Information search method and apparatus

Abstract

The embodiment of the present disclosure provides an information search method and device, the method comprises the following steps: in response to the interactive information input by the user, determining the search information corresponding to the interactive information, the search information comprising a target feature label and a plurality of search keywords; searching, from a pre-generated event library, a plurality of first events whose event identifiers comprise any search keyword and whose event feature labels comprise the target feature label, wherein the event library stores a plurality of events, and the event identifier and the event feature label of each event; predicting, according to the event identifier and the event feature label of the plurality of first events, the interactive information, the target feature label and the plurality of search keywords, the relevance information of the first events and the interactive information; and selecting, according to the respective relevance information of the plurality of first events, a plurality of second events from the plurality of first events as the search result of the interactive information. The method can improve the search efficiency of events.

Description

Technical Field

[0001] This disclosure relates to the field of Internet technology, and in particular to an information search method and device. Background Technology

[0002] With the development of internet technology, users can publish content about a particular event online. When an event receives widespread discussion and attention, it becomes a trending topic. Trending topics possess enormous traffic value due to their broad discussion and attention. When users want to learn about a trending topic, they need to search through numerous events to find the one they want to know about.

[0003] Existing methods for retrieving trending events rely on keywords to search for relevant events from a large pool of information. However, keyword searches often require users to input different keywords multiple times before finding the desired event.

[0004] It is evident that the retrieval efficiency of existing retrieval methods is relatively low. Summary of the Invention

[0005] This disclosure provides an information search method and device that can improve information retrieval efficiency.

[0006] In a first aspect, embodiments of this disclosure provide an information search method, including:

[0007] In response to user-inputted interactive information, the system determines the search information corresponding to the interactive information, which includes target feature tags and multiple search keywords.

[0008] Search a pre-generated event library for multiple first events whose event identifiers include any of the search keywords and whose event feature tags include the target feature tags, wherein the event library stores multiple events and the event identifier and event feature tags of each event;

[0009] Based on the event identifiers and event feature tags of the plurality of first events, the interaction information, the target feature tags, and the plurality of search keywords, the correlation information between the first events and the interaction information is predicted, and the correlation information is used to indicate the degree of correlation between the first events and the interaction information;

[0010] Based on the relevance information corresponding to each of the plurality of first events, a plurality of second events are selected from the plurality of first events as the search results for the interaction information.

[0011] Secondly, embodiments of this disclosure provide an information search device, comprising:

[0012] A determining unit is configured to determine search information corresponding to the interactive information input by the user, the search information including target feature tags and multiple search keywords;

[0013] The search unit is configured to search from a pre-generated event library for a plurality of first events whose event identifiers include any of the search keywords and whose event feature tags include the target feature tags, wherein the event library stores a plurality of events and an event identifier and an event feature tag for each event;

[0014] The prediction unit is configured to predict the relevance information between the first event and the interaction information based on the event identifiers and event feature tags of the plurality of first events, the interaction information, the target feature tags, and the plurality of search keywords. The relevance information is used to indicate the degree of correlation between the first event and the interaction information.

[0015] The selection unit is used to select multiple second events from the multiple first events as search results for the interactive information based on the relevance information corresponding to each of the multiple first events.

[0016] Thirdly, embodiments of this disclosure provide an electronic device, including: a processor and a memory;

[0017] The memory stores computer-executed instructions;

[0018] The processor executes computer execution instructions stored in the memory, causing the at least one processor to perform the information search method as described in the first aspect and various possible designs of the first aspect.

[0019] Fourthly, embodiments of this disclosure provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the information search method described in the first aspect and various possible designs of the first aspect.

[0020] Fifthly, embodiments of this disclosure provide a computer program product, including a computer program that, when executed by a processor, implements the information search method described in the first aspect and various possible designs of the first aspect.

[0021] This embodiment provides an information search method and device. The method includes: responding to user-inputted interactive information, determining search information corresponding to the interactive information, the search information including target feature tags and multiple search keywords; searching from a pre-generated event library for multiple first events whose event identifiers include any search keyword and whose event feature tags include the target feature tag, wherein the event library stores multiple events and the event identifier and event feature tag of each event; predicting the relevance information between the first events and the interactive information based on the event identifiers and event feature tags of the multiple first events, the interactive information, the target feature tag, and the multiple search keywords, the relevance information being used to indicate the degree of relevance between the first events and the interactive information; and selecting multiple second events from the multiple first events as search results for the interactive information based on the relevance information corresponding to each of the multiple first events. In this technical solution, since multiple first events are initially screened through object tags and keywords, and then multiple second events are finely screened from the multiple first events based on the degree of relevance between the first events and the interactive information, multiple dimensions of object tags and keywords, as well as two screening processes of initial screening and fine screening, can quickly search for hot events that users intend to learn about, thus improving the efficiency of event search. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a schematic diagram illustrating an application scenario of an information search method provided in an embodiment of this disclosure;

