Content searching method and device, equipment and storage medium

Abstract

The embodiment of the invention provides a content searching method and device, equipment and a storage medium. The method comprises the following steps: determining a first matching degree between a first semantic feature of a search word and a group of reference semantic features of a group of candidate contents; at least one target content is determined from the group of candidate contents at least based on the first matching degree to serve as a search result for the search word, and the group of reference semantic features are determined based on the following processes that attribute information of the group of candidate contents about multiple preset attributes is determined; and generating a set of reference semantic features for the set of candidate content based on the attribute information. Therefore, according to the embodiment of the invention, the search result associated with the search word can be accurately matched based on the search word.

Description

Technical Field

[0001] Example embodiments of the present disclosure generally relate to the field of computers, and more particularly, to a method, apparatus, device, and computer-readable storage medium for content search. Background Art

[0002] With the rapid development of Internet technology and the explosive growth of information, the demand for efficiently obtaining required information from massive data is increasing. In recent years, content search technology has continued to evolve with the increase in search demand for unstructured data. In order to provide users with more comprehensive and accurate search results, the optimization of content search functions is undoubtedly the key to improving user experience and satisfaction. Summary of the invention

[0003] In a first aspect of the present disclosure, a method for content search is provided. The method includes: determining a first matching degree between a first semantic feature of a search term and a set of reference semantic features of a set of candidate contents; and determining at least one target content from the set of candidate contents based at least on the first matching degree as a search result for the search term, wherein the set of reference semantic features is determined based on the following process: determining attribute information of a set of candidate contents about a plurality of preset attributes; and generating a set of reference semantic features of a set of candidate contents based on the attribute information.

[0004] In a second aspect of the present disclosure, a device for providing content search is provided. The device includes: a first matching degree calculation module, configured to determine a first matching degree between a first semantic feature of a search term and a set of reference semantic features of a set of candidate contents; and a search result determination module, configured to determine at least one target content from a set of candidate contents based at least on the first matching degree as a search result for the search term, wherein the set of reference semantic features is determined based on the following process: determining attribute information of a set of candidate contents about a plurality of preset attributes; and generating a set of reference semantic features of a set of candidate contents based on the attribute information.

[0005] In a third aspect of the present disclosure, an electronic device is provided. The device includes at least one processing unit; and at least one memory, the at least one memory is coupled to the at least one processing unit and stores instructions for execution by the at least one processing unit. When the instructions are executed by the at least one processing unit, the device executes the method of the first aspect.

[0006] In a fourth aspect of the present disclosure, a computer-readable storage medium is provided, wherein a computer program is stored on the computer-readable storage medium, and the computer program can be executed by a processor to implement the method of the first aspect.

[0007] It should be understood that the contents described in this content section are not intended to limit the key features or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0009] Figure 1 A schematic diagram showing an example environment in which embodiments of the present disclosure can be implemented;

[0010] Figure 2 A flowchart of content search according to some embodiments of the present disclosure is shown;

[0011] Figure 3 The detailed process of content search according to some embodiments of the present disclosure is shown;

[0012] Figure 4 The construction process of training data according to some embodiments of the present disclosure is shown;

[0013] Figure 5 A block diagram showing an apparatus for content search according to some embodiments of the present disclosure; and

[0014] Figure 6 A block diagram of an electronic device capable of implementing various embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0015] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0016] It should be noted that the titles of any sections / subsections provided herein are not restrictive. Various embodiments are described throughout this article, and any type of embodiment may be included under any section / subsection. In addition, the embodiments described in any section / subsection may be combined in any manner with any other embodiments described in the same section / subsection and / or different sections / subsections.

[0017] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The term "some embodiments" should be understood as "at least some embodiments". Other explicit and implicit definitions may be included below. The terms "first", "second", etc. may refer to different or the same objects. Other explicit and implicit definitions may be included below.

