CN113641718A

CN113641718A - Model generation method, search recommendation method, device, equipment and medium

Info

Publication number: CN113641718A
Application number: CN202110926895.1A
Authority: CN
Inventors: 苑霸; 刘康康; 巩芙榕; 王懿嘉; 李远杭; 于复淮
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2021-08-12
Filing date: 2021-08-12
Publication date: 2021-11-12

Abstract

The disclosure provides a model generation method, a search recommendation device, equipment and a medium, relates to the technical field of artificial intelligence, and particularly relates to an intelligent recommendation and deep learning technology. The implementation scheme is as follows: initializing a search tag model, wherein the search tag model comprises one or more tree structure models, each tree structure model of the search tag model corresponds to a tag type, and each node of the tree structure model is a search tag comprising at least one entry; editing entries corresponding to one or more nodes of the search tag model based on the search history of the user; and modifying the structure of the tree structure model of the search tag model based on the user search history.

Description

Model generation method, search recommendation method, device, equipment and medium

Technical Field

The present disclosure relates to the field of artificial intelligence technologies, and in particular, to an intelligent recommendation and deep learning technology, and in particular, to a model generation method, a search recommendation method, an apparatus, an electronic device, a computer-readable storage medium, and a computer program product.

Background

Artificial intelligence is the subject of research that makes computers simulate some human mental processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.), both at the hardware level and at the software level. The artificial intelligence hardware technology generally comprises technologies such as a sensor, a special artificial intelligence chip, cloud computing, distributed storage, big data processing and the like, and the artificial intelligence software technology mainly comprises a computer vision technology, a voice recognition technology, a natural language processing technology, machine learning/deep learning, a big data processing technology, a knowledge graph technology and the like.

In the prior art, since a user search request may not accurately describe the real needs of the user, search recommendation information (e.g., keywords generated based on the user search request) needs to be generated according to the user search request to guide the user to further clarify the needs. Therefore, there is a need to provide accurate and comprehensive search recommendation information to users to meet the current search needs of the users and further stimulate the relevant search needs of the users.

The approaches described in this section are not necessarily approaches that have been previously conceived or pursued. Unless otherwise indicated, it should not be assumed that any of the approaches described in this section qualify as prior art merely by virtue of their inclusion in this section. Similarly, unless otherwise indicated, the problems mentioned in this section should not be considered as having been acknowledged in any prior art.

Disclosure of Invention

The present disclosure provides a model generation method, a search recommendation method, an apparatus, an electronic device, a computer-readable storage medium, and a computer program product.

According to an aspect of the present disclosure, there is provided a model generation method including: initializing a search tag model, wherein the search tag model comprises one or more tree structure models, each tree structure model of the search tag model corresponds to a tag type, and each node of the search tree structure model is a search tag comprising at least one entry; editing entries corresponding to one or more nodes of the search tag model based on the search history of the user; and modifying the structure of the tree structure model of the search tag model based on the search history of the search user.

According to another aspect of the present disclosure, there is provided a search recommendation method including: responding to a received user search request, selecting a node matched with the user search request in a search tag model as a hit node, wherein the search tag model is the search tag model generated according to the model generation method disclosed by the disclosure; and generating search recommendation information based on the hit nodes.

According to another aspect of the present disclosure, there is provided a model generation apparatus including: a model initialization module configured to: initializing a search tag model, wherein the search tag model comprises one or more tree structure models, each tree structure model of the search tag model corresponds to a tag type, and each node of the tree structure model is a search tag comprising at least one entry; an entry editing module configured to: editing entries corresponding to one or more nodes of the search tag model based on the search history of the user; and a structure modification module configured to: the structure of the tree structure model of the search tag model is modified based on the user search history.

According to another aspect of the present disclosure, there is provided a search recommendation apparatus including: a node hit module configured to: responding to a received user search request, and selecting a node matched with the user search request in a search tag model as a hit node, wherein the search tag model is the search tag model generated by the model generation device according to the disclosure; and a search recommendation information generation module configured to: based on the hit node, search recommendation information is generated.

According to another aspect of the present disclosure, there is provided an electronic device including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a model generation method and/or a search recommendation method as described in the present disclosure.

According to another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform a model generation method and/or a search recommendation method according to the present disclosure.

According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein the computer program, when executed by a processor, implements a model generation method and/or a search recommendation method as described in the present disclosure.

According to one or more embodiments of the present disclosure, accurate and comprehensive search recommendation information can be provided to a user to meet the current search requirements of the user and further stimulate the relevant search requirements of the user.

It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the embodiments and, together with the description, serve to explain the exemplary implementations of the embodiments. The illustrated embodiments are for purposes of illustration only and do not limit the scope of the claims. Throughout the drawings, identical reference numbers designate similar, but not necessarily identical, elements.

