Information display method and device and electronic equipment

Abstract

The embodiment of the invention provides an information display method and device and electronic equipment, and relates to the technical field of computers.The method comprises the steps that in response to a target search word input by a user, candidate keywords matched with the target search word are selected from all candidate keywords to serve as target candidate keywords; wherein each candidate keyword corresponds to at least one description text, and each description text is description information of information content which can be represented by the corresponding candidate keyword under one information dimension; determining user portrait features of the user; selecting a description text from the description texts corresponding to the target candidate keyword based on the user portrait features, and taking the selected description text as a target description text corresponding to the target candidate keyword; displaying recommendation information of the target search word; wherein the recommendation information comprises the target candidate keyword and a target description text corresponding to the target candidate keyword. Through the scheme, the search time demand of the user can be improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to an information display method, device, and electronic device. Background Art

[0002] Retrieving through the search function is an effective way to obtain information. With the continuous development of technology, in addition to users searching for search terms in the search box on the display interface, the network platform can also recommend information, such as recommending terms that users may be interested in.

[0003] In the prior art, after receiving a search term input by a user, the matching degree between the search term and each candidate keyword is determined, and the candidate keyword corresponding to the search term is selected as the target recommendation keyword. The target recommendation keyword is then displayed as recommendation information, thereby utilizing the target recommendation keyword to meet the user's secondary search needs. The candidate keywords can be keywords in a pre-established vocabulary, and the so-called secondary search needs refer to the user's potential need for further searches based on the content displayed in the search results after obtaining the search results for the current search term.

[0004] However, in the related art, the information contained in the recommendation information displayed to the user is relatively simple, and there will be the following problems: if the user is not familiar enough with the target recommendation word as the recommendation information, when seeing the target recommendation word, he may not understand the content expressed by the target recommendation word. For example, in the early days of the TV series "Kuang Biao", when the user saw that the target recommendation word was Kuang Biao, he did not have enough knowledge about it and would not be interested in clicking it, so there was no search demand.

[0005] Based on this, how to improve users' interest in the displayed recommended words so as to increase users' search demand has become a technical problem that needs to be solved urgently. Summary of the Invention

[0006] The purpose of the embodiments of the present application is to provide an information display method, device, and electronic device to enrich the information content displayed by recommended information, increase user interest in the displayed content, and thus increase user search demand. The specific technical solution is as follows:

[0007] In a first aspect of the embodiments of the present application, a method, device, and electronic device for displaying information are provided. The method includes:

[0008] In response to a target search term input by a user, a candidate keyword matching the target search term is selected from each candidate keyword as a target candidate keyword; wherein each candidate keyword corresponds to at least one description text, and each description text is descriptive information of the information content that can be represented by the corresponding candidate keyword in an information dimension;

[0009] Determining user profile characteristics of the user;

[0010] Based on the user portrait feature, selecting a description text from each description text corresponding to the target candidate keyword as the target description text corresponding to the target candidate keyword;

[0011] Display recommendation information of the target search term; wherein the recommendation information includes the target candidate keyword and the target description text corresponding to the target candidate keyword.

[0012] Optionally, in one implementation, a method for determining each description text corresponding to any candidate keyword includes:

[0013] Determining target data content associated with the candidate keyword; wherein the target data content is the search results that can be searched when the candidate keyword is used as a search term;

[0014] A text analysis of the information content of each information dimension is performed on the target data content to obtain each description text corresponding to the candidate keyword.

[0015] Optionally, in one implementation, performing text analysis on the target data content of each information dimension to obtain each description text corresponding to the candidate keyword includes:

[0016] A target question for interacting with a predetermined large language model is constructed using the target data content, the candidate keyword, and each information dimension; wherein the target question is used to instruct the large language model to analyze, from the target data content, a descriptive text of the information content represented by the candidate keyword and the information dimension, according to each information dimension;

[0017] The target question is input into the large language model to obtain description texts corresponding to the candidate keywords.

[0018] Optionally, in one implementation, determining the target data content associated with the candidate keyword includes:

[0019] Determine the search results obtained when the candidate keyword is used as a search term;

[0020] The search results that meet the predetermined determination conditions are determined as the target data content associated with the candidate keyword; wherein the search results that meet the predetermined determination conditions are: all search results obtained by the search, or search results whose content is released within a predetermined time period.

[0021] Optionally, in one implementation, selecting a description text from each description text corresponding to the target candidate keyword based on the user portrait feature as the target description text corresponding to the target candidate keyword includes:

[0022] For each description text corresponding to the target candidate keyword, determine the text features of the description text, and calculate the similarity between the text features of the description text and the user portrait features;

[0023] Based on the obtained similarity corresponding to each description text, a target description text corresponding to the target candidate keyword is selected from the description texts corresponding to the target candidate keyword.

[0024] Optionally, in one implementation, displaying recommendation information for the target search term includes:

[0025] In response to the target candidate keyword corresponding to a plurality of target description texts, the plurality of target description texts are sorted according to a predetermined sorting method to obtain a target sequence corresponding to the target candidate keyword; wherein the predetermined sorting method includes a sorting method based on content popularity and / or a sorting method based on similarity between the plurality of target description texts and the user profile feature;

[0026] Using the target candidate keyword and the corresponding target sequence as recommendation information for the target search term;

[0027] The recommendation information is displayed.