[0018] The embodiments of the present disclosure may involve user data, data acquisition and / or use, etc. These aspects are subject to the corresponding laws, regulations and relevant provisions. In the embodiments of the present disclosure, all data collection, acquisition, processing, processing, forwarding, use, etc. are carried out on the premise that the user knows and confirms. Accordingly, when implementing each embodiment of the present disclosure, the type, scope of use, usage scenario, etc. of the data or information that may be involved should be informed to the user and the user's authorization should be obtained in an appropriate manner in accordance with the relevant laws and regulations. The specific notification and / or authorization method can vary according to the actual situation and application scenario, and the scope of the present disclosure is not limited in this respect.

[0019] In this specification and the embodiments, if personal information processing is involved, it will be processed on the premise of having a legal basis (such as obtaining the consent of the subject of personal information, or it is necessary to perform a contract, etc.), and will only be processed within the scope of regulations or agreements. If a user refuses to process personal information other than the necessary information for basic functions, it will not affect the user's use of basic functions.

[0020] As briefly mentioned above, with the rapid development of Internet technology and the explosive growth of information, the demand for efficiently obtaining required information from massive data is increasing. In recent years, content search technology has continued to evolve with the increase in search demand for unstructured data. In order to provide users with more comprehensive and accurate search results, the optimization of content search functions is undoubtedly the key to improving user experience and satisfaction.

[0021] To this end, an embodiment of the present disclosure proposes a solution for content search. According to various embodiments of the present disclosure, a first matching degree between a first semantic feature of a search term and a set of reference semantic features of a set of candidate contents is determined; and at least based on the first matching degree, at least one target content is determined from the set of candidate contents as a search result for the search term, wherein the set of reference semantic features is determined based on the following process: determining attribute information of a set of candidate contents about multiple preset attributes; and generating a set of reference semantic features of a set of candidate contents based on the attribute information.

[0022] In this way, the embodiments of the present disclosure can determine the semantic features of a set of candidate contents based on multiple attribute information of a set of candidate contents, and obtain search results based on matching the semantic features of a set of candidate contents with search terms, thereby making the obtained search results more accurate.

[0023] Example embodiments of the present disclosure are described below with reference to the accompanying drawings.

[0024] Example Environment

[0025] Figure 1 1 is a schematic diagram of an example environment 100 in which embodiments of the present disclosure can be implemented. Figure 1 As shown, the environment 100 includes a terminal device 110 and an electronic device 130 .

[0026] In this example environment 100, the terminal device 110 may run an application 120 for providing a search function. The application 120 may be any appropriate type of application for providing a search function, examples of which may include but are not limited to: online video applications, social applications, content sharing applications, etc. The user 140 may interact with the application 120 via the terminal device 110 and / or its attached devices.

[0027] exist Figure 1 In the environment 100, if the application 120 is active, the electronic device 110 can present an interface 150 corresponding to the application 120. The interface 150 may include various pages provided by the application 120, and the interface 150 may, for example, provide a search result page associated with the search term. The search result page may include multiple candidate contents, and the candidate contents may, for example, be text content, media content, or a combination of text content and media content.

[0028] In some embodiments, the terminal device 110 communicates with the electronic device 130 to provide services for the application 120. The electronic device 130 may provide management, configuration, maintenance, and search functions for applications or websites.

[0029] The terminal device 110 can be any type of mobile terminal, fixed terminal or portable terminal, including mobile phones, desktop computers, laptop computers, notebook computers, netbook computers, tablet computers, media computers, multimedia tablets, handheld computers, portable game terminals, VR / AR devices, personal communication systems (PCS) devices, personal navigation devices, personal digital assistants (PDA), audio / video players, digital cameras / camcorders, positioning devices, television receivers, radio broadcast receivers, e-book devices, game devices, or any combination of the foregoing, including accessories and peripherals of these devices or any combination thereof. In some embodiments, the terminal device 110 can also support any type of interface for the user (such as "wearable" circuits, etc.).

[0030] The electronic device 130 may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content distribution networks, and big data and artificial intelligence platforms. The electronic device 130 may include, for example, a computing system / server, such as a mainframe, an edge computing node, a computing device in a cloud environment, and the like. The electronic device 130 may provide background services for the application 120 that supports content search in the terminal device 110.