FIG. 1 illustrates a schematic diagram of an exemplary system in which various methods described herein may be implemented, according to an embodiment of the present disclosure;

2A-2C illustrate schematic diagrams of a user interface displayed at a client during a user search according to embodiments of the present disclosure;

FIG. 3 shows a flow diagram of a model generation method according to an embodiment of the present disclosure;

FIG. 4 shows a schematic diagram of a search tag model, according to an embodiment of the present disclosure;

FIG. 5 illustrates a flow diagram of an example process for editing terms corresponding to one or more nodes of a search tag model based on a user search history in the method of FIG. 3, in accordance with an embodiment of the present disclosure;

FIG. 6 shows a flow diagram of a search recommendation method according to an embodiment of the present disclosure;

FIG. 7 illustrates a flow diagram of an example process of generating search recommendation information based on hit nodes in the method of FIG. 6, according to an embodiment of the disclosure;

FIG. 8 shows a block diagram of a model generation apparatus according to an embodiment of the present disclosure;

fig. 9 shows a block diagram of a structure of a search recommendation apparatus according to an embodiment of the present disclosure;

FIG. 10 illustrates a block diagram of an exemplary electronic device that can be used to implement embodiments of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

In the present disclosure, unless otherwise specified, the use of the terms "first", "second", etc. to describe various elements is not intended to limit the positional relationship, the timing relationship, or the importance relationship of the elements, and such terms are used only to distinguish one element from another. In some examples, a first element and a second element may refer to the same instance of the element, and in some cases, based on the context, they may also refer to different instances.

The terminology used in the description of the various described examples in this disclosure is for the purpose of describing particular examples only and is not intended to be limiting. Unless the context clearly indicates otherwise, if the number of elements is not specifically limited, the elements may be one or more. Furthermore, the term "and/or" as used in this disclosure is intended to encompass any and all possible combinations of the listed items.

Embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

Fig. 1 illustrates a schematic diagram of an exemplary system 100 in which various methods and apparatus described herein may be implemented in accordance with embodiments of the present disclosure. Referring to fig. 1, the system 100 includes one or

more client devices

101, 102, 103, 104, 105, and 106, a server 120, and one or more communication networks 110 coupling the one or more client devices to the server 120.

Client devices

101, 102, 103, 104, 105, and 106 may be configured to execute one or more applications.

In embodiments of the present disclosure, server 120 may run one or more services or software applications that enable the execution of the model generation methods and/or the search recommendation methods as described in the present disclosure.

In some embodiments, the server 120 may also provide other services or software applications that may include non-virtual environments and virtual environments. In certain embodiments, these services may be provided as web-based services or cloud services, for example, provided to users of

client devices

101, 102, 103, 104, 105, and/or 106 under a software as a service (SaaS) model.

In the configuration shown in fig. 1, server 120 may include one or more components that implement the functions performed by server 120. These components may include software components, hardware components, or a combination thereof, which may be executed by one or more processors. A user operating a

client device

101, 102, 103, 104, 105, and/or 106 may, in turn, utilize one or more client applications to interact with the server 120 to take advantage of the services provided by these components. It should be understood that a variety of different system configurations are possible, which may differ from system 100. Accordingly, fig. 1 is one example of a system for implementing the various methods described herein and is not intended to be limiting.

The user may use the

client device

101, 102, 103, 104, 105, and/or 106 to input a user search request and obtain search recommendation information and search results from the server 120 through the

client device

101, 102, 103, 104, 105, and/or 106. The client device may provide an interface that enables a user of the client device to interact with the client device. The client device may also output information to the user via the interface. Although fig. 1 depicts only six client devices, those skilled in the art will appreciate that any number of client devices may be supported by the present disclosure.

Client devices

101, 102, 103, 104, 105, and/or 106 may include various types of computer devices, such as portable handheld devices, general purpose computers (such as personal computers and laptop computers), workstation computers, wearable devices, gaming systems, thin clients, various messaging devices, sensors or other sensing devices, and so forth. These computer devices may run various types and versions of software applications and operating systems, such as MICROSOFT Windows, APPLE iOS, UNIX-like operating systems, Linux, or Linux-like operating systems (e.g., GOOGLE Chrome OS); or include various Mobile operating systems such as MICROSOFT Windows Mobile OS, iOS, Windows Phone, Android. Portable handheld devices may include cellular telephones, smart phones, tablets, Personal Digital Assistants (PDAs), and the like. Wearable devices may include head mounted displays and other devices. The gaming system may include a variety of handheld gaming devices, internet-enabled gaming devices, and the like. The client device is capable of executing a variety of different applications, such as various Internet-related applications, communication applications (e.g., email applications), Short Message Service (SMS) applications, and may use a variety of communication protocols.

Network 110 may be any type of network known to those skilled in the art that may support data communications using any of a variety of available protocols, including but not limited to TCP/IP, SNA, IPX, etc. By way of example only, one or more networks 110 may be a Local Area Network (LAN), an ethernet-based network, a token ring, a Wide Area Network (WAN), the internet, a virtual network, a Virtual Private Network (VPN), an intranet, an extranet, a Public Switched Telephone Network (PSTN), an infrared network, a wireless network (e.g., bluetooth, WIFI), and/or any combination of these and/or other networks.

The server 120 may include one or more general purpose computers, special purpose server computers (e.g., PC (personal computer) servers, UNIX servers, mid-end servers), blade servers, mainframe computers, server clusters, or any other suitable arrangement and/or combination. The server 120 may include one or more virtual machines running a virtual operating system, or other computing architecture involving virtualization (e.g., one or more flexible pools of logical storage that may be virtualized to maintain virtual storage for the server). In various embodiments, the server 120 may run one or more services or software applications that provide the functionality described below.

The computing units in server 120 may run one or more operating systems including any of the operating systems described above, as well as any commercially available server operating systems. The server 120 may also run any of a variety of additional server applications and/or middle tier applications, including HTTP servers, FTP servers, CGI servers, JAVA servers, database servers, and the like.

