc.

[0129] Those skilled in the art will understand that Fig.12 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0130] Based on the same inventive concept, an embodiment of the present application also provides a computer-readable storage medium, which may include: a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc.

[0131] Since the computer program stored in the computer-readable storage medium can execute any one of the knowledge tag retrieval methods provided in the embodiments of the present application, the beneficial effects that can be achieved by any one of the knowledge tag retrieval methods provided in the embodiments of the present application can be achieved. Please refer to the previous embodiments for details and will not be repeated here.

[0132] Based on the same inventive concept, the embodiment of the present application further provides a computer program product or a computer program, which includes a computer instruction, and the computer instruction is stored in a computer-readable storage medium. The processor of the computer device reads the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the method provided in various optional implementations in the above embodiments.

[0133] It should be noted that the object data (including but not limited to user device information, user personal information, etc.) and conversation data involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data need to comply with relevant laws, regulations and standards of relevant countries and regions. A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods.

[0134] Any reference to the memory, database or other media used in the embodiments provided in the present application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (Re RAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0135] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0136] In the above-mentioned knowledge tag retrieval device, computer-readable storage medium, computer equipment, and computer program product embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, refer to the relevant descriptions of other embodiments. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process and beneficial effects of the above-described knowledge tag retrieval device, computer-readable storage medium, computer program product, computer equipment and its corresponding units can refer to the description of the knowledge tag retrieval method in the above embodiment, and will not be repeated here.

[0137] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0138] The above is a detailed introduction to a knowledge tag retrieval method, device, computer equipment, computer-readable storage medium and computer program product provided in the embodiments of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, according to the ideas of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A knowledge tag retrieval method, characterized in that: The method comprises: At least one first knowledge tag matched based on the search information, and determining a first tag category corresponding to the first knowledge tag; Acquire the second knowledge tags belonging to each preset tag category and the hierarchical relationship between the preset tag categories; Based on the hierarchical relationship between the preset tag categories, determine the hierarchical order of the first tag categories, and according to the hierarchical order, use the first tag category in each level as the target tag category; Based on the first knowledge tags under the target tag category determined at each level, filtering the second knowledge tags under the preset tag category after the target tag category at the level to obtain the filtered second knowledge tags at each level; Based on the second knowledge tags after filtering at each level, a search result of the search information is obtained.

2. The method according to claim 1, characterized in that The first knowledge tag under the target tag category determined based on each level, filtering the second knowledge tags under the preset tag category after the target tag category of the level, to obtain the filtered second knowledge tags of each level, includes: Based on the hierarchical order of the target label categories, determining the first label category of the target to be processed currently; Based on the first knowledge tag under the target first tag category, updating the second knowledge tag for each preset tag category that is after the target first tag category in hierarchical order; Determine the preset tag category that is the same as the target first tag category and the preset tag category that is before the target first tag category in hierarchical order as the target second tag category, and determine the second knowledge tag under the target second tag category as the second knowledge tag after hierarchical filtering; Return to the step of determining the target first tag category currently to be processed based on the hierarchical order of the first tag category until the target first tag category currently to be processed is empty.

3. The method according to claim 2, characterized in that The updating of the second knowledge label for each preset label category after the target first label category in hierarchical order based on the first knowledge label under the target first label category includes: Acquire first knowledge from all first knowledge tags under the target first tag category; Determine a preset tag category that is subsequent to the target first tag category in hierarchical order; Based on the first knowledge and the determined second knowledge tags under the preset tag category, determine a second knowledge tag set matching each of the first knowledge under the same preset tag category, wherein the second knowledge tags in the same second knowledge tag set contain the same first knowledge; The intersection and union of the second knowledge tag sets under the same preset tag category are calculated, and a candidate difference tag is obtained by subtracting the intersection from the union, and the second knowledge tag under the preset tag category is updated based on the candidate difference tag.

4. The method according to claim 2, characterized in that The updating of the second knowledge label for each preset label category after the target first label category in hierarchical order based on the first knowledge label under the target first label category includes: If there is no second knowledge tag that is the same as the first knowledge tag of the target first tag category under the same preset tag category as the target first tag category, the first knowledge tag is deleted; Based on the remaining first knowledge tags under the target first tag category, the second knowledge tags are updated for each preset tag category that follows the target first tag category in a hierarchical order.

5. The method according to claim 2, characterized in that Also includes: If the current target first label category to be processed is empty, and there is a preset label category, the preset label category is determined as the target second label category, and the second knowledge label under the target second label category is used as the second knowledge label after hierarchical filtering.

6. The method according to any one of claims 1 to 5, characterized in that: After obtaining the search result of the search information based on the second knowledge tag filtered at each level, the method further includes: Displaying the search results through a client interface corresponding to the search information; Among them, on the client interface, the first knowledge tag in the second knowledge tags after the hierarchical filtering is displayed in a target display style, wherein the target display style is used to indicate that the corresponding first knowledge tag is in a selected state.

7. The method according to any one of claims 1 to 5, characterized in that: The obtaining of the second knowledge tags belonging to each preset tag category includes: Obtain a knowledge tag relationship table for each preset tag category; For each preset tag category, a tag tree is constructed based on the knowledge tag relationship table, and knowledge is configured for each tag in the tag tree to obtain a second knowledge tag.

8. A knowledge tag retrieval device, characterized in that: The device comprises: A first determination module, configured to determine a first tag category corresponding to at least one first knowledge tag matched based on the search information; An acquisition module, used to acquire second knowledge tags belonging to each preset tag category and the hierarchical relationship between the preset tag categories; A second determination module is used to determine the hierarchical order of the first tag categories based on the hierarchical relationship between the preset tag categories, and according to the hierarchical order, take the first tag category in each level as the target tag category; A filtering module, configured to filter the second knowledge tags under a preset tag category after the target tag category at the level based on the first knowledge tags under the target tag category determined at each level, to obtain the filtered second knowledge tags at each level; The retrieval module is used to obtain the retrieval result of the retrieval information based on the second knowledge tags after filtering at each level.

9. A computer device, characterized in that: It comprises a processor and a memory, wherein the memory stores a plurality of instructions; the processor loads instructions from the memory to execute the steps of the knowledge tag retrieval method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor to execute the steps of the knowledge tag retrieval method according to any one of claims 1 to 7.

11. A computer software, characterized in that: The computer software includes a computer program, and the computer program is executed by a processor to perform the steps of the knowledge tag retrieval method as described in any one of claims 1 to 7.

Images