CN116127154A

CN116127154A - Knowledge tag recommendation method and device, electronic equipment and storage medium

Info

Publication number: CN116127154A
Application number: CN202211578827.1A
Authority: CN
Inventors: 李�瑞; 金尚坤; 赵飞; 罗仕杰; 吴海英; 蒋宁
Original assignee: Mashang Consumer Finance Co Ltd
Current assignee: Mashang Consumer Finance Co Ltd
Priority date: 2022-12-05
Filing date: 2022-12-05
Publication date: 2023-05-16

Abstract

The disclosure provides a knowledge tag recommendation method, a knowledge tag recommendation device, electronic equipment and a storage medium, and relates to the technical field of Internet. The method comprises the steps of responding to a retrieval instruction aiming at a knowledge base, and acquiring a plurality of first knowledge labels corresponding to retrieval results; constructing a first tag list corresponding to the first knowledge tags for each of the plurality of first knowledge tags, the first tag list including the first knowledge tags and second knowledge tags associated with the first knowledge tags; constructing a second tag list, wherein the second tag list comprises knowledge tags with differences between first tag lists corresponding to the first knowledge tags respectively; and obtaining the recommended knowledge label corresponding to the search result according to the second label list. According to the embodiment of the invention, the knowledge labels with differences are used as recommendation labels, so that a user can be helped to accurately find the required knowledge data, the screening process of the search result is optimized, and the search efficiency is improved.

Description

Knowledge tag recommendation method and device, electronic equipment and storage medium

Technical Field

The disclosure relates to the technical field of internet, and in particular relates to a knowledge tag recommendation method, a knowledge tag recommendation device, electronic equipment and a storage medium.

Background

With the rapid development of internet technology, the amount of business related knowledge is gradually huge, and the information in the knowledge base is also increasingly complicated. When the user performs targeted retrieval on knowledge, the user cannot always directly hit the required retrieval result. In this case, in order to further narrow the search results, the user typically screens the search results based on knowledge tags.

In the related art, a user needs to select a label closest to a required content from a large number of knowledge labels corresponding to a search result, which is inefficient and difficult to hit the knowledge label accurately.

Disclosure of Invention

In view of this, the disclosure provides a knowledge tag recommendation method, a knowledge tag recommendation device, an electronic device and a storage medium.

In a first aspect, a knowledge tag recommendation method is provided, including: responding to a retrieval instruction aiming at a knowledge base, and acquiring a plurality of first knowledge labels corresponding to retrieval results; constructing a first tag list corresponding to the first knowledge tags for each of the plurality of first knowledge tags, the first tag list including the first knowledge tags and second knowledge tags associated with the first knowledge tags; constructing a second tag list, wherein the second tag list comprises knowledge tags with differences between first tag lists corresponding to the first knowledge tags respectively; and obtaining the recommended knowledge label corresponding to the search result according to the second label list.

In a second aspect, there is provided a knowledge tag recommendation device, including: the acquisition module is used for responding to a retrieval instruction aiming at the knowledge base and acquiring a plurality of first knowledge labels corresponding to the retrieval result; a first construction module, configured to construct, for each of a plurality of first knowledge tags, a first tag list corresponding to the first knowledge tag, the first tag list including the first knowledge tag and a second knowledge tag associated with the first knowledge tag; the second construction module is used for constructing a second tag list, and the second tag list comprises knowledge tags with differences between the first tag lists corresponding to the plurality of first knowledge tags respectively; and the recommending module is used for obtaining the recommending knowledge label corresponding to the retrieval result according to the second label list.

In a third aspect, there is provided an electronic device comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform the method of the first aspect described above via execution of executable instructions.

In a fourth aspect, a computer readable storage medium is provided, on which a computer program is stored which, when executed by a processor, implements the method of the first aspect described above.

According to the knowledge tag recommending method provided by the embodiment of the disclosure, the first tag lists are obtained by combining each first knowledge tag corresponding to the search result and the second knowledge tag associated with the first knowledge tag, and then differences among the first tag lists are compared, so that knowledge tags with differences in the first tag lists can be obtained, and further the recommended knowledge tag is obtained according to the knowledge tags with differences. According to the embodiment of the disclosure, the knowledge labels with the differences corresponding to the search results can be accurately obtained, and the knowledge labels with the differences are used as recommendation labels for users to screen the search results, so that the users can be helped to accurately search the required knowledge data from the knowledge base, the screening process of the search results is optimized, and the search efficiency is improved.

Drawings

Fig. 1 is a schematic diagram of a system architecture of a tag recommendation method according to an embodiment of the disclosure.