[0031] A communication connection may be established between the electronic device 130 and the terminal device 110. The communication connection may be established in a wired manner or a wireless manner. The communication connection may include, but is not limited to, a Bluetooth connection, a mobile network connection, a Universal Serial Bus (USB) connection, a Wireless Fidelity (WiFi) connection, etc., and the embodiments of the present disclosure are not limited in this respect. In the embodiments of the present disclosure, the electronic device 130 and the terminal device 110 may implement signaling interaction through the communication connection between the two.

[0032] It should be understood that the structure and function of the various elements in the environment 100 are described for exemplary purposes only and do not imply any limitation on the scope of the present disclosure.

[0033] Some example embodiments of the present disclosure will be described below with continued reference to the accompanying drawings.

[0034] Example Process

[0035] Figure 2FIG. 2 is a flowchart of a process 200 for content search according to some embodiments of the present disclosure. The process 200 may be implemented at the electronic device 130. Figure 1 The process 200 is described below.

[0036] like Figure 2 As shown, in box 210, the electronic device 130 determines a first matching degree between a first semantic feature of a search term and a set of reference semantic features of a set of candidate contents.

[0037] As an example, Figure 3 As shown, Figure 3 The overall process of content search of an embodiment of the present invention is shown. The electronic device 130 can obtain a search term 306. The search term 306 can be, for example, content input by the user 140, or it can be a search term generated based on the content input by the user through a language model or other model for generating or optimizing the input content. After obtaining the search term 306, the electronic device 130 can call the semantic extraction model 304 to extract the semantic features of the search term 306 to obtain a first semantic feature 307. Furthermore, the electronic device 130 can use the first semantic feature 307 and a set of reference semantic features 305 of a set of candidate content as an input sequence of a semantic matching model 308 to obtain a semantic relevance score 309 (i.e., a first degree of matching).

[0038] Continue to refer Figure 2 In block 220, the electronic device 130 determines at least one target content from a set of candidate content based at least on the first matching degree as a search result for the search term. Determining the search result by the first matching degree associated with the semantic feature can make the search result more accurate.

[0039] As an example, the target content may be text content, media content, or a combination of text content and media content. The electronic device 130 may sort the candidate content based on the matching degree between the search term and each candidate content in a set of candidate content. For example, the sorting may be performed in a positive order, that is, the candidate content with a higher matching degree with the search term is ranked higher.

[0040] In some scenarios, after determining multiple target contents, the electronic device 130 may send the multiple target contents and the sorting information to the mobile terminal 110. The mobile terminal 110 may present the multiple target contents on the screen based on the sorting information, so that the user can more conveniently browse the contents more related to the search term, thereby improving the user experience.

[0041] Continue to refer Figure 2 In block 220, the electronic device 130 determines a set of reference semantic features based on the following process: determining a set of attribute information of candidate content about a plurality of preset attributes. Figure 3 As shown, the electronic device 130 may obtain historical text and / or video 301. Further, the electronic device 130 may call a large language model 301 (ie, a generative model) to determine attribute information 303 of a plurality of preset attributes.

[0042] In some embodiments, the electronic device 130 may provide a set of candidate content and a guide item to the generative model, and the guide item is used to instruct the generative model to extract the values ​​of multiple preset attributes. Further, the electronic device 130 may obtain attribute information of multiple preset attributes generated by the generative model. The preset attributes include multiple of the following: title information of the candidate content, summary of the candidate content, keywords of the candidate content, product information in the candidate content, and multiple publisher information of the candidate content.

[0043] As an example, Figure 3 As shown, the electronic device 130 can instruct the large language model 302 to generate attribute information of various preset attributes in the historical text and / or video 301 through appropriate prompt words. The attribute information may include, for example, a summary of the historical text and / or video 301, keywords, and entities and / or descriptions of vehicles appearing in the historical text and / or video 301. Keywords may, for example, be text content used to summarize vehicle-related information appearing in the historical text and / or video 301. The entity and / or description of the vehicle may, for example, be a section of content describing the configuration of the vehicle, or may also be configuration information of the vehicle.