In some implementations, the server 120 may include one or more applications to analyze and consolidate data feeds and/or event updates received from users of the

client devices

101, 102, 103, 104, 105, and 106. Server 120 may also include one or more applications to display data feeds and/or real-time events via one or more display devices of

client devices

101, 102, 103, 104, 105, and 106.

In some embodiments, the server 120 may be a server of a distributed system, or a server incorporating a blockchain. The server 120 may also be a cloud server, or a smart cloud computing server or a smart cloud host with artificial intelligence technology. The cloud Server is a host product in a cloud computing service system, and is used for solving the defects of high management difficulty and weak service expansibility in the traditional physical host and Virtual Private Server (VPS) service.

The system 100 may also include one or more databases 130. In some embodiments, these databases may be used to store data and other information. For example, one or more of the databases 130 may be used to store information such as audio files and video files. The data store 130 may reside in various locations. For example, the data store used by the server 120 may be local to the server 120, or may be remote from the server 120 and may communicate with the server 120 via a network-based or dedicated connection. The data store 130 may be of different types. In certain embodiments, the data store used by the server 120 may be a database, such as a relational database. One or more of these databases may store, update, and search to and from the database in response to the command.

In some embodiments, one or more of the databases 130 may also be used by applications to store application data. The databases used by the application may be different types of databases, such as key-value stores, object stores, or regular stores supported by a file system.

The system 100 of fig. 1 may be configured and operated in various ways to enable application of the various methods and apparatus described in accordance with the present disclosure.

Fig. 2A-2C show schematic diagrams of a user interface 200 displayed at a client during a user search according to an embodiment of the present disclosure.

FIG. 2A shows a schematic diagram of a user interface 200 displayed at a client when a user enters a search request. As shown in fig. 2A, a user may input a search request through the user input module 210. According to some embodiments, as shown in fig. 2, a user may enter textual search information (e.g., "duck") through a text box 211 in the user input module 210 and trigger a "search" button in the user input module 210 (e.g., click on the "search" button using a mouse 201) to cause the client to send a user search request including the textual search information entered by the user to the server. According to other embodiments, the user may also input search information of other modalities, such as uploading pictures, through the user input module 210.

The server generates search recommendation information and search results according to the user search request, and transmits the generated search recommendation information and search results to the client. FIG. 2B shows a schematic diagram of the user interface 200 after the client receives the search recommendation information and search results.

As shown in fig. 2B, the search recommendation module 220 displays a plurality of pieces of search recommendation information (e.g., first recommendation information 221, second recommendation information 222, and third recommendation information 223) generated according to the user search request, for example, when the user searches for "duck", the recommendation information may include "duck", "koldy", "muscovy duck", "duck", and "mandarin duck", and the like.

As shown in fig. 2B, the search result module 230 displays a plurality of search results (e.g., first search content 231 and second search content 232) generated according to the user search request, for example, when the user searches for "duck", the search results are resources (e.g., pictures or web page information related to duck) searched according to "duck".

When the user selects any piece of recommendation information (e.g., clicks an icon corresponding to the recommendation information through the mouse 201), a further search may be performed based on the selected recommendation information to update the search results displayed in the search results module 230 of the client. FIG. 2C shows a schematic view of the user interface 200 after the user selects any piece of recommendation information.

As shown in fig. 2C, when the user selects the second recommendation information 222, the first search content 231 and the second search content 232 generated according to the user search request displayed by the search result module 230 are replaced with the third search content 233 and the fourth search content 234 generated according to the second recommendation information 222.

According to some embodiments, in response to the user selecting the second recommendation information 222, the client sends a search request including the second recommendation information to the server, the server performs a search again based on the search request including the second recommendation information, and sends the search result of the search again to the client.

For example, when the user selects the recommendation information "koldha" generated based on "duck", the client transmits a search request based on "koldha" to the server, the server performs a search again based on "koldha", and the search result generated based on "duck" in the search result module 230 of the client is replaced with the search result generated based on "koldha". Therefore, the search recommendation information generated based on the preliminary search request of the user can guide the user to further clarify and adjust the search requirement. Therefore, the search recommendation information should be comprehensive and accurate to fit the search requirements of the user as much as possible.

In order to provide comprehensive and accurate search recommendation information, embodiments of the present disclosure provide a model generation method, including: initializing a search tag model, wherein the search tag model comprises one or more tree structure models, each tree structure model of the search tag model corresponds to a tag type, and each node of the tree structure model is a search tag comprising at least one entry; editing entries corresponding to one or more nodes of the search tag model based on the search history of the user; and modifying the structure of the tree structure model of the search tag model based on the user search history.

FIG. 3 shows a flow diagram of a model generation method 300 according to an embodiment of the present disclosure. According to some embodiments, the method may be implemented by the server 120 described with reference to fig. 1.

At step S301, a search tag model is initialized. According to some embodiments, the search tag model comprises one or more tree structure models, each tree structure model of the search tag model corresponding to a tag type, each node of the tree structure model being a search tag comprising at least one entry.