Fig. 2 is a flowchart illustrating a label recommendation method according to an embodiment of the disclosure.

FIG. 3 illustrates a schematic diagram of knowledge data versus knowledge tags in an embodiment of the disclosure.

Fig. 4 shows a schematic diagram of a subordinate label and a parent link label in a label tree in an embodiment of the present disclosure.

Fig. 5 shows a flowchart of a first tag list construction method in an embodiment of the present disclosure.

Fig. 6 shows a flowchart of a second tag list construction method in an embodiment of the present disclosure.

Fig. 7 shows a flowchart of a method for constructing a label tree in an embodiment of the present disclosure.

Fig. 8 is a schematic structural diagram of a tag recommendation device in an embodiment of the disclosure.

Fig. 9 shows a schematic structural diagram of an electronic device in an embodiment of the disclosure.

Detailed Description

Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments may be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

Furthermore, the drawings are merely schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus a repetitive description thereof will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software or in one or more hardware modules or integrated circuits or in different networks and/or processor devices and/or microcontroller devices.

With the development of internet technology, accurate and rapid acquisition of knowledge data from a huge knowledge base is an urgent need of users. In order to shorten the retrieval time of the knowledge data by the user, knowledge data in the knowledge base are usually marked with knowledge labels for distinguishing different knowledge applications in different problem scenes. In the related art, although knowledge tags exist in a knowledge base, a user needs to select a tag closest to required contents from a large number of knowledge tags corresponding to search results by himself, which is inefficient and difficult to hit the knowledge tag required by himself precisely.

According to the scheme provided by the disclosure, a plurality of first knowledge labels corresponding to the retrieval results can be acquired in response to the retrieval instruction aiming at the knowledge base. For each first knowledge tag of the plurality of first knowledge tags, constructing a first tag list corresponding to the first knowledge tag, the first tag list including the first knowledge tag and a second knowledge tag associated with the first knowledge tag. And constructing a second tag list, wherein the second tag list comprises knowledge tags with differences between the first tag lists corresponding to the plurality of first knowledge tags respectively. And obtaining the recommended knowledge label corresponding to the search result according to the second label list. According to the embodiment of the disclosure, when a user performs knowledge tag screening, knowledge tags with differences among a plurality of knowledge data can be accurately obtained, so that the efficiency and accuracy of user screening are improved.

It should be appreciated that the apparatus for performing the tag recommendation method in the embodiments of the present disclosure may be referred to as a tag recommendation apparatus, which is an apparatus for automatically comparing and discovering related tags, and may be a piece of code logic running inside a computer server.

In particular, referring to fig. 1, fig. 1 shows an exemplary system architecture diagram of a tag recommendation method or a tag recommendation apparatus applied to an embodiment of the present disclosure. As shown in fig. 1, the system architecture 100 includes a processor 101 and a memory 102.

The processor 101 is configured to execute program instructions, for example, may execute the tag recommendation method provided in the present disclosure. The memory 102 may be present in the system architecture 100 in various forms of program storage units or data storage units, such as hard disk, read Only Memory (ROM), random Access Memory (RAM), which can be used to store various data files used by the processor in processing and/or performing the tag recommendation method, as well as possible program instructions for execution by the processor. Although not shown in the figures, the system architecture 100 may also include an input/output component to support input/output data flow between the tag recommendation device to which the system architecture 100 is applied and devices downstream thereof. In addition, the tag recommendation device applying the system architecture 100 may also send and receive information and data from the network through the communication port.

Although in fig. 1, the processor 101 and the memory 102 are presented as separate modules, it will be appreciated by those skilled in the art that the above-described apparatus modules may be implemented as separate hardware devices or may be integrated as one or more hardware devices, such as in a smart watch or other smart device. The specific implementation of the different hardware devices should not be taken as a factor limiting the scope of protection of the present disclosure, as long as the principles described in this disclosure can be implemented.

The present exemplary embodiment will be described in detail below with reference to the accompanying drawings and examples.

First, in the embodiment of the present disclosure, a knowledge tag recommendation method is provided, which may be performed by any electronic device having computing processing capability.

Fig. 2 is a schematic flow chart of a knowledge tag recommendation method in an embodiment of the disclosure, and as shown in fig. 2, the knowledge tag recommendation method provided in the embodiment of the disclosure includes the following steps.

S201, responding to a retrieval instruction aiming at a knowledge base, and acquiring a plurality of first knowledge labels corresponding to a retrieval result.