[0044] In some scenarios, the electronic device 130 can call the large language model 302 to generate a summary of the historical text and / or video 301 to replace the main text as the input data of the semantic extraction model. In this way, the input length of the semantic extraction model can be effectively reduced, and the representation difficulty can be simplified, thereby generating a higher quality semantic representation vector. These vectors can be better matched with the search term 306, thereby improving the overall matching effect.

[0045] In other scenarios, the electronic device 130 may receive a predefined keyword extraction prompt. Further, the electronic device 130 may instruct the large language model 302 to extract keywords from the historical text and / or video 301 through the keyword extraction prompt. Generating keywords of the historical text and / or video 301 through the large language model can solve the problem that the vehicle information in the search results and the search results do not match the search intent of the user 140, and improve the relevance of the search results to the search terms and the user's satisfaction with the search results.

[0046] In other scenarios, the electronic device 130 may receive a vehicle entity extraction prompt. Further, the electronic device 130 may instruct the large language model 302 to extract the entity and / or description of the vehicle appearing in the historical text and / or video 301 through the vehicle entity extraction prompt. In this way, the matching degree between the search results and the search terms can be effectively improved.

[0047] Continue to refer Figure 2 In box 220, after determining the attribute information of the plurality of preset attributes, the electronic device 130 generates a set of reference semantic features of a set of candidate contents based on the attribute information.

[0048] As an example, Figure 3 As shown, the electronic device 130 can use the attribute information 303 of multiple preset attributes as an input sequence of a semantic extraction model 304 , and obtain a set of reference features 305 through the semantic extraction model 304 .

[0049] In some embodiments, the electronic device 130 may determine the target product information corresponding to the search term. Figure 3 As shown, the electronic device 130 can determine target product information 312 matching the search term from the product information library 310 .

[0050] In some embodiments, the electronic device 130 may determine a first product information set corresponding to the search term from the product information library based on the search term. Further, the electronic device 130 may construct an input sequence of the measurement model based on the search term and the first product information. Finally, the electronic device 130 may determine the target product information based on the output result of the measurement model. As an example, Figure 3 As shown, the electronic device 130 can recall multiple vehicle entities associated with the search term from the product information library 310 through a regular recall method. Furthermore, the electronic device 130 can further filter multiple vehicle entities associated with the search term through a metric model to obtain the vehicle model that best matches the search term to determine the target product information.

[0051] In this way, the target product information matching the search terms is finely screened, which can make the subsequent search results more accurate.

[0052] Further, the electronic device 130 may determine a second matching degree between the target product information and a set of reference product information associated with a set of candidate content. Figure 3As shown, the electronic device 130 can determine a set of reference product information 313 associated with a set of candidate content through the recall and metric matching module 331 in the product information library 310. Further, the electronic device 130 can call the matching model 314 to calculate the second matching degree based on the target product information and the set of reference product information.

[0053] Finally, the electronic device 130 may determine at least one target content from a set of candidate content based on the first matching degree and the second matching degree. As an example, the electronic device 130 may calculate the comprehensive matching degree based on the first matching degree and the second matching degree. Further, the electronic device 130 may send a preset number of contents with a comprehensive matching degree greater than a threshold to the terminal device 110, so that the terminal device 110 may present a preset number of contents. In some scenarios, the electronic device 130 may also sort the preset number of contents based on the comprehensive matching degree.

[0054] In some embodiments, the target product information and / or a set of reference product information indicates at least one attribute of a vehicle entity. As an example, the at least one attribute of the vehicle entity may indicate a brand, series, model or style of the vehicle entity.