According to some embodiments, professional taxonomy information may be obtained to initialize the search tag model, wherein the professional taxonomy information includes taxonomy levels, categories in each level, and relationships between categories of different levels. For example, the classification information about the living body includes biological classification levels (for example, classification levels of "living body" include "kingdom", "phylum", "class", "order", "family", "genus", and "species"), categories in each biological classification level (for example, "kingdom" includes two categories of "kingdom of animals" and "kingdom of plants" in a hierarchy corresponding to "kingdom"), and relationships between categories of different biological classification levels (for example, "mammalia" in a hierarchy corresponding to "class" includes "monocellular order", "epizoo subclass", "marsupial order" in a hierarchy corresponding to "order").

According to some embodiments, a tree structure model of the search tag model is generated according to the acquired professional classification information. According to some embodiments, each tree structure model of the search tag model corresponds to one tag type, e.g., "animal" corresponds to one tree structure model and "car" corresponds to another tree structure model.

The tree structure model may be a model representing a plurality of search tags using a tree structure. Each node in the tree structure model may be a search tag comprising at least one term. According to some embodiments, when a node is a search tag comprising a plurality of terms, the plurality of terms of the node comprises a name term indicating the name of the node and at least one alias term, e.g., for a node named "koji", the nodes comprise the terms "koji", "welshikokya", "cadiengley" and "penburokee" wherein "koji" is the name term, "welkya welchii", "cadieny welshikokya" and "penburoe welshikokya" are the alias terms.

At step S303, entries corresponding to one or more nodes of the search tag model are edited based on the user search history.

According to some embodiments, a user search history is a collection of user search requests received over a period of time by a server providing search services.

According to some embodiments, editing terms corresponding to one or more nodes of the search tag model based on the user search history comprises: extracting key words in user search requests of user search history; selecting nodes matched with the keywords in the search tag model; and in response to the node matching the keyword not containing an entry corresponding to the keyword, adding an entry corresponding to the keyword to the node matching the keyword. By adding the keywords in the user search request to the nodes matched with the keywords, synonym expansion in the search tag model is realized.

According to further embodiments, editing terms corresponding to one or more nodes of the search tag model based on the user search history comprises: calculating the number of times each node in the plurality of nodes is searched based on the user search history in response to the plurality of nodes in the search tag model including the same entry; and deleting the same entry in the rest nodes except the node which is searched for the most times in the plurality of nodes. For example, the nodes "azalea" and "azalea bird" each include the word "azalea", wherein the node "azalea" is searched for the most number of times, the word "azalea" is deleted from the node "azalea bird", and the word "azalea" is retained only in the "azalea". The problem of word ambiguity is solved by selecting the node with the most searched times as the node corresponding to the same entry.

According to still further embodiments, editing terms corresponding to one or more nodes of the search tag model based on the user search history comprises: and converting the entries corresponding to one or more nodes of the search tag model into a format required by the search. According to some embodiments, the vocabulary entry may be converted to conform to a format required by the search, such as full-half-angle conversion, case conversion, language conversion, simplified and unsimplified conversion, and meaningless symbol removal.

At step S305, the structure of the tree structure model of the search tag model is modified based on the user search history.

According to some embodiments, modifying the structure of the tree structure model of the search tag model based on the user search history comprises: for each tree structure model, calculating the times of searching each layer of the tree structure model based on the user search history, wherein the times of searching each layer in the tree structure model are the times of searching any node in the layer; and deleting the layers in the tree structure model, wherein the searched times are less than a preset time threshold value.

According to some embodiments, calculating the number of times each level of the tree structure model is searched comprises: for each layer of the tree structure model, the number of times any node in the layer is searched is calculated. That is, whenever any node in the layer is searched in a user search, the layer is searched in the user search.

According to some embodiments, for a user search request in a user search history, extracting a keyword of the user search request, and selecting a node matched with the keyword in a search tag model, wherein the matched node is judged to be searched by the user search request.

According to some embodiments, after deleting a layer searched in the tree structure model a number of times of which is less than a predetermined number of times threshold, a node in a layer below the deleted layer is connected to a node in a layer above the deleted layer according to an original connection relationship of the tree structure model.

For example, a first level of the tree structure model includes nodes A and B, and a second level includes the children of node A, node A₁And A₂And a child node B of the node B₁And B₂The third layer includes node A₁Child node A of₁₁And A₁₂Node A₂Child node A of₂₁And A₂₂Node B₁Child node B of₁₁And B₁₂And node B₂Child node B of₂₁And B₂₂Then after deleting the second layer, node A₁₁、A₁₂、A₂₁And A₂₂Become child nodes of node A, and B₁₁、B₁₂、B₂₁And B₂₂Becoming a child of node B.

By deleting the layer of which the searched times in the tree structure model of the search tag model are smaller than the preset time threshold, the redundant structure in the search tag model is simplified, and the speed of matching nodes in the search tag model according to the search request of the user in the follow-up process is improved.

According to some embodiments, modifying the structure of the tree structure model of the search tag model based on the user search history further comprises: for each tree structure model, calculating the number of similar nodes in the adjacent layer of the tree structure model; and in response to the number of similar nodes in the adjacent tier being greater than the predetermined number of nodes, merging the adjacent tiers.

According to some embodiments, for each tree structure model, calculating the number of similar nodes in adjacent layers of the tree structure model comprises: for each node in a first layer in adjacent layers, in response to the node having a similar entry to a corresponding node in a second layer, determining that the node and the corresponding node in the second layer are similar nodes; and calculating the number of nodes having corresponding similar nodes in the first layer as the number of similar nodes in the adjacent layer. According to some embodiments, the first layer is located above the second layer.