[0024] Figure 2 Flowchart of the information search method provided in the embodiments of this disclosure Figure 1 ;

[0025] Figure 3 Illustration of the information search method provided in the embodiments of this disclosure Figure 1 ;

[0026] Figure 4 Illustration of the information search method provided in the embodiments of this disclosure Figure 2 ;

[0027] Figure 5 Illustration of the information search method provided in the embodiments of this disclosure Figure 3 ;

[0028] Figure 6 Illustration of the information search method provided in the embodiments of this disclosure Figure 4 ;

[0029] Figure 7 Illustration of the information search method provided in the embodiments of this disclosure Figure 5 ;

[0030] Figure 8 A schematic diagram of the structure of the information search device provided in the embodiments of this disclosure;

[0031] Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0032] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0033] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in one or more embodiments of this specification are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of related data must comply with relevant laws, regulations and standards, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0034] With the development of internet technology, users can publish content about a particular event online. When an event receives widespread discussion and attention, it becomes a trending topic. Trending topics possess enormous traffic value due to their broad discussion and attention. When users want to learn about a trending topic, they need to search through numerous events to find the one they want to know about.

[0035] Existing methods for retrieving trending events rely on keywords to search for relevant events from a large pool of information. However, keyword searches often require users to input different keywords multiple times to find the desired events. Therefore, existing retrieval methods are inefficient.

[0036] To address the technical problems in existing technologies, the inventors propose the following technical concept: By using keywords and event feature tags, events are initially screened from the mined event database. The relevance of events and interactive information is then scored, and highly relevant events are recommended to users. This allows for quick searching of trending events that users intend to learn about, thereby improving the efficiency of event search.

[0037] Accordingly, the specific steps may include: First, in response to user-inputted interactive information, determining the search information corresponding to the interactive information, which includes target feature tags and multiple search keywords. Second, searching from a pre-generated event database for multiple first events whose event identifiers include any search keyword and whose event feature tags include the target feature tag; predicting the relevance information between the first events and the interactive information based on the event identifiers and event feature tags of the multiple first events, the interactive information, the target feature tags, and the multiple search keywords. Finally, selecting multiple second events from the multiple first events as the search results for the interactive information based on the relevance information corresponding to each of the multiple first events.

[0038] In this technical solution, multiple primary events are initially screened using object tags and keywords. Then, multiple secondary events are further screened from these primary events based on their relevance to interactive information. By using multiple dimensions such as object tags and keywords, as well as the initial and final screening processes, the hot topics that users want to know about can be quickly searched, thus improving the efficiency of event search.

[0039] The application scenarios of the embodiments of this disclosure are explained below:

[0040] The information search method provided in this disclosure can be applied to various information interaction application scenarios. Figure 1 This is a schematic diagram illustrating an application scenario of an information search method provided in an embodiment of this disclosure. For example... Figure 1 As shown, terminal 101 and server 102 are connected via a network and can transmit information to each other. For example, when searching for an event, a user can input interactive information through terminal 101. Terminal 101 sends the user-input interactive information to server 102. Server 102 receives the user-input interactive information and, using the information search method provided in this embodiment, searches for the event corresponding to the interactive information. Server 102 then returns the event corresponding to the interactive information to display terminal 101 for display.

[0041] The following describes the specific implementation process of the information search method and device involved in the embodiments of this disclosure. Some examples are merely illustrative and not intended to limit the scope. The executing entity of the information search method involved in the embodiments of this disclosure is an electronic device, which may be a terminal, server, etc.

[0042] Figure 2 Flowchart of the information search method provided in the embodiments of this disclosure Figure 1 ,like Figure 2 As shown, this information search method may include:

[0043] S201. In response to the interactive information input by the user, determine the search information corresponding to the interactive information. The search information includes target feature tags and multiple search keywords.

[0044] In some embodiments, such as Figure 3 As shown, the target dimension corresponding to the interactive information can be determined first, and keywords and target feature tags corresponding to the target dimension can be generated. Accordingly, this step may include: responding to the interactive information input by the user, determining the target dimension corresponding to the interactive information from multiple preset dimensions; generating first search keywords and target feature tags through the target search information generation model corresponding to the target dimension, and determining the first search keywords and target feature tags as the search information corresponding to the interactive information.

[0045] The preset dimension can be any dimension related to interactive information. Optionally, multiple preset dimensions include at least two of the following: date dimension, identifier dimension, category dimension, and content dimension. For example, Figure 3 As shown, multiple preset dimensions include date dimension, identifier dimension, category dimension, and content dimension.

[0046] It should be noted that each preset dimension can correspond to one or more feature tags. For example, the date dimension can include a festival dimension. The multiple festival feature tags corresponding to this festival dimension include all official festivals and folk festivals. The identifier dimension can include a brand dimension. The brand feature tags corresponding to this brand dimension include: product, brand, spokesperson, store location, etc. The category dimension can include an industry dimension. The industry feature tags corresponding to the industry dimension include: technology, tourism, aviation, automotive, catering, hotel, education, etc. The content dimension corresponds to content feature tags including: video, audio, text, etc.