[0055] In some embodiments, the electronic device 130 may determine a second product information set corresponding to a set of candidate contents from a product information library based on a set of candidate contents. The second product information set may include, for example, the brand, series, and model of the vehicle entity. Further, the electronic device 130 may construct an input sequence of a measurement model based on a set of candidate contents and the second product information set. Finally, the electronic device 130 determines a set of reference product information based on the output result of the measurement model.

[0056] As an example, Figure 3 As shown, the electronic device 130 can recall multiple product information associated with a set of candidate contents from the product information library 310 through a regular recall method to obtain a second product information set. Further, the electronic device 130 can input the set of candidate contents and the second product information set into the measurement model 311 to filter out reference product information corresponding to the car model described in the set of candidate contents.

[0057] In some embodiments, the electronic device 130 may construct an input sequence of a matching model based on a search term, a set of candidate content, target product information, and a set of reference product information. Further, the electronic device 130 may determine a second matching degree based on an output result of the matching model. As an example, Figure 3As shown, the electronic device 130 may input the search term 306 , the automobile entity or description in the attribute information 303 , the target product information 312 , and the reference product information 313 into the matching model 314 to obtain a structural relevance score 315 (ie, a second matching degree).

[0058] In some scenarios, such as Figure 4 As shown, Figure 4 The construction process of the training data of the measurement model of an embodiment of the present invention is shown. The electronic device 130 determines a set of product information 430 corresponding to the first training set 410 from the product information library 420. Further, the electronic device 130 can call the large language model 440 to annotate the set of product information 430 to determine the product information that matches the vehicle model description term in the first data set 410 in the set of product information 430. The electronic device 130 can use the annotated set of product information 450 as the training data of the measurement model to train the measurement model. The measurement model trained by the data constructed by the above method can accurately determine the desired vehicle model indicated by the search term, thereby improving the overall relevance of the search results to the search term.

[0059] In this way, the embodiments of the present disclosure can determine the semantic features of a set of candidate contents based on multiple attribute information of a set of candidate contents, and obtain search results based on matching the semantic features of a set of candidate contents with search terms, thereby making the obtained search results more accurate.

[0060] Example devices and equipment

[0061] The embodiments of the present disclosure also provide corresponding devices for implementing the above methods or processes. Figure 5 A schematic structural block diagram of an apparatus 500 for content search according to some embodiments of the present disclosure is shown. The apparatus 500 may be implemented as or included in the electronic device 130. Each module / component in the apparatus 500 may be implemented by hardware, software, firmware or any combination thereof.

[0062] like Figure 5 As shown, the device 500 includes a first matching degree calculation module 510, which is configured to determine a first matching degree between a first semantic feature of a search term and a set of reference semantic features of a set of candidate contents; a search result determination module 520, which is configured to determine at least one target content from a set of candidate contents as a search result for the search term based at least on the first matching degree, wherein the set of reference semantic features is determined based on the following process: determining attribute information of a set of candidate contents about multiple preset attributes; and generating a set of reference semantic features of a set of candidate contents based on the attribute information.

[0063] In some embodiments, the device 500 also includes an attribute information determination module, which is configured to provide a set of candidate content and guide items to the generative model, the guide items are used to instruct the generative model to extract values ​​of multiple preset attributes; and obtain attribute information of multiple preset attributes generated by the generative model.

[0064] In some embodiments, the plurality of preset attributes include a plurality of the following: title information of the candidate content; summary information of the candidate content; keyword information of the candidate content; product information in the candidate content; and a plurality of publisher information of the candidate content.

[0065] In some embodiments, the search result determination module 520 is further configured to: determine the target product information corresponding to the search term; determine a second degree of match based at least on the target product information and a set of reference product information associated with a set of candidate content; and determine at least one item of target content from a set of candidate content based on the first degree of match and the second degree of match.

[0066] In some embodiments, the search result determination module 520 is further configured to: determine a first product information set corresponding to the search term from a product information library based on the search term; construct an input sequence of a measurement model based on the search term and the first product information set; and determine target product information based on an output result of the measurement model.