It should be noted that the knowledge base may be a structured and easy-to-operate knowledge cluster, that is, an interrelated knowledge data set that is stored, organized, managed, and used in a computer memory by adopting several knowledge representation modes according to the requirement of solving a problem in a certain field. Such knowledge data includes theoretical knowledge related to the field, fact data, heuristic knowledge derived from expert experience, and the like. Knowledge data in a knowledge base is typically pre-labeled with one or more knowledge tags for ease of user review and retrieval.

In some embodiments, knowledge tags in the knowledge base may be interrelated in a tree structure. That is, each knowledge tag in the knowledge base has at least one parent tag, and/or at least one subordinate tag.

It should be noted that, by performing targeted search in the knowledge base, the user may obtain a plurality of knowledge data in the knowledge base. The knowledge labels corresponding to the knowledge data are the first knowledge labels.

FIG. 3 illustrates a schematic diagram of knowledge data versus knowledge tags in an embodiment of the disclosure. As shown in fig. 3, one knowledge data may correspond to a plurality of knowledge tags, and different knowledge data may correspond to the same knowledge tag. For example, knowledge data 1 may correspond to knowledge tags such as knowledge tag 1 and knowledge tag 2, and knowledge data 2 may also correspond to knowledge tags such as knowledge tag 1 and knowledge tag 2, which are not listed here.

Illustratively, there may be a one-to-many relationship between knowledge data and knowledge tags. Thus, in the case where one knowledge data has a plurality of knowledge tags, the first knowledge tag may be a set of a plurality of knowledge tags.

It should be understood that the first knowledge tag in the embodiments of the present disclosure is not limited to the number of tags, that is, the first knowledge tag may be one knowledge tag or may be a plurality of knowledge tags. That is, in the embodiment of the present disclosure, the plurality of first knowledge tags corresponding to the search result may be first knowledge tags corresponding to the plurality of pieces of retrieved knowledge data, and the first knowledge tag may be one knowledge tag corresponding to one piece of knowledge data or may be a plurality of knowledge tags corresponding to one piece of knowledge data.

S202, constructing a first tag list corresponding to the first knowledge tags for each of the plurality of first knowledge tags.

It should be noted that the first tag list may be a tag list composed of a first knowledge tag and a second knowledge tag associated with the first knowledge tag.

In some embodiments, the first tag list may be constructed in the following manner: and acquiring a tag tree where the first knowledge tag is located for each first knowledge tag in the plurality of first knowledge tags. Each knowledge tag in the tag tree is then traversed to determine a second knowledge tag associated with the first knowledge tag. And constructing a first tag list corresponding to the first knowledge tag according to the second knowledge tag. The second knowledge tag may be a parent tag of the first knowledge tag in the tag tree, or may be a subordinate tag of the first knowledge tag in the tag tree.

According to the embodiment of the disclosure, other knowledge tags associated with the knowledge tags are determined through the tag tree where the knowledge tags are located, omission of the other knowledge tags is avoided, and meanwhile results of recommending the tags are enriched.

In some embodiments, the second knowledge tag in embodiments of the disclosure may be a subordinate tag of the first knowledge tag in the tag data, and/or a parent link tag of the first knowledge tag in the tag tree. In particular, the above-mentioned lower level labels may be all child node labels of the first knowledge label in the label tree. The parent link label may be a parent label of the first knowledge label, a parent label of the parent label, and so on, until traversing to the root node, i.e., all knowledge labels (including the root node label) on the path of the label tree where the first knowledge label is connected to the root node label.

Illustratively, FIG. 4 shows a lower level label and parent link label schematic in a label tree. In fig. 4, the parent link label of the knowledge label B1 includes a knowledge label a and a root node label, and the subordinate label of the knowledge label B1 includes a knowledge label C1 and a knowledge label C2. The parent link labels of the knowledge label B2 are also the knowledge label a and the root node label, and the knowledge label B2 does not have a lower label.

For ease of understanding, the method for constructing the first tag list in the embodiment of the present disclosure will be described in detail below with reference to fig. 5. As shown in fig. 5, the method includes the following steps.

S501, obtaining a tag tree where the first knowledge tag is located.

S502, traversing knowledge labels in a label tree.

S503, judging whether the traversed knowledge label belongs to a parent link label of the first knowledge label, if so, executing S504.

It should be noted that, since the label path of the first knowledge label may be used to obtain the identification set of the parent link label of the first knowledge label in advance. If the identity of the traversed knowledge tag exists in the identity set, the traversed knowledge tag term parent link tag of the first knowledge tag.

S504, obtaining a parent link label of the first knowledge label.