According to some embodiments, the similarity between two terms may be calculated by a cosine value similarity algorithm or an L's edit distance algorithm, and when the similarity between two terms exceeds a similarity threshold, the two terms are judged to be similar terms.

According to some embodiments, merging adjacent layers comprises: merging similar nodes in adjacent layers, and adding the merged nodes into the merged layer; and adding nodes except similar nodes in the adjacent layers into the merged layer. According to some embodiments, merging similar nodes in adjacent layers comprises: and adding the entries of the similar nodes into the merged nodes.

In the model generation method provided by the embodiment of the disclosure, after the search tag model is initialized, based on the user search history, entries corresponding to one or more nodes of the search tag model are adjusted and the structure of the tree structure model of the search tag model is modified, so that the generated search tag model can accurately and comprehensively reflect the user search requirements.

FIG. 4 shows a schematic diagram of a search tag model 400 according to an embodiment of the present disclosure.

As shown in fig. 4, the search tag model 400 includes a first tree structure model 400a and a second tree structure model 400b, wherein the first tree structure model 400a corresponds to a first tag type (e.g., "animal") and the second tree structure model 400b corresponds to a second tag type (e.g., "car"). It should be understood that the number of tree structure models in the search tag model 400 can be more (e.g., 3) or less (e.g., 1).

The first tree structure model 400a and the second tree structure model 400b each include a plurality of levels, wherein each level corresponds to a classification level. For example, the first, second, and

third levels

410a, 420a, and 430a of the first tree structure model 400a correspond to "kingdom", "class", "family", respectively, and the first, second, third, and fourth levels 410b, 420b, 430b, and 440b of the second tree structure model 400b correspond to "brand of automobile", "type of automobile", "automobile body series", and "type of automobile", respectively.

In the first tree structure model 400a and the second tree structure model 400b, the nodes in the same hierarchy are nodes under the same classification level, for example, the

nodes

421a, 422a in the second hierarchy 420a of the first tree structure model 400a correspond to "mammalia", "aventura", respectively; the connecting lines between the nodes in different levels indicate the dependency relationship therebetween, for example, in the first tree structure model 400a, the

nodes

431a and 432a located at the third level correspond to "feline", "canine", and are child nodes of the node 421a located at the second level corresponding to "mammalia".

Fig. 5 shows a flowchart of an example process of editing terms corresponding to one or more nodes of the search tag model based on the user search history in the method of fig. 3 (step S303), according to an embodiment of the present disclosure.

At step S501, keywords in a user search request of a user search history are extracted.

According to some embodiments, the keyword may be the search information itself, e.g., the keyword is "panda" when the user searches for the term "panda". According to further embodiments, the keyword may be a word in the search information indicating a target of the search, for example, when the user searches for the entry "kokyo picture", the keyword is "kokyo".

At step S503, a node in the search tag model that matches the keyword is selected.

According to some embodiments, a tree structure model in the search tag model is searched for nodes that match the keyword. According to some embodiments, similarity of the keyword and the entry corresponding to the node is calculated to determine whether the keyword and the node are matched.

At step S505, in response to the node matching the keyword not containing the entry corresponding to the keyword, the entry corresponding to the keyword is added to the node matching the keyword, for example, as an alias entry for the node.

In the embodiment as described with reference to FIG. 5, the term information in the search tag model is enriched by "mapping" synonyms in the user search history to matching nodes of the search tag model.

According to some embodiments, the model generation method as described in the present disclosure, further comprising, after modifying the structure of the tree structure model of the search tag model based on the user search history: and deleting the same entries in other nodes except the node with the lowest hierarchy among the nodes with the same entries in response to the nodes of different layers of the same tree structure model of the search tag model having the same entries. For example, if the node 421a at the second hierarchical level 420a and the node 432a at the third hierarchical level 430a shown in fig. 4 have the same entry, the same entry in the node 421a at the second hierarchical level 420a is deleted.

According to some embodiments, the model generation method as described in the present disclosure further comprises, after modifying the structure of the tree structure model of the search tag model based on the user search history: for each layer of each tree structure model, calculating the number of times each node in the layer is searched based on the user search history; and sorting the nodes in the layer according to the searched times of each node in the layer, wherein the result of sorting the nodes in the layer is the search heat sorting of the layer.

According to further embodiments, the model generation method as described in the present disclosure further comprises, after modifying the structure of the tree structure model of the search tag model based on the user search history: for each node in each tree structure model, calculating the times of the common occurrence of other nodes in the layer where the node is located and the node in the user search history based on the user search history; and sequencing other nodes in the layer where the node is located according to the co-occurrence times, wherein the result of sequencing the other nodes in the layer where the node is located is the co-occurrence sequencing of the node.

In the present disclosure, if two search requests before and after the same user (for example, two search requests spaced apart by less than a certain time length) respectively correspond to two nodes in the same layer, the two nodes are considered to appear in common in the user search history. For example, when the user searches for "cat" after searching for "dog", the nodes "canine" and "feline" are considered to co-occur in the user search history.

The embodiment of the present disclosure further provides a search recommendation method, including: in response to receiving a user search request, selecting a node in a search tag model, which is matched with the user search request, as a hit node, wherein the search tag model is generated according to the model generation method disclosed by the disclosure; and generating search recommendation information based on the hit nodes.

FIG. 6 shows a flow diagram of a search recommendation method 600 according to an embodiment of the present disclosure.