[0067] In some embodiments, a set of reference product information associated with a set of candidate content is determined based on the following process: based on the set of candidate content, determining a second product information set corresponding to the set of candidate content from a product information library; based on the set of candidate content and the second product information set, constructing an input sequence of a measurement model; and based on the output result of the measurement model, determining a set of reference product information.

[0068] In some embodiments, the search result determination module 520 is further configured to: construct an input sequence of a matching model based on a search term, a set of candidate contents, target product information, and a set of reference product information; and determine a second matching degree based on an output result of the matching model.

[0069] In some embodiments, the target product information and / or a set of reference product information indicates at least one attribute of a vehicle entity.

[0070] The units included in the device 500 can be implemented in various ways, including software, hardware, firmware, or any combination thereof. In some embodiments, one or more units can be implemented using software and / or firmware, such as machine executable instructions stored on a storage medium. In addition to or as an alternative to machine executable instructions, some or all of the units in the device 500 can be implemented at least in part by one or more hardware logic components. As an example and not limitation, exemplary types of hardware logic components that can be used include field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0071] Figure 6 1 shows a block diagram of an electronic device 600 in which one or more embodiments of the present disclosure may be implemented. It should be understood that Figure 6 The electronic device 600 shown is merely exemplary and should not constitute any limitation on the functionality and scope of the embodiments described herein. Figure 6 The electronic device 600 shown can be used to implement Figure 1 electronic device 130.

[0072] like Figure 6 As shown, the electronic device 600 is in the form of a general electronic device. The components of the electronic device 600 may include, but are not limited to, one or more processors or processing units 610, a memory 620, a storage device 630, one or more communication units 640, one or more input devices 650, and one or more output devices 660. The processing unit 610 may be an actual or virtual processor and is capable of performing various processes according to a program stored in the memory 620. In a multi-processor system, multiple processing units execute computer executable instructions in parallel to improve the parallel processing capability of the electronic device 600.

[0073] The electronic device 600 typically includes a plurality of computer storage media. Such media may be any accessible media that is accessible to the electronic device 600, including but not limited to volatile and non-volatile media, removable and non-removable media. The memory 620 may be a volatile memory (e.g., registers, caches, random access memory (RAM)), a non-volatile memory (e.g., a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), flash memory), or some combination thereof. The storage device 630 may be a removable or non-removable medium, and may include a machine-readable medium, such as a flash drive, a disk, or any other medium, which may be capable of being used to store information and / or data and may be accessed within the electronic device 600.

[0074] The electronic device 600 may further include additional removable / non-removable, volatile / non-volatile storage media. Figure 6 As shown in , a disk drive for reading or writing from a removable, non-volatile disk (e.g., a "floppy disk") and an optical drive for reading or writing from a removable, non-volatile optical disk may be provided. In these cases, each drive may be connected to the bus (not shown) by one or more data media interfaces. The memory 620 may include a computer program product 625 having one or more program modules that are configured to perform various methods or actions of various embodiments of the present disclosure.

[0075] The communication unit 640 implements communication with other electronic devices through a communication medium. Additionally, the functions of the components of the electronic device 600 can be implemented with a single computing cluster or multiple computing machines that can communicate through a communication connection. Therefore, the electronic device 600 can operate in a networked environment using a logical connection with one or more other servers, a network personal computer (PC), or another network node.

[0076] The input device 650 may be one or more input devices, such as a mouse, a keyboard, a tracking ball, etc. The output device 660 may be one or more output devices, such as a display, a speaker, a printer, etc. The electronic device 600 may also communicate with one or more external devices (not shown) through the communication unit 640 as needed, such as a storage device, a display device, etc., communicate with one or more devices that allow a user to interact with the electronic device 600, or communicate with any device that allows the electronic device 600 to communicate with one or more other electronic devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface (not shown).

[0077] According to an exemplary implementation of the present disclosure, a computer-readable storage medium is provided, on which computer-executable instructions are stored, wherein the computer-executable instructions are executed by a processor to implement the method described above. According to an exemplary implementation of the present disclosure, a computer program product is also provided, which is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, and the computer-executable instructions are executed by a processor to implement the method described above.