[0047] In this embodiment of the disclosure, the association between target feature tags and multiple first search keywords can be pre-stored. Optionally, the target dimension is a festival dimension, and the association between each festival feature tag and multiple first search keywords can be pre-stored. When determining the target feature tag, the first search keyword corresponding to the target feature tag is determined through the above association. For example, if the target feature tag is Spring Festival, the multiple first search keywords related to Spring Festival are: Spring Festival, New Year's goods, carnival, big promotion, Spring Festival season, and tourism. If the target feature tag is Valentine's Day, the multiple first search keywords related to Valentine's Day are: Valentine's Day, beauty, skincare, cosmetics, roses, and chocolate.

[0048] For example, the user inputs interactive information as: "Hot topics related to the Spring Festival." From multiple preset dimensions, the target dimension corresponding to the interactive information is determined as: the "festival dimension." This festival dimension includes multiple festival feature tags, covering all official and folk festivals. Furthermore, a festival dimension strategy generation model can be used to generate the target feature tag corresponding to the interactive information as: "Spring Festival"; and generate multiple primary search keywords related to the Spring Festival as: Spring Festival, New Year's goods, carnival, big promotion, Spring Festival season, and tourism.

[0049] For example, the user inputs interactive information as: Valentine's Day related hot topics. From multiple preset dimensions, the target dimension corresponding to the interactive information is determined as: the holiday dimension. A model can be generated using the holiday dimension strategy to generate the target feature label corresponding to the interactive information as: Valentine's Day; and to generate multiple first search keywords related to Valentine's Day as: Valentine's Day, beauty, skincare, cosmetics, roses, and chocolate.

[0050] In other embodiments, this application can also combine trending texts to generate second search keywords. Accordingly, in response to user-inputted interactive information, determining search information corresponding to the interactive information includes: in response to user-inputted interactive information, determining a target dimension corresponding to the interactive information from multiple preset dimensions, the multiple preset dimensions including at least two of date dimension, identifier dimension, category dimension, and content dimension; generating first search keywords and target feature tags through a target search information generation model corresponding to the target dimension; selecting at least one target text corresponding to the interactive information from multiple texts satisfying preset conditions, and determining multiple second search keywords corresponding to the at least one target text; wherein, the preset condition is that the text popularity value is greater than a preset popularity threshold, the text popularity value is determined based on one or more of the text read count, text like count, text comment count, and text share count; and determining the first search keyword, target feature tags, and second search keywords as the search information corresponding to the interactive information.

[0051] For example, such as Figure 4 As shown, in response to user-inputted interactive information, a search engine searches for keywords in the mutual information to obtain at least one target text (such as...). Figure 4 (Popular text in the search results). Based on user-input interaction information, a target search information generation model is used to generate first search keywords and target feature tags, and based on at least one target text, second search keywords are generated.

[0052] S202. Search for multiple first events from a pre-generated event library whose event identifiers include any search keyword and whose event feature tags include the target feature tag, wherein the event library stores multiple events and the event identifier and event feature tag of each event.

[0053] In this embodiment of the disclosure, an event identifier is used to distinguish different events. Optionally, the event identifier can be an event name. For example, the event identifiers are: "XX popular tourist spot was packed with people during the May Day holiday" and "XX mobile phone sales were number one during the back-to-school season".

[0054] Event feature tags are used to represent a specific attribute of an event. For example, an event feature tag can represent a holiday tag, such as Spring Festival, Dragon Boat Festival, or Mid-Autumn Festival. Another example is an event feature tag that can represent a content category tag, such as video, audio, or text.

[0055] In some embodiments, event feature tags include one or more of the following: holiday tags, industry category tags, content category tags, domain category tags, event object identifiers, event object types, and event popularity values, whereby the event popularity value is used to indicate the degree of attention paid to the first event. Optionally, as... Figure 5 As shown, event feature tags include holiday tags, industry category tags, content category tags, domain category tags, and event object identifiers (corresponding to...). Figure 5 Brand words in the event object (corresponding to the brand name in the event object) Figure 5 (Product keywords) and event popularity value.

[0056] For example, the user-input interactive information is: mobile phone-related hot topics. The search information corresponding to the interactive information (mobile phone-related hot topics) includes the target feature tag: back-to-school season. Multiple search keywords are: mobile phone, sales volume. The event identifier is: XX mobile phone sales number one during the back-to-school season. The event feature tags include: back-to-school season, XX mobile phone, electronic products. If the event identifier includes the search keyword "mobile phone" and the event feature tags include the target feature tag "back-to-school season," then this event is determined to be the first event.

[0057] In some embodiments, such as Figure 6 As shown, the steps for pre-generating the event library may include the following:

[0058] (1) Feature extraction: Obtain the text identifiers and text information of multiple texts, where the text identifiers include the text title and the event identifier to which the text belongs.