At step S601, in response to receiving a user search request, a node in the search tag model that matches the user search request is selected as a hit node.

According to some embodiments, in response to receiving a user search request, selecting a node in the search tag model that matches the user search request comprises: in response to receiving a user search request, extracting keywords in the user search request; and selecting a node matched with the user search request in the search tag model as a hit node based on the keyword in the user search request, wherein the hit node comprises a term matched with the keyword in the user search request.

As described above, the keyword may be the search information itself or a word indicating a search target in the search information, and whether the keyword matches a node may be determined by calculating the similarity of the keyword and a vocabulary entry corresponding to the node.

At step S603, based on the hit node, search recommendation information is generated.

According to some embodiments, the search recommendation information is generated based on the hit node and the nodes in the search tag model that are related to the hit node, e.g., based on the hit node itself, other nodes in the layer where the hit node is located, and/or a parent node of the hit node.

For example, when the hit node is "canine", search recommendation information is generated from the node "canine", the "feline", "human", "panda", and the parent node "mammal" of the node "canine" at the same level as the node "canine".

According to some embodiments, for each of the hit node and a node in the search tag model that is related to the hit node, a corresponding picture is matched for the node based on the name of the node, and based on the name of the node and the matched picture, teletext information corresponding to the node is generated.

According to some embodiments, generating the search recommendation information based on the hit nodes comprises: generating information corresponding to the hit node; generating information corresponding to other nodes of the layer where the hit nodes are located based on the co-occurrence ranking of the hit nodes and the search heat ranking of the layer where the hit nodes are located, wherein the co-occurrence ranking of the hit nodes is as follows: and sequencing results of other nodes in the layer where the hit nodes are located according to the times of the common appearance of the other nodes in the layer where the hit nodes are located and the hit nodes in the user search history, wherein the search heat sequencing of the layer where the hit nodes are located is as follows: sequencing the nodes in the layer where the hit nodes are located according to the number of times that each node in the layer where the hit nodes are located is searched; and generating search recommendation information based on the information corresponding to the hit node and information corresponding to other nodes of the layer where the hit node is located, wherein in the search recommendation information, the information corresponding to the hit node is located before the information corresponding to other nodes of the layer where the hit node is located.

Fig. 7 shows a flowchart of an example process of generating search recommendation information based on hit nodes in the method of fig. 6 (step S603), according to an embodiment of the present disclosure.

At step S701, information corresponding to a hit node is generated.

At step S703, information corresponding to other nodes of the layer in which the hit node is located is generated based on the co-occurrence ranking of the hit node and the search heat ranking of the layer in which the hit node is located.

The co-occurrence ordering of hit nodes is: and sequencing the other nodes in the layer where the hit node is located according to the times of the common occurrence of the other nodes in the layer where the hit node is located and the hit node in the user search history. The search heat ranking of the layer where the hit nodes are located is: and sequencing the nodes in the layer where the hit nodes are located according to the number of times that each node in the layer where the hit nodes are located is searched.

At step S705, search recommendation information in which information corresponding to the hit node precedes information corresponding to other nodes of the layer in which the hit node is located is generated based on the information corresponding to the hit node and information corresponding to other nodes of the layer in which the hit node is located.

According to some embodiments, in addition to the information corresponding to the hit node and the information corresponding to other nodes of the layer in which the hit node is located, information of other nodes related to the hit node, for example, information corresponding to a parent node of the hit node, may be included in the search recommendation information.

According to some embodiments, generating information corresponding to other nodes of the tier in which the hit node is located based on the co-occurrence ranking of the hit node and the search heat ranking of the tier in which the hit node is located comprises: generating information corresponding to a first predetermined number of nodes based on the co-occurrence ranking of the hit nodes, wherein the first predetermined number of nodes is a first predetermined number of nodes in the co-occurrence ranking of the hit nodes; and generating information of remaining nodes corresponding to the layer where the hit node is located, excluding the hit node and the first predetermined number of nodes, based on the search heat ranking of the layer where the hit node is located, wherein the information corresponding to the first predetermined number of nodes is prior to the information corresponding to the remaining nodes, among the information corresponding to other nodes of the layer where the hit node is located.

For example, when the first predetermined number is 5, the search recommendation information includes, in order from front to back: information corresponding to the hit node, information corresponding to the co-occurrence top-five nodes of the hit node, and information corresponding to the remaining nodes of the layer where the hit node is located.

In the search recommendation method according to the present disclosure, based on the co-occurrence ranking of the hit nodes and the search heat ranking of the layer where the hit nodes are located, information corresponding to other nodes of the layer where the hit nodes are located is generated, so that a user can expand the search and adjust the search method more easily when searching, the time for the user to reach a search target is shortened, and the search scale of the user is enlarged.

Fig. 8 shows a block diagram of a model generation apparatus 800 according to an embodiment of the present disclosure.

As shown in fig. 8, the model generation apparatus 800 includes: a model initialization module 801 configured to: initializing a search tag model, wherein the search tag model comprises one or more tree structure models, each tree structure model of the search tag model corresponds to a tag type, and each node of the tree structure model is a search tag comprising at least one entry; an entry editing module 802 configured to: editing entries corresponding to one or more nodes of the search tag model based on the search history of the user; and a structure modification module 803 configured to: the structure of the tree structure model of the search tag model is modified based on the user search history.

Fig. 9 shows a block diagram of a search recommendation apparatus 900 according to an embodiment of the present disclosure.