It should be noted that, the obtained parent link label is the knowledge label traversed currently.

S505, judging whether the ID of the traversed knowledge label is the same as the ID of the first knowledge label, if so, executing S506.

S506, determining the subordinate label of the first knowledge label according to the position of the traversed knowledge label in the label tree.

It should be noted that, after determining the position of the traversed knowledge tag in the tag tree, the next-stage searching is performed to find the tag associated with the knowledge tag, that is, the next-stage tag of the first knowledge tag.

S507, adding the obtained father link label and the lower label into the first label list.

According to the embodiment of the disclosure, before the comparison of the knowledge labels, the lower-level labels of the knowledge labels and the father-link labels are considered, so that the difference knowledge label results obtained by the subsequent comparison can be enriched, more selectable labels are provided for users when the search results are screened, and the search results are refined, so that the users can accurately hit the required knowledge data.

S203, constructing a second tag list.

It should be noted that the second tag list includes knowledge tags having differences between the first tag lists corresponding to the plurality of first knowledge tags, respectively. That is, the knowledge tags in the second tag list may be knowledge tags in any of the first tag lists that are not present in all of the first tag lists at the same time. For example, assuming that the first tag lists corresponding to the three first knowledge tags are { tag a, tag B, tag C }, { tag a, tag B, tag D }, { tag a, tag C, tag D }, respectively, since only tag a above is present in each first tag list at the same time, the knowledge tag having a difference between the three first tag lists above is { tag B, tag C, tag D }.

In some application scenarios, the specified knowledge tag may be pre-excluded in the construction process of the second tag list according to the search requirement of the user, which is not limited in the embodiments of the present disclosure. For example, after the second tag list { tag B, tag C, tag D } is obtained in the above example, if it is determined that the search result of the user is irrelevant to tag B, tag B may be removed from { tag B, tag C, tag D }, that is, { tag C, tag D } is used as the second tag list.

It should be understood that, since the same knowledge tags between the respective first tag lists (i.e., the knowledge tags that exist in the respective first tag lists at the same time) have no screening effect on the search result, the core idea of the embodiment of the present disclosure is to reject the same knowledge tags between the respective first tag lists, and the processing manner of the remaining knowledge tags is not limited.

In some embodiments, by constructing the first tag set and the second tag set, the knowledge tags with differences can be quickly compared to complete the construction of the second tag list, and the knowledge tags with differences are used as recommendation tags for users to screen search results, so that users can be helped to accurately search the required knowledge data from the knowledge base.

Specifically, the first tag set includes the same knowledge tags in the first tag list corresponding to the plurality of first knowledge tags, respectively, and the second tag set includes all knowledge tags in the first tag list corresponding to the plurality of first knowledge tags, respectively. That is, the first set of labels is an intersection of the plurality of first lists of labels and the second set of labels is a union of the plurality of first lists of labels.

At this time, if the first tag set is a non-empty set, the difference set between the second tag set and the first tag set (i.e., the result set obtained by subtracting the second tag set from the first tag set) is the second tag list. If the first tag set is the empty set, the second tag set is the second tag list.

For ease of understanding, the method of constructing the second tag list in the embodiment of the present disclosure will be described in detail with reference to fig. 6. As shown in fig. 6, the method includes the following steps.

S601, an intersection of a plurality of first tag lists is taken as a first tag set.

S602, taking a union set of a plurality of first tag lists as a second tag set.

S603, judging whether the first label set is an empty set, if so, executing S604; if not, S605 is executed.

S604, taking the second label set as a second label list.

S605 takes the difference set between the second tag set and the first tag set as the second tag list.

For example, assuming that two first knowledge tags { securities }, { funds }, then the first tag lists to which the two first knowledge tags respectively correspond may be { securities, risk controls, financial services }, { funds, risk controls, financial services }. At this time, as can be seen by comparing the two first tag lists, the first tag set is the same tag (intersection) in the two first tag lists, i.e., { risk control, financial service }; the second set of tags is all tags (union) in the two first tag lists, i.e., { securities, funds, risk control, financial services }. At this time, the difference set { securities, funds } between the second tag set and the first tag set is the second tag list.

Similarly, assuming two first knowledge tags { securities } and { endowments }, then the first tag list to which the two first knowledge tags correspond respectively may be { securities, risk controls, financial services }, { endowments, asset management }. At this time, as can be seen by comparing the two first tag lists, since the same tag does not exist in the two first tag lists, i.e. the first tag is an empty set, the second tag set { securities, risk control, financial services, endowment, asset management } is the second tag list.