[0059] The text information for each text can be any attribute information related to that text. For example, such as... Figure 6As shown, the text information can include: keywords in the text (words that appear more than a preset number of times), holidays, brands, industries, and the number of times the text is reposted, commented on, or liked.

[0060] (2) Event clustering: Multiple texts with the same event identifier are clustered into one event, resulting in multiple events.

[0061] (3) Event feature calculation: For each event, the event feature label is determined based on the text information of multiple texts in the event.

[0062] In this step, event feature labels can be calculated for the corresponding event using statistical methods based on the textual information of multiple texts within the event. For example, festival information can be identified in each of the multiple texts; if more than XX% of the texts contain information about the Spring Festival (Chinese New Year), then the event feature label for the event is determined to be: Spring Festival.

[0063] (4) Associate and store each event, the event identifier of each event, and the feature label of each event in the event library.

[0064] S203. Based on the event identifiers and event feature tags of multiple first events, interaction information, target feature tags, and multiple search keywords, predict the relevance information between the first events and the interaction information. The relevance information is used to indicate the degree of relevance between the first events and the interaction information.

[0065] In this embodiment of the disclosure, a preset relevance model can be used to predict the relevance information between the first event and the interaction information. Accordingly, this step may include: inputting the event identifier and event feature label of each first event, the interaction information, the target feature label, and multiple search keywords into the preset relevance model, and predicting the relevance information between each first event and the interaction information through the preset relevance model.

[0066] The preset relevance model can be any relevance analysis model that can predict relevance information. Optionally, the preset relevance model is a large language model.

[0067] S204. Based on the correlation information corresponding to each of the multiple first events, select multiple second events from the multiple first events as the search results for interactive information.

[0068] In some embodiments, such as Figure 3 As shown, based on relevance information, multiple second events are selected from multiple first events. Accordingly, this step may include: selecting a preset number of second events as search results for interactive information from the multiple first events, according to the relevance information corresponding to each of the multiple first events, in descending order of relevance information.

[0069] In other embodiments, a preset number of second events can be selected from multiple first events by using correlation information and combining multiple preset filtering conditions.

[0070] Optionally, such as Figure 5 As shown, the preset filtering criteria can be whether the domain to which the first event belongs is the target domain. Accordingly, this step can include: selecting a preset number of second events that conform to the target domain from the multiple first events, based on the relevance information corresponding to each of the multiple first events, in descending order of relevance information. Optionally, the target domain can be a business domain, an entertainment domain, an education domain, etc.

[0071] Optionally, such as Figure 5 As shown, the preset filtering condition can also be whether the event popularity value of the first event is greater than a preset popularity value. Accordingly, this step may include: based on the relevance information corresponding to each of the multiple first events, selecting a preset number of second events whose event popularity value is greater than the preset popularity value from the multiple first events in descending order of relevance information.

[0072] This disclosure provides an information search method: In response to user-inputted interactive information, search information corresponding to the interactive information is determined, including target feature tags and multiple search keywords; multiple first events are searched from a pre-generated event database, where the event identifier includes any search keyword and the event feature tag includes the target feature tag, wherein the event database stores multiple events and the event identifier and event feature tag of each event; based on the event identifier and event feature tag of the multiple first events, the interactive information, the target feature tag, and the multiple search keywords, relevance information between the first events and the interactive information is predicted, whereby the relevance information indicates the degree of relevance between the first events and the interactive information; based on the relevance information corresponding to each of the multiple first events, multiple second events are selected from the multiple first events as search results for the interactive information. In this technical solution, since multiple first events are initially screened using object tags and keywords, and then multiple second events are refined from the multiple first events based on the degree of relevance between the first events and the interactive information, through multiple dimensions of object tags and keywords, and two screening processes (initial screening and refined screening), the hot topics that the user intends to learn about can be quickly searched, thus improving the efficiency of event search.

[0073] In some embodiments, the method further includes: obtaining user business requirement information, wherein the business requirement information includes one or more of creative title generation, poster generation, multimodal understanding, and selling point analysis; and generating object content related to the business requirement information based on the business requirement information, multiple second events, and a preset content processing model. For example, such as... Figure 5As shown, the business requirements information includes creative title generation, poster generation, multimodal understanding, and selling point analysis.

[0074] Optionally, based on business requirement information, multiple second events, and a preset content processing model, object content related to the business requirement information is generated, including: determining a target processing operator from multiple processing operators in the preset content processing model based on the business requirement information; the target processing operator includes one or more of the following: creative title generation operator, poster generation operator, multimodal understanding operator, creative scoring operator, safety scoring operator, and selling point analysis operator; and processing multiple second events through the target processing operator to generate object content related to the business requirement information, wherein the target processing operator is combined in a directed acyclic graph arrangement.

[0075] In this disclosure, there is no limit to the number of processing operators in the preset content processing model; they can be added or deleted according to user needs. Target processing operators can be arbitrarily combined through DAG (Directed Acyclic Graph) process orchestration to achieve customized processing requirements for each user.