As shown in fig. 9, the search recommendation apparatus 900 includes: a node hit module 901 configured to: responding to a received user search request, and selecting a node matched with the user search request in a search tag model as a hit node, wherein the search tag model is the search tag model generated by the model generation device according to the disclosure; and a search recommendation information generation module 902 configured to: based on the hit node, search recommendation information is generated.

In the technical scheme of the disclosure, the acquisition, storage, application and the like of the personal information of the related user all accord with the regulations of related laws and regulations, and do not violate the good customs of the public order.

According to an embodiment of the present disclosure, there is also provided an electronic device, a readable storage medium, and a computer program product.

According to an embodiment of the present disclosure, there is provided an electronic apparatus including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a model generation method and/or a search recommendation method as described in the present disclosure.

According to an embodiment of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute a model generation method and/or a search recommendation method according to the present disclosure.

According to an embodiment of the present disclosure, a computer program product is provided, comprising a computer program, wherein the computer program, when executed by a processor, implements a model generation method and/or a search recommendation method as described in the present disclosure.

Referring to fig. 10, a block diagram of a structure of an electronic device 1000, which may be a server or a client of the present disclosure, which is an example of a hardware device that may be applied to aspects of the present disclosure, will now be described. Electronic device is intended to represent various forms of digital electronic computer devices, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 10, the apparatus 1000 includes a computing unit 1001 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM)1002 or a computer program loaded from a storage unit 1008 into a Random Access Memory (RAM) 1003. In the RAM1003, various programs and data necessary for the operation of the device 1000 can also be stored. The calculation unit 1001, the ROM1002, and the RAM1003 are connected to each other by a bus 1004. An input/output (I/O) interface 1005 is also connected to bus 1004.

A number of components in device 1000 are connected to I/O interface 1005, including: input section 1006, output section 1007, storage section 1008, and communication section 1009. Input unit 1006 may be any type of device capable of inputting information to device 1000, and input unit 1006 may receive input numeric or character information and generate key signal inputs related to user settings and/or function controls of the electronic device, and may include, but is not limited to, a mouse, a keyboard, a touch screen, a track pad, a track ball, a joystick, a microphone, and/or a remote control. Output unit 1007 may be any type of device capable of presenting information and may include, but is not limited to, a display, speakers, a video/audio output terminal, a vibrator, and/or a printer. The storage unit 1008 may include, but is not limited to, a magnetic disk, an optical disk. The communications unit 1009 allows the device 1000 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunications networks, and may include, but is not limited to, modems, network cards, infrared communication devices, wireless communication transceivers, and/or chipsets, such as bluetooth (TM) devices, 1302.11 devices, WiFi devices, WiMax devices, cellular communication devices, and/or the like.

Computing unit 1001 may be a variety of general and/or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 1001 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The computing unit 1001 performs the various methods and processes described above, such as the method 300 and/or the method 600. For example, in some embodiments, method 300 and/or method 600 may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 1008. In some embodiments, part or all of the computer program may be loaded and/or installed onto device 1000 via ROM1002 and/or communications unit 1009. When the computer program is loaded into RAM1003 and executed by computing unit 1001, one or more steps of method 300 and/or method 600 described above may be performed. Alternatively, in other embodiments, the computing unit 1001 may be configured to perform the method 300 and/or the method 600 by any other suitable means (e.g., by way of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on 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.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.

The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server with a combined blockchain.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be performed in parallel, sequentially or in different orders, and are not limited herein as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved.

Although embodiments or examples of the present disclosure have been described with reference to the accompanying drawings, it is to be understood that the above-described methods, systems and apparatus are merely exemplary embodiments or examples and that the scope of the present invention is not limited by these embodiments or examples, but only by the claims as issued and their equivalents. Various elements in the embodiments or examples may be omitted or may be replaced with equivalents thereof. Further, the steps may be performed in an order different from that described in the present disclosure. Further, various elements in the embodiments or examples may be combined in various ways. It is important that as technology evolves, many of the elements described herein may be replaced with equivalent elements that appear after the present disclosure.

Claims

1. A model generation method, comprising:

initializing a search tag model, wherein the search tag model comprises one or more tree structure models, each tree structure model of the search tag model corresponds to a tag type, and each node of the tree structure model is a search tag comprising at least one entry;

editing entries corresponding to one or more nodes of the search tag model based on the search history of the user; and

modifying a structure of a tree structure model of the search tag model based on the user search history.

2. The method of claim 1, wherein editing the terms corresponding to the one or more nodes of the search tag model based on the user search history comprises:

extracting key words in user search requests of the user search history;

selecting nodes matched with the keywords in the search tag model; and

in response to the node matching the keyword not containing an entry corresponding to the keyword, adding an entry corresponding to the keyword to the node matching the keyword.

3. The method of claim 1, wherein editing the terms corresponding to the one or more nodes of the search tag model based on the user search history comprises:

calculating, based on the user search history, a number of times each node in the plurality of nodes was searched in response to the plurality of nodes in the search tag model including the same term; and

and deleting the same entry in the rest nodes except the node which is searched for the most times in the plurality of nodes.

4. The method of any of claims 1-3, wherein the modifying the structure of the tree structure model of the search tag model based on the user search history comprises:

for each tree structure model, calculating the times of searching each layer of the tree structure model based on the user search history, wherein the times of searching each layer in the tree structure model are the times of searching any node in the layer; and

and deleting the layers searched in the tree structure model for times smaller than a preset time threshold.