S204, obtaining the recommended knowledge label corresponding to the search result according to the second label list.

The recommended knowledge tag is a knowledge tag which is used for being displayed to the user and can precisely divide the search result of the user. The user can screen the search result according to the recommended knowledge label, so that knowledge data required by the user can be accurately hit in the knowledge base.

In some embodiments, the recommended knowledge tag may be obtained by constructing a third tag list. Specifically, the third tag list includes all knowledge tags in the second tag list, and parent link tags of all knowledge tags in the second tag list in respective tag trees. By analyzing the knowledge tags included in the third tag list, a recommended knowledge tag corresponding to the search result can be obtained.

When knowledge labels with differences are displayed to users, the father links of the knowledge labels are considered, so that the users can fully know the association between the different knowledge labels, and the users are assisted to confirm the knowledge label with the highest association with the required retrieval result.

In some embodiments, in order to intuitively present the relationships between the plurality of recommended knowledge tags to the user, the user may quickly and accurately locate knowledge tags that are closely related to the self-retrieved content from the plurality of recommended knowledge tags. The recommendation knowledge tags may be presented to the user in the form of a tag tree.

Illustratively, according to the tag tree to which each knowledge tag in the third tag list belongs, all knowledge tags in the third tag list are grouped to obtain a plurality of knowledge tag groups. Specifically, the tag tree to which the knowledge tags in each knowledge tag group belong is the same. The tag tree to which the knowledge tag belongs can be determined by the ROOT node identification (root_id) of the knowledge tag, that is, the ROOT node identification is the same as the tag tree to which the same knowledge tag belongs.

After a plurality of knowledge tag groups are divided, the knowledge tags in each knowledge tag group are rearranged into a new tag tree, and the recommendation tags can be displayed to the user in the form of the tag tree, so that the user can obtain the recommendation tags corresponding to the retrieval results.

In some embodiments, based on the plurality of knowledge tag groups, the manner in which the recommendation tag tree is constructed may be: for each of the plurality of knowledge tag groups, an association relationship of each knowledge tag in the knowledge tag group may be determined according to a parent tag of each knowledge tag in the knowledge tag group. And according to the association relation of each knowledge label in the knowledge label group, a recommendation label tree can be constructed. It should be noted that the final number of the recommendation tag trees is consistent with the number of the knowledge tag groups, that is, each knowledge tag group may be constructed as an independent recommendation tag tree.

Illustratively, by analyzing the association relationship between the knowledge tags through the parent tags of the knowledge tags in each knowledge tag group, a new tag tree can be formed by using the knowledge tags in each knowledge tag group. The association relationship of each knowledge tag can show the relationship of each knowledge tag in the same tag tree. For example, if the parent tags of multiple knowledge tags are identical, the knowledge tags may be used as peer tags and commonly connected to the same parent tag in the tag tree, and if the parent tag of one knowledge tag is another knowledge tag, then there is a higher-lower membership between the two knowledge tags.

In some embodiments, after the first tag list, the second tag list and the third tag list are constructed, repeated tags in the tag list may be first removed, so as to prevent repeated and redundant knowledge tags from being generated in the using process of the tag list in the later period.

For ease of understanding, the method of constructing the tag tree in the embodiments of the present disclosure will be described in detail with reference to fig. 7. As shown in fig. 7, the method includes the following steps.

S701, traversing the knowledge tags in the knowledge tag group.

In some embodiments, before traversing the knowledge tag group, a map-type data set, i.e., a map (ID, knowledge tag), with a knowledge tag ID of a key (build) and a knowledge tag value may be pre-constructed according to knowledge tags in the knowledge tag group, so as to form a recommendation tag tree with a tree structure.

S702, obtaining the parent tag ID of the currently traversed knowledge tag.

In some embodiments, the parent tag ID of the knowledge tag currently traversed may be obtained from the knowledge tag group because the parent tag ID is an inherent attribute of the knowledge tag.

S703, judging whether the parent tag ID is empty, if so, executing S704; if not, then S705 is performed.

S704, taking the currently traversed knowledge label as a root node of a recommendation label tree, and then repeatedly executing the S701-S703.

S705, obtaining the parent label of the current node according to the parent label ID.

In some embodiments, knowledge tags corresponding to parent tag IDs may be obtained from a pre-built map-type data set based on the parent tag IDs.

S706, adding the currently traversed knowledge label under the parent label, and then repeatedly executing S701-S703.

In some embodiments, the map-type data corresponding to the current traversed knowledge tag may be added to the map-type data corresponding to its parent tag in the pre-built map-type data set, thereby forming a tree structure.