[0076] For example, such as Figure 7 As shown, based on the business requirement information corresponding to business 1, target processing operators are determined from multiple processing operators in the preset content processing model, including processing operator 11, processing operator 12, and processing operator 1n, to meet the processing requirements of business 1. Based on the business requirement information corresponding to business 2, target processing operators are determined from multiple processing operators in the preset content processing model, including processing operator 21, processing operator 22, and processing operator 2n, to meet the processing requirements of business 2. Based on the business requirement information corresponding to business 3, target processing operators are determined from multiple processing operators in the preset content processing model, including processing operator 31, processing operator 32, and processing operator 3n, to meet the processing requirements of business 3.

[0077] It should be noted that, as Figure 5 As shown, by connecting all the above processes in this implementation, end-to-end hotspot retrieval and processing capabilities can be achieved. In the hotspot discovery phase: event clustering can be performed on the text of hotspots to pre-generate an event library. In the hotspot filtering phase: based on user-input interaction information, multiple first events are initially filtered from the event library. Then, based on relevance information, multiple second events are filtered. Finally, in the hotspot application phase, based on business requirements, the filtered second events are processed to generate the content needed by the user.

[0078] Figure 8 This is a schematic diagram of the structure of the information search device provided in the embodiments of this disclosure, such as... Figure 8As shown, the information search device includes:

[0079] The determining unit 801 is used to determine the search information corresponding to the interactive information input by the user in response to the interactive information, wherein the search information includes target feature tags and multiple search keywords;

[0080] Search unit 802 is used to search from a pre-generated event library for a plurality of first events whose event identifiers include any of the search keywords and whose event feature tags include the target feature tags, wherein the event library stores a plurality of events and an event identifier and an event feature tag for each event;

[0081] Prediction unit 803 is configured to predict the relevance information between the first event and the interaction information based on the event identifiers and event feature tags of the plurality of first events, the interaction information, the target feature tags, and the plurality of search keywords, wherein the relevance information is used to indicate the degree of correlation between the first event and the interaction information;

[0082] The selection unit 804 is used to select multiple second events from the multiple first events as search results for the interaction information based on the relevance information corresponding to each of the multiple first events.

[0083] According to one or more embodiments of this disclosure, the determining unit 801, in response to user-inputted interactive information, determines search information corresponding to the interactive information, including: in response to user-inputted interactive information, determining a target dimension corresponding to the interactive information from a plurality of preset dimensions, the plurality of preset dimensions including at least two of date dimension, identifier dimension, category dimension, and content dimension; generating a first search keyword and a target feature tag through a target search information generation model corresponding to the target dimension, and determining the first search keyword and the target feature tag as the search information corresponding to the interactive information.

[0084] According to one or more embodiments of this disclosure, the determining unit 801 is further configured to select at least one target text corresponding to the interactive information from a plurality of texts that meet preset conditions, and determine a plurality of second search keywords corresponding to the at least one target text; wherein, the preset condition is that the text popularity value is greater than a preset popularity threshold, and the text popularity value is determined based on one or more of the following: text read count, text like count, text comment count, and text share count; and the first search keyword, the target feature tag, and the second search keyword are determined as search information corresponding to the interactive information.

[0085] According to one or more embodiments of this disclosure, the selection unit 804 selects a plurality of second events from the plurality of first events as search results for the interactive information based on the relevance information corresponding to each of the plurality of first events, including: selecting a preset number of second events from the plurality of first events as search results for the interactive information in descending order of relevance information based on the relevance information corresponding to each of the plurality of first events.

[0086] According to one or more embodiments of this disclosure, the device further includes: an event library generation unit; the event library generation unit is configured to acquire text identifiers and text information of multiple texts, wherein the text identifiers include text titles and event identifiers to which the texts belong; cluster multiple texts with the same event identifiers into one event to obtain multiple events; for each event, determine an event feature tag of the event based on the text information of the multiple texts in the event; and associate and store each event, the event identifier of each event, and each event feature tag in the event library.

[0087] According to one or more embodiments of this disclosure, the device further includes: an event processing unit; the event processing unit is configured to acquire user business requirement information, wherein the business requirement information includes one or more of creative title generation, poster generation, multimodal understanding, and selling point analysis; and generate object content related to the business requirement information based on the business requirement information, the plurality of second events, and a preset content processing model.

[0088] According to one or more embodiments of this disclosure, the event processing unit generates object content related to the business requirement information based on the business requirement information, the plurality of second events, and a preset content processing model, including: determining a target processing operator from a plurality of processing operators in the preset content processing model based on the business requirement information, the target processing operator including one or more of a creative title generation operator, a poster generation operator, a multimodal understanding operator, a creative scoring operator, a security scoring operator, and a selling point analysis operator; and processing the plurality of second events through the target processing operator to generate object content related to the business requirement information, wherein the target processing operator is combined in a directed acyclic graph arrangement.