5. The method of claim 4, wherein the modifying the structure of the tree structure model of the search tag model based on the user search history further comprises:

for each tree structure model, calculating the number of similar nodes in the adjacent layer of the tree structure model; and

merging the adjacent layers in response to the number of similar nodes in the adjacent layers being greater than a predetermined number of nodes.

6. The method of claim 5, wherein for each tree structure model, calculating the number of similar nodes in adjacent layers of the tree structure model comprises:

for each node in a first layer of the adjacent layers, determining that the node and a corresponding node in the second layer are similar nodes in response to the node having similar entries to the corresponding node in the second layer; and

calculating the number of nodes having corresponding similar nodes in the first layer as the number of similar nodes in the adjacent layer.

7. The method of claim 6, wherein said merging the adjacent layers comprises:

merging similar nodes in the adjacent layers, and adding the merged nodes into the merged layers; and

and adding the nodes except the similar nodes in the adjacent layer into the merged layer.

8. The method of any of claims 1-3, further comprising, after the modifying the structure of the tree structure model of the search tag model based on the user search history:

in response to nodes of different layers of the same tree structure model of the search tag model having the same entry, deleting the same entry in nodes other than the node with the lowest hierarchy among the nodes having the same entry.

9. The method of any of claims 1-3, further comprising, after the modifying the structure of the tree structure model of the search tag model based on the user search history:

for each layer of each tree structure model, calculating the number of times each node in the layer is searched based on the user search history; and

and sequencing the nodes in the layer according to the searched times of each node in the layer, wherein the sequencing result of the nodes in the layer is the sequencing of the searching heat degree of the layer.

10. The method of any of claims 1-3, further comprising, after the modifying the structure of the tree structure model of the search tag model based on the user search history:

for each node in each tree structure model, calculating the times of the common occurrence of other nodes in the layer where the node is located and the node in the user search history based on the user search history; and

and sequencing other nodes in the layer where the node is located according to the co-occurrence times, wherein the result of sequencing the other nodes in the layer where the node is located is the co-occurrence sequencing of the node.

11. A search recommendation method, comprising:

in response to receiving a user search request, selecting a node in a search tag model matching the user search request as a hit node, wherein the search tag model is a search tag model generated by the model generation method according to any one of claims 1 to 10; and

and generating search recommendation information based on the hit nodes.

12. The method of claim 11, wherein said selecting a node in the search tag model that matches a user search request in response to receiving the user search request comprises:

in response to receiving the user search request, extracting keywords in the user search request; and

and selecting a node matched with the user search request in the search tag model as the hit node based on the keyword in the user search request, wherein the hit node comprises an entry matched with the keyword in the user search request.

13. The method of claim 11, wherein the generating search recommendation information based on the hit nodes comprises:

generating information corresponding to the hit node;

generating information of other nodes corresponding to the layer where the hit nodes are located based on the common occurrence sequence of the hit nodes and the search heat sequence of the layer where the hit nodes are located, wherein the common occurrence sequence of the hit nodes is as follows: and sequencing results of other nodes in the layer where the hit node is located according to the times of common occurrence of the other nodes in the layer where the hit node is located and the hit node in the user search history, wherein the search heat sequencing of the layer where the hit node is located is as follows: according to the number of times each node in the layer where the hit node is located is searched, sequencing the nodes in the layer where the hit node is located; and

generating the search recommendation information based on the information corresponding to the hit node and information corresponding to other nodes of a layer in which the hit node is located, wherein in the search recommendation information, the information corresponding to the hit node precedes the information corresponding to other nodes of the layer in which the hit node is located.

14. The method of claim 13, wherein generating information corresponding to other nodes of the tier in which the hit node is located based on the co-occurrence ranking of the hit node and the search heat ranking of the tier in which the hit node is located comprises:

generating information corresponding to a first predetermined number of nodes based on the co-occurrence ranking of the hit nodes, wherein the first predetermined number of nodes is a first predetermined number of nodes in the co-occurrence ranking of the hit nodes; and

generating information corresponding to remaining nodes of the layer in which the hit node is located, excluding the hit node and the first predetermined number of nodes, based on a search heat ranking of the layer in which the hit node is located,

wherein, among the information corresponding to the other nodes of the layer in which the hit node is located, the information corresponding to the first predetermined number of nodes precedes the information corresponding to the remaining nodes.

15. A model generation apparatus comprising:

a model initialization module configured to: initializing a search tag model, wherein the search tag model comprises one or more tree structure models, each tree structure model of the search tag model corresponds to a tag type, and each node of the tree structure model is a search tag comprising at least one entry;

an entry editing module configured to: editing entries corresponding to one or more nodes of the search tag model based on the search history of the user; and

a structure modification module configured to: modifying a structure of a tree structure model of the search tag model based on the user search history.

16. A search recommendation apparatus comprising:

a node hit module configured to: in response to receiving a user search request, selecting a node in a search tag model that matches the user search request as a hit node, wherein the search tag model is the search tag model generated by the model generation apparatus according to claim 15; and

a search recommendation information generation module configured to: and generating search recommendation information based on the hit nodes.

17. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein

The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-14.

18. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-14.

19. A computer program product comprising a computer program, wherein the computer program realizes the method of any one of claims 1-14 when executed by a processor.