S707, after all the knowledge tag traversal in the knowledge tag group is finished, the recommendation tag tree corresponding to the knowledge tag group is constructed.

In some embodiments, taking the consumer finance field as an example, a user may retrieve business-related knowledge in a business knowledge base. For example, when the user searches for "how to raise the credit line", the search result may include knowledge items such as "what the credit line raising condition is" (the knowledge label "change the credit line"), "how to modify the withdrawal amount" (the knowledge label "change the withdrawal line"), "how to query the withdrawal line" (the knowledge label "query the withdrawal line"), etc., which are not exemplified here. Taking the above three knowledge items as an example, assume that the parent labels of "offer credit modification" and "offer credit inquiry" are both "offer credit", and the parent label of "loan credit modification" is "loan". In the knowledge retrieval results, the labels with the differences are recommended to the user, so that the user can quickly screen and locate knowledge items expected by the user.

Because of the knowledge tag recommendation method provided by the embodiment of the disclosure, the associated tags of all knowledge tags are considered. Thus, in the above example, the user can quickly locate his or her desired business directly through the recommended knowledge tags "offer" and "loan", i.e., the parent tag of the knowledge tag, e.g., by "offer" locating the offer business. If the search result is still more and inconvenient to view, the user can further screen the result according to the next level knowledge label, for example, the "presenting limit change" and the "presenting limit query" in the previous example. Accordingly, the embodiment of the disclosure can improve the retrieval efficiency of the user on the business knowledge and enhance the user experience.

Fig. 8 is a schematic structural diagram of a tag recommendation device according to an embodiment of the present disclosure, and as shown in fig. 8, the tag recommendation device 800 includes: an acquisition module 801, a first construction module 802, a second construction module 803, and a recommendation module 804.

Specifically, the obtaining module 801 is configured to obtain, in response to a search instruction for a knowledge base, a plurality of first knowledge tags corresponding to search results. The first construction module 802 is configured to construct, for each first knowledge tag of the plurality of first knowledge tags, a first tag list corresponding to the first knowledge tag, the first tag list including the first knowledge tag and a second knowledge tag associated with the first knowledge tag. The second construction module 803 is configured to construct a second tag list, where the second tag list includes knowledge tags that have differences between first tag lists corresponding to the plurality of first knowledge tags, respectively. The recommendation module 804 is configured to obtain a recommendation knowledge tag corresponding to the search result according to the second tag list.

In some embodiments, the first building module 802 is further configured to, for each of the plurality of first knowledge tags, obtain a tag tree in which the first knowledge tag is located; traversing each knowledge tag in the tag tree to determine a second knowledge tag associated with the first knowledge tag; and constructing a first tag list corresponding to the first knowledge tag according to the second knowledge tag.

In some embodiments, the second knowledge tag associated with the first knowledge tag comprises: the first knowledge tag is a subordinate tag in the tag tree and/or the first knowledge tag is a parent link tag in the tag tree.

In some embodiments, the second construction module 803 is further configured to construct a first tag set and a second tag set respectively, where the first tag set includes the same knowledge tags in the first tag list corresponding to the plurality of first knowledge tags respectively, and the second tag set includes all knowledge tags in the first tag list corresponding to the plurality of first knowledge tags respectively; if the first tag set is a non-empty set, the difference set between the second tag set and the first tag set is used as a second tag list.

In some embodiments, the second building module 803 is further configured to use the second tag set as the second tag list if the first tag set is an empty set.

In some embodiments, the recommendation module 804 is further configured to construct a third tag list, where the third tag list includes all knowledge tags in the second tag list, and parent link tags of all knowledge tags in the second tag list in respective tag trees; and obtaining a recommended label corresponding to the search result according to the third label list.

In some embodiments, the recommendation module 804 is further configured to group all the knowledge tags in the third tag list according to the tag tree to which the knowledge tags belong, to obtain a plurality of knowledge tag groups; and constructing a recommendation label tree based on the plurality of knowledge label groups, thereby obtaining recommendation labels corresponding to the retrieval results.

In some embodiments, the recommendation module 804 is further configured to, for each of the plurality of knowledge tag groups, determine, according to a parent tag of each knowledge tag in the knowledge tag group, an association relationship of each knowledge tag in the knowledge tag group; and constructing a recommendation tag tree according to the association relation of each knowledge tag in the knowledge tag group.