[0089] According to one or more embodiments of this disclosure, the event feature tags include one or more of the following: holiday tags, industry category tags, content category tags, domain category tags, event object identifiers, event object types, and event popularity values, wherein the event popularity value is used to indicate the degree of attention paid to the first event.

[0090] refer to Figure 9The diagram illustrates a structural schematic of an electronic device 900 suitable for implementing embodiments of the present disclosure. The electronic device 900 can be a terminal device or a server. The terminal device can include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, personal digital assistants (PDAs), tablet computers, portable media players (PMPs), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 9 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0091] like Figure 9 As shown, the electronic device 900 may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 901, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 902 or a program loaded from a storage device 908 into a random access memory (RAM) 903. The RAM 903 also stores various programs and data required for the operation of the electronic device 900. The processing unit 901, ROM 902, and RAM 903 are interconnected via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0092] Typically, the following devices can be connected to I / O interface 905: input devices 906 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 907 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 908 including, for example, magnetic tapes, hard disks, etc.; and communication devices 909. Communication device 909 allows electronic device 900 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 9 An electronic device 900 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0093] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 909, or installed from a storage device 908, or installed from a ROM 902. When the computer program is executed by a processing device 901, it performs the functions defined in the methods of embodiments of this disclosure.

[0094] It should be noted that the computer-readable medium described in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0095] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0096] The aforementioned computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the methods shown in the above embodiments.

[0097] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0098] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0099] The units described in the embodiments of this disclosure can be implemented in software or in hardware. The name of a unit does not necessarily limit the unit itself; for example, the first acquisition unit can also be described as "a unit that acquires at least two Internet Protocol addresses".

[0100] The functions described above in this document can be performed, at least in part, by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: Field Programmable Gate Arrays (FPGAs), Application-Specific Integrated Circuits (ASICs), Application Standard Products (ASSPs), System-on-Chip (SoCs), Complex Programmable Logic Devices (CPLDs), and so on.

[0101] In a first aspect, according to one or more embodiments of this disclosure, an information search method is provided, comprising:

[0102] In response to user-inputted interactive information, the system determines the search information corresponding to the interactive information, which includes target feature tags and multiple search keywords.

[0103] Search a pre-generated event library for multiple first events whose event identifiers include any of the search keywords and whose event feature tags include the target feature tags, wherein the event library stores multiple events and the event identifier and event feature tags of each event;

[0104] Based on the event identifiers and event feature tags of the plurality of first events, the interaction information, the target feature tags, and the plurality of search keywords, the correlation information between the first events and the interaction information is predicted, and the correlation information is used to indicate the degree of correlation between the first events and the interaction information;

[0105] Based on the relevance information corresponding to each of the plurality of first events, a plurality of second events are selected from the plurality of first events as the search results for the interaction information.

[0106] According to one or more embodiments of this disclosure, determining the search information corresponding to the interactive information in response to user input includes: in response to user input, determining a target dimension corresponding to the interactive information from a plurality of preset dimensions, wherein the plurality of preset dimensions include at least two of a date dimension, an identifier dimension, a category dimension, and a content dimension; generating a first search keyword and a target feature tag through a target search information generation model corresponding to the target dimension; and determining the first search keyword and the target feature tag as the search information corresponding to the interactive information.

[0107] According to one or more embodiments of this disclosure, the method further includes: selecting at least one target text corresponding to the interactive information from a plurality of texts that meet preset conditions, and determining a plurality of second search keywords corresponding to the at least one target text; wherein the preset conditions are that the text popularity value is greater than a preset popularity threshold, and the text popularity value is determined based on one or more of the following: text read count, text like count, text comment count, and text share count; and determining the first search keyword, the target feature tag, and the second search keyword as the search information corresponding to the interactive information.

[0108] According to one or more embodiments of this disclosure, selecting a plurality of second events from the plurality of first events as search results for the interactive information based on the relevance information corresponding to each of the plurality of first events includes: selecting a preset number of second events from the plurality of first events as search results for the interactive information in descending order of relevance information based on the relevance information corresponding to each of the plurality of first events.

[0109] According to one or more embodiments of this disclosure, the method further includes: obtaining text identifiers and text information of multiple texts, wherein the text identifiers include text titles and event identifiers to which the texts belong; clustering multiple texts with the same event identifier into one event to obtain multiple events; for each event, determining an event feature tag of the event based on the text information of the multiple texts in the event; and associating and storing each event, the event identifier of each event, and each event feature tag in an event library.

[0110] According to one or more embodiments of this disclosure, the method further includes: obtaining user business requirement information, wherein the business requirement information includes one or more of creative title generation, poster generation, multimodal understanding, and selling point analysis; and generating object content related to the business requirement information based on the business requirement information, the plurality of second events, and a preset content processing model.

[0111] According to one or more embodiments of this disclosure, generating object content related to the business requirement information based on the business requirement information, the plurality of second events, and a preset content processing model includes: determining a target processing operator from a plurality of processing operators in the preset content processing model based on the business requirement information; the target processing operator includes one or more of a creative title generation operator, a poster generation operator, a multimodal understanding operator, a creative scoring operator, a security scoring operator, and a selling point analysis operator; and processing the plurality of second events through the target processing operator to generate object content related to the business requirement information, wherein the target processing operator is combined in a directed acyclic graph arrangement.