[0078] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices, equipment, and computer program products implemented according to the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0079] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0080] Computer-readable program instructions can be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, so that the instructions executed on the computer, other programmable data processing apparatus, or other device implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0081] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple implementations of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of a module, program segment or instruction includes one or more executable instructions for realizing the logical function of the specification. In some implementations as replacements, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be realized by a special hardware-based system that performs the function or action of the specification, or can be realized by a combination of special hardware and computer instructions.

[0082] The above descriptions of various implementations of the present disclosure are exemplary, non-exhaustive, and not limited to the disclosed implementations. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described implementations. The selection of terms used herein is intended to best explain the principles of the implementations, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the various implementations disclosed herein.

Claims

1. A content search method, comprising: Determining a first degree of match between a first semantic feature of a search term and a set of reference semantic features of a set of candidate content; as well as At least based on the first matching degree, determining at least one target content from the set of candidate content as a search result for the search term, The set of reference semantic features is determined based on the following process: determining attribute information of the set of candidate contents with respect to a plurality of preset attributes; as well as Based on the attribute information, the set of reference semantic features of the set of candidate contents is generated.

2. The method according to claim 1, wherein determining the attribute information of the set of candidate contents with respect to a plurality of preset attributes comprises: Providing the set of candidate contents and a guide item to a generative model, wherein the guide item is used to instruct the generative model to extract values ​​of the plurality of preset attributes; as well as The attribute information of the plurality of preset attributes generated by the generative model is obtained.

3. The method according to claim 1, wherein the plurality of preset attributes comprises a plurality of the following: Title information of the candidate content; Summary information of the candidate content; Keyword information of candidate content; Product information in the candidate content; as well as Multiple publisher information of candidate content.

4. The method according to claim 1, wherein determining at least one target content from the set of candidate contents based at least on the first degree of match further comprises: Determine the target product information corresponding to the search term; determining a second matching degree based at least on the target product information and a set of reference product information associated with the set of candidate contents; as well as The at least one target content is determined from the group of candidate contents based on the first matching degree and the second matching degree.

5. The method according to claim 4, wherein determining the target product information corresponding to the search term comprises: Based on the search term, determining a first product information set corresponding to the search term from the product information library; constructing an input sequence of a metric model based on the search term and the first product information set; as well as Based on the output result of the measurement model, the target product information is determined.

6. The method according to claim 4, wherein the set of reference product information associated with the set of candidate contents is determined based on the following process: Based on the set of candidate contents, determining from the product information library a second product information set corresponding to the set of candidate contents; constructing an input sequence of a metric model based on the set of candidate contents and the second product information set; as well as Based on the output result of the measurement model, the set of reference product information is determined.

7. The method according to claim 4, wherein determining the second matching degree based on at least the target product information and a set of reference product information associated with the set of candidate contents comprises: constructing an input sequence of a matching model based on the search term, the set of candidate contents, the target product information, and the set of reference product information; The second matching degree is determined based on an output result of the matching model. 8 . The method according to claim 4 , wherein the target product information and / or the set of reference product information indicates at least one attribute of a vehicle entity.

9. A device for content search, comprising: A first matching degree calculation module is configured to determine a first matching degree between a first semantic feature of a search term and a set of reference semantic features of a set of candidate contents; a search result determination module, configured to determine at least one target content from the set of candidate content based at least on the first matching degree as a search result for the search term, The set of reference semantic features is determined based on the following process: determining attribute information of the set of candidate contents with respect to a plurality of preset attributes; and generating the set of reference semantic features of the set of candidate contents based on the attribute information.

10. An electronic device, comprising: at least one processing unit; as well as At least one memory, the at least one memory being coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, the instructions causing the electronic device to perform the method according to any one of claims 1 to 8 when executed by the at least one processing unit.

11. A computer-readable storage medium having a computer program stored thereon, wherein the computer program can be executed by a processor to implement the method according to any one of claims 1 to 8.

Images