It should be noted that, when the tag recommendation device provided in the foregoing embodiment is used for tag recommendation, only the division of the foregoing functional modules is used for illustration, and in practical application, the foregoing functional allocation may be performed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules, so as to complete all or part of the functions described above. In addition, the tag recommendation device and the tag recommendation method embodiment provided in the foregoing embodiments belong to the same concept, and specific implementation processes of the tag recommendation device and the tag recommendation method embodiment are detailed in the method embodiment, and are not repeated herein.

Those skilled in the art will appreciate that the various aspects of the present disclosure may be implemented as a system, method, or program product. Accordingly, various aspects of the disclosure may be embodied in the following forms, namely: an entirely hardware embodiment, an entirely software embodiment (including firmware, micro-code, etc.) or an embodiment combining hardware and software aspects may be referred to herein as a "circuit," module "or" system.

An electronic device 900 according to such an embodiment of the present disclosure is described below with reference to fig. 9. The electronic device 900 shown in fig. 9 is merely an example and should not be construed to limit the functionality and scope of use of embodiments of the present disclosure in any way.

As shown in fig. 9, the electronic device 900 is embodied in the form of a general purpose computing device. Components of electronic device 900 may include, but are not limited to: the at least one processing unit 910, the at least one storage unit 920, and a bus 930 connecting the different system components (including the storage unit 920 and the processing unit 910).

Wherein the storage unit stores program code that is executable by the processing unit 910 such that the processing unit 910 performs steps according to various exemplary embodiments of the present disclosure described in the above-described "exemplary methods" section of the present specification.

In some embodiments, the processing unit 910 may perform the following steps of the text processing method embodiments described above: responding to a retrieval instruction aiming at a knowledge base, and acquiring a plurality of first knowledge labels corresponding to retrieval results; constructing a first tag list corresponding to the first knowledge tags for each of the plurality of first knowledge tags, the first tag list including the first knowledge tags and second knowledge tags associated with the first knowledge tags; constructing a second tag list, wherein the second tag list comprises knowledge tags with differences between first tag lists corresponding to the first knowledge tags respectively; and obtaining the recommended knowledge label corresponding to the search result according to the second label list.

The storage unit 920 may include readable media in the form of volatile storage units, such as Random Access Memory (RAM) 9201 and/or cache memory 9202, and may further include Read Only Memory (ROM) 9203.

The storage unit 920 may also include a program/utility 9204 having a set (at least one) of program modules 9205, such program modules 9205 include, but are not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment.

The bus 930 may be one or more of several types of bus structures including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

The electronic device 900 may also communicate with one or more external devices 940 (e.g., keyboard, pointing device, bluetooth device, etc.), one or more devices that enable a user to interact with the electronic device 900, and/or any devices (e.g., routers, modems, etc.) that enable the electronic device 900 to communicate with one or more other computing devices. Such communication may occur through an input/output (I/O) interface 950. Also, electronic device 900 may communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the Internet, through network adapter 960. As shown, the network adapter 960 communicates with other modules of the electronic device 900 over the bus 930. It should be appreciated that although not shown, other hardware and/or software modules may be used in connection with electronic device 900, including, but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, data backup storage systems, and the like.

From the above description of embodiments, those skilled in the art will readily appreciate that the example embodiments described herein may be implemented in software, or may be implemented in software in combination with the necessary hardware. Thus, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a U-disk, a mobile hard disk, etc.) or on a network, including several instructions to cause a computing device (may be a personal computer, a server, a terminal device, or a network device, etc.) to perform the method according to the embodiments of the present disclosure.

In an exemplary embodiment of the present disclosure, a computer-readable storage medium, which may be a readable signal medium or a readable storage medium, is also provided. On which a program product is stored which enables the implementation of the method described above of the present disclosure. In some possible implementations, various aspects of the disclosure may also be implemented in the form of a program product comprising program code for causing a terminal device to carry out the steps according to the various exemplary embodiments of the disclosure as described in the "exemplary methods" section of this specification, when the program product is run on the terminal device.

More specific examples of the computer readable storage medium in the present disclosure may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

In this disclosure, a computer readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, with readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A readable signal medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

Alternatively, the program code embodied on a computer readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

In particular implementations, the program code for carrying out operations of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of remote computing devices, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., connected via the Internet using an Internet service provider).

It should be noted that although in the above detailed description several modules or units of a device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit in accordance with embodiments of the present disclosure. Conversely, the features and functions of one module or unit described above may be further divided into a plurality of modules or units to be embodied.

Furthermore, although the steps of the methods in the present disclosure are depicted in a particular order in the drawings, this does not require or imply that the steps must be performed in that particular order or that all illustrated steps be performed in order to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step to perform, and/or one step decomposed into multiple steps to perform, etc.