[0112] According to one or more embodiments of this disclosure, the event feature tags include one or more of the following: holiday tags, industry category tags, content category tags, domain category tags, event object identifiers, event object types, and event popularity values, wherein the event popularity value is used to indicate the degree of attention paid to the first event.

[0113] Secondly, according to one or more embodiments of this disclosure, an information search device is provided, comprising:

[0114] A determining unit is configured to determine search information corresponding to the interactive information input by the user, the search information including target feature tags and multiple search keywords;

[0115] The search unit is configured to search from a pre-generated event library for a plurality of first events whose event identifiers include any of the search keywords and whose event feature tags include the target feature tags, wherein the event library stores a plurality of events and an event identifier and an event feature tag for each event;

[0116] The prediction unit is configured to predict the relevance information between the first event and the interaction information based on the event identifiers and event feature tags of the plurality of first events, the interaction information, the target feature tags, and the plurality of search keywords. The relevance information is used to indicate the degree of correlation between the first event and the interaction information.

[0117] The selection unit is used to select multiple second events from the multiple first events as search results for the interactive information based on the relevance information corresponding to each of the multiple first events.

[0118] According to one or more embodiments of this disclosure, the determining unit, in response to user-inputted interactive information, determines search information corresponding to the interactive information, including: in response to user-inputted interactive information, determining a target dimension corresponding to the interactive information from a plurality of preset dimensions, the plurality of preset dimensions including at least two of date dimension, identifier dimension, category dimension, and content dimension; generating a first search keyword and a target feature tag through a target search information generation model corresponding to the target dimension, and determining the first search keyword and the target feature tag as the search information corresponding to the interactive information.

[0119] According to one or more embodiments of this disclosure, the determining unit is further configured to select at least one target text corresponding to the interactive information from a plurality of texts that meet preset conditions, and determine a plurality of second search keywords corresponding to the at least one target text; wherein, the preset condition is that the text popularity value is greater than a preset popularity threshold, and the text popularity value is determined based on one or more of the following: text read count, text like count, text comment count, and text share count; and the first search keyword, the target feature tag, and the second search keyword are determined as search information corresponding to the interactive information.

[0120] According to one or more embodiments of this disclosure, the selection unit selects a plurality of second events from the plurality of first events as search results for the interactive information based on the relevance information corresponding to each of the plurality of first events, including: selecting a preset number of second events from the plurality of first events as search results for the interactive information in descending order of relevance information based on the relevance information corresponding to each of the plurality of first events.

[0121] According to one or more embodiments of this disclosure, the device further includes: an event library generation unit; the event library generation unit is configured to acquire text identifiers and text information of multiple texts, wherein the text identifiers include text titles and event identifiers to which the texts belong; cluster multiple texts with the same event identifiers into one event to obtain multiple events; for each event, determine an event feature tag of the event based on the text information of the multiple texts in the event; and associate and store each event, the event identifier of each event, and each event feature tag in the event library.

[0122] According to one or more embodiments of this disclosure, the device further includes: an event processing unit; the event processing unit is configured to acquire user business requirement information, wherein the business requirement information includes one or more of creative title generation, poster generation, multimodal understanding, and selling point analysis; and generate object content related to the business requirement information based on the business requirement information, the plurality of second events, and a preset content processing model.

[0123] According to one or more embodiments of this disclosure, the event processing unit generates object content related to the business requirement information based on the business requirement information, the plurality of second events, and a preset content processing model, including: determining a target processing operator from a plurality of processing operators in the preset content processing model based on the business requirement information, the target processing operator including one or more of a creative title generation operator, a poster generation operator, a multimodal understanding operator, a creative scoring operator, a security scoring operator, and a selling point analysis operator; and processing the plurality of second events through the target processing operator to generate object content related to the business requirement information, wherein the target processing operator is combined in a directed acyclic graph arrangement.

[0124] According to one or more embodiments of this disclosure, the event feature tags include one or more of the following: holiday tags, industry category tags, content category tags, domain category tags, event object identifiers, event object types, and event popularity values, wherein the event popularity value is used to indicate the degree of attention paid to the first event.

[0125] Thirdly, according to one or more embodiments of the present disclosure, an electronic device is provided, comprising: at least one processor and a memory;

[0126] The memory stores computer-executed instructions;

[0127] The at least one processor executes computer execution instructions stored in the memory, causing the at least one processor to perform the information search method as described in the first aspect and various possible designs of the first aspect.

[0128] Fourthly, according to one or more embodiments of the present disclosure, a computer-readable storage medium is provided, wherein computer-executable instructions are stored therein, and when a processor executes the computer-executable instructions, the information search method described in the first aspect and various possible designs of the first aspect is implemented.

[0129] Fifthly, according to one or more embodiments of the present disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the information search method as described in the first aspect and various possible designs of the first aspect.

[0130] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

[0131] Furthermore, while the operations are described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or in a sequential order. In certain environments, multitasking and parallel processing may be advantageous. Similarly, while several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this disclosure. Certain features described in the context of individual embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented individually or in any suitable sub-combination in multiple embodiments.

[0132] Although the subject matter has been described using language specific to structural features and / or methodological logic, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Rather, the specific features and actions described above are merely illustrative examples of implementing the claims.

Claims

1. An information search method, characterized in that, The method includes: In response to user-inputted interactive information, the system determines the search information corresponding to the interactive information, which includes target feature tags and multiple search keywords. Search a pre-generated event library for multiple first events whose event identifiers include any of the search keywords and whose event feature tags include the target feature tags, wherein the event library stores multiple events and the event identifier and event feature tags of each event; Based on the event identifiers and event feature tags of the plurality of first events, the interaction information, the target feature tags, and the plurality of search keywords, the correlation information between the first events and the interaction information is predicted, and the correlation information is used to indicate the degree of correlation between the first events and the interaction information; Based on the relevance information corresponding to each of the plurality of first events, a plurality of second events are selected from the plurality of first events as the search results for the interaction information.

2. The method according to claim 1, characterized in that, The step of responding to user-inputted interactive information and determining the search information corresponding to the interactive information includes: In response to user-inputted interactive information, a target dimension corresponding to the interactive information is determined from multiple preset dimensions, including at least two of the following: date dimension, identifier dimension, category dimension, and content dimension. The target search information generation model corresponding to the target dimension generates a first search keyword and a target feature label, and the first search keyword and the target feature label are determined as the search information corresponding to the interaction information.

3. The method according to claim 2, characterized in that, Also includes: From multiple texts that meet preset conditions, at least one target text corresponding to the interactive information is selected, and multiple second search keywords corresponding to the at least one target text are determined; wherein, the preset condition is that the text popularity value is greater than a preset popularity threshold, and the text popularity value is determined based on one or more of the following: text read count, text like count, text comment count, and text share count; The first search keyword, the target feature tag, and the second search keyword are determined as the search information corresponding to the interactive information.

4. The method according to claim 1, characterized in that, The step of selecting multiple second events from the multiple first events as search results for the interaction information based on the relevance information corresponding to each of the multiple first events includes: Based on the relevance information corresponding to each of the plurality of first events, a preset number of second events are selected from the plurality of first events in descending order of relevance information as the search results for the interactive information.

5. The method according to claim 1, characterized in that, The method further includes: Obtain text identifiers and text information for multiple texts, wherein the text identifiers include text titles and event identifiers to which the texts belong; Clustering multiple texts with the same event identifier into one event results in multiple events; For each event, an event feature tag is determined based on the text information of multiple texts in the event; Each event, its event identifier, and its feature tags are associated and stored in the event library.

6. The method according to claim 1, characterized in that, The method further includes: Obtain user business requirement information, wherein the business requirement information includes one or more of the following: creative title generation, poster generation, multimodal understanding, and selling point analysis; Based on the business requirement information, the multiple second events, and the preset content processing model, generate object content related to the business requirement information.

7. The method according to claim 6, characterized in that, The step of generating object content related to the business requirement information based on the business requirement information, the multiple second events, and a preset content processing model includes: Based on the business requirement information, a target processing operator is determined from multiple processing operators in the preset content processing model. The target processing operator includes one or more of the following: creative title generation operator, poster generation operator, multimodal understanding operator, creative scoring operator, security scoring operator, and selling point analysis operator. The target processing operator is used to process the multiple second events to generate object content related to the business requirement information, wherein the target processing operator is combined in a directed acyclic graph arrangement.

8. The method according to claim 1, characterized in that, The event feature tags include one or more of the following: holiday tags, industry category tags, content category tags, domain category tags, event object identifiers, event object types, and event popularity values. The event popularity value is used to indicate the degree of attention paid to the first event.

9. An information search device, characterized in that, The device includes: A determining unit is configured to determine search information corresponding to the interactive information input by the user, the search information including target feature tags and multiple search keywords; The search unit is configured to search from a pre-generated event library for a plurality of first events whose event identifiers include any of the search keywords and whose event feature tags include the target feature tags, wherein the event library stores a plurality of events and an event identifier and an event feature tag for each event; The prediction unit is configured to predict the relevance information between the first event and the interaction information based on the event identifiers and event feature tags of the plurality of first events, the interaction information, the target feature tags, and the plurality of search keywords. The relevance information is used to indicate the degree of correlation between the first event and the interaction information. The selection unit is used to select multiple second events from the multiple first events as search results for the interactive information based on the relevance information corresponding to each of the multiple first events.

10. An electronic device, characterized in that, include: Processor and memory; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the information search method as described in any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, implement the information search method as described in any one of claims 1 to 8.

12. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the information search method as described in any one of claims 1 to 8.

Images