From the description of the above embodiments, those skilled in the art will readily appreciate that the example embodiments described herein may be implemented in software, or may be implemented in software in combination with the necessary hardware. Thus, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a U-disk, a mobile hard disk, etc.) or on a network, including several instructions to cause a computing device (may be a personal computer, a server, a mobile terminal, or a network device, etc.) to perform the method according to the embodiments of the present disclosure.

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This disclosure is intended to cover any adaptations, uses, or adaptations of the disclosure following the general principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

Claims

1. A knowledge tag recommendation method, comprising:

responding to a retrieval instruction aiming at a knowledge base, and acquiring a plurality of first knowledge labels corresponding to retrieval results;

constructing a first tag list corresponding to the first knowledge tags for each first knowledge tag in the plurality of first knowledge tags, wherein the first tag list comprises the first knowledge tags and second knowledge tags associated with the first knowledge tags;

constructing a second tag list, wherein the second tag list comprises knowledge tags with differences between first tag lists corresponding to the plurality of first knowledge tags respectively;

and obtaining a recommended knowledge tag corresponding to the search result according to the second tag list.

2. The method of claim 1, wherein the constructing, for each first knowledge tag of the plurality of first knowledge tags, a first tag list corresponding to the first knowledge tag comprises:

acquiring a tag tree where the first knowledge tags are located for each first knowledge tag in the plurality of first knowledge tags;

traversing each knowledge tag in the tag tree to determine a second knowledge tag associated with the first knowledge tag;

And constructing a first tag list corresponding to the first knowledge tag according to the second knowledge tag.

3. The method of claim 2, wherein the second knowledge tag associated with the first knowledge tag comprises: the first knowledge tag is a subordinate tag in the tag tree and/or the first knowledge tag is a parent link tag in the tag tree.

4. A method according to any one of claims 1 to 3, wherein said constructing a second tag list comprises:

respectively constructing a first tag set and a second tag set, wherein the first tag set comprises knowledge tags which are the same as those in a first tag list respectively corresponding to the plurality of first knowledge tags, and the second tag set comprises all knowledge tags in the first tag list respectively corresponding to the plurality of first knowledge tags;

and if the first tag set is a non-empty set, taking a difference set between the second tag set and the first tag set as the second tag list.

5. The method of claim 4, further comprising, after said constructing the first and second sets of labels, respectively:

And if the first tag set is an empty set, the second tag set is used as the second tag list.

6. A method according to any one of claims 1 to 3, wherein said obtaining, from said second tag list, a recommended tag corresponding to said search result comprises:

constructing a third tag list, wherein the third tag list comprises all knowledge tags in the second tag list and parent chain tags of all knowledge tags in the second tag list in respective tag trees;

and obtaining a recommended label corresponding to the search result according to the third label list.

7. The method of claim 6, wherein the obtaining, according to the third tag list, a recommended tag corresponding to the search result includes:

grouping all the knowledge labels in the third label list according to the label tree to which the knowledge labels belong to, so as to obtain a plurality of knowledge label groups;

and constructing a recommendation label tree based on the knowledge label groups, so as to obtain recommendation labels corresponding to the retrieval results.

8. The method of claim 7, wherein constructing a recommendation tag tree based on the plurality of knowledge tag groups comprises:

Aiming at each knowledge tag group in the plurality of knowledge tag groups, determining the association relation of each knowledge tag in the knowledge tag groups according to the father tag of each knowledge tag in the knowledge tag groups;

and constructing the recommendation tag tree according to the association relation of each knowledge tag in the knowledge tag group.

9. A knowledge tag recommendation device, comprising:

the acquisition module is used for responding to a retrieval instruction aiming at the knowledge base and acquiring a plurality of first knowledge labels corresponding to the retrieval result;

a first construction module, configured to construct, for each first knowledge tag of the plurality of first knowledge tags, a first tag list corresponding to the first knowledge tag, where the first tag list includes the first knowledge tag and a second knowledge tag associated with the first knowledge tag;

the second construction module is used for constructing a second tag list, and the second tag list comprises knowledge tags with differences between first tag lists respectively corresponding to the plurality of first knowledge tags;

and the recommending module is used for obtaining a recommending knowledge label corresponding to the retrieval result according to the second label list.

10. An electronic device, comprising:

a processor; and

a memory for storing executable instructions of the processor;

wherein the processor is configured to perform the method of any one of claims 1 to 8 via execution of the executable instructions.

11. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the method of any one of claims 1 to 8.