[0028] In a second aspect of the embodiments of the present application, an information display device is further provided, the device comprising:

[0029] A selection module is configured to select, in response to a target search term input by a user, a candidate keyword that matches the target search term from each candidate keyword as a target candidate keyword; wherein each candidate keyword corresponds to at least one description text, and each description text is descriptive information of the information content that can be represented by the corresponding candidate keyword in an information dimension;

[0030] A first determining module, configured to determine a user profile feature of the user;

[0031] A second determining module is configured to select a description text from each description text corresponding to the target candidate keyword based on the user portrait feature as a target description text corresponding to the target candidate keyword;

[0032] A display module is used to display the recommendation information of the target search term; wherein the recommendation information includes the target candidate keyword and the target description text corresponding to the target candidate keyword.

[0033] Optionally, in one implementation, a method for determining each description text corresponding to any candidate keyword includes:

[0034] Determining target data content associated with the candidate keyword; wherein the target data content is the search results that can be searched when the candidate keyword is used as a search term;

[0035] A text analysis of the information content of each information dimension is performed on the target data content to obtain each description text corresponding to the candidate keyword.

[0036] Optionally, in one implementation, performing text analysis on the target data content of each information dimension to obtain each description text corresponding to the candidate keyword includes:

[0037] A target question for interacting with a predetermined large language model is constructed using the target data content, the candidate keyword, and each information dimension; wherein the target question is used to instruct the large language model to analyze, from the target data content, a descriptive text of the information content represented by the candidate keyword and the information dimension, according to each information dimension;

[0038] The target question is input into the large language model to obtain description texts corresponding to the candidate keywords.

[0039] Optionally, in one implementation, determining the target data content associated with the candidate keyword includes:

[0040] Determine the search results obtained when the candidate keyword is used as a search term;

[0041] The search results that meet the predetermined determination conditions are determined as the target data content associated with the candidate keyword; wherein the search results that meet the predetermined determination conditions are: all search results obtained by the search, or search results whose content is released within a predetermined time period.

[0042] Optionally, in one implementation, the second determining module is specifically configured to:

[0043] For each description text corresponding to the target candidate keyword, determine the text features of the description text, and calculate the similarity between the text features of the description text and the user portrait features;

[0044] Based on the obtained similarity corresponding to each description text, a target description text corresponding to the target candidate keyword is selected from the description texts corresponding to the target candidate keyword.

[0045] Optionally, in one implementation, the display module is specifically configured to:

[0046] In response to the target candidate keyword corresponding to a plurality of target description texts, the plurality of target description texts are sorted according to a predetermined sorting method to obtain a target sequence corresponding to the target candidate keyword; wherein the predetermined sorting method includes a sorting method based on content popularity and / or a sorting method based on similarity between the plurality of target description texts and the user profile feature;

[0047] Using the target candidate keyword and the corresponding target sequence as recommendation information for the target search term;

[0048] The recommendation information is displayed.

[0049] In the third aspect provided by the embodiment of the present application, an electronic device is also provided, including a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; the memory is used to store computer programs; and the processor is used to implement any information display method provided in the first aspect when executing the program stored in the memory.

[0050] In another aspect provided by the embodiments of the present application, a computer-readable storage medium is provided, in which a computer program is stored. When the computer program is executed by a processor, any information display method provided in the first aspect is implemented.

[0051] In another aspect provided by the embodiments of the present application, a computer program product comprising instructions is also provided, which, when executed on a computer, enables the computer to execute any of the information display methods provided in the first aspect above.

[0052] In an information display method provided by an embodiment of the present application, each candidate keyword corresponds to at least one description text, and each description text is descriptive information of the information content that can be represented by the corresponding candidate keyword under an information dimension. In this way, after selecting a candidate keyword that matches the target search term input by the user from each candidate keyword as the target candidate keyword, based on the determined user portrait features, a description text is selected from each description text corresponding to the target candidate keyword as the target description text corresponding to the target candidate keyword, and recommendation information of the target search term is displayed, and the recommendation information includes the target candidate keyword and the target description text corresponding to the target candidate keyword. It can be seen that the information content displayed by the recommended information can be enriched through this solution, and the determined target description text is selected based on the user portrait features, and personalized recommendation of recommended information can be performed for different users, thereby increasing the user's interest in the displayed content and the user's search needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art.

[0054] Figure 1 A schematic diagram of a flow chart of a method for obtaining recommended words in the prior art provided in an embodiment of the present application;

[0055] Figure 2 A flowchart of an information display method provided in an embodiment of the present application;

[0056] Figure 3 A flowchart of another information display method provided in an embodiment of the present application;

[0057] Figure 4 A flowchart of another information display method provided in an embodiment of the present application;

[0058] Figure 5 A flowchart of a specific embodiment provided in the embodiments of the present application;

[0059] Figure 6 A schematic diagram of generating multiple description texts for a film or TV series provided in an embodiment of the present application;

[0060] Figure 7 A schematic diagram of a calculation process for the similarity between user preference information and description text provided in an embodiment of the present application;

[0061] Figure 8 A schematic diagram of the structure of an information display device provided in an embodiment of the present application;

[0062] Figure 9 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0063] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.

[0064] In order to better understand the present application, the background technology involved in the embodiments of the present application is first exemplarily introduced below.

[0065] Traditional video search engines all have a related search module that provides users with a batch of recommended words related to the search terms currently entered by the user, with the aim of satisfying the user's search needs, reducing the number of searches, and improving the user experience.

[0066] For example, Figure 1 A flow chart of a method for obtaining recommended words in the prior art provided for an embodiment of the present application. Among them, the vocabulary is the predetermined vocabulary in the embodiment of the present application, and the user question is the target search word in the embodiment of the present application. After receiving the user question sent by the user, the similarity between the user question and each word in the vocabulary is calculated, and the words with higher similarity are determined as recommended words, and the determined recommended words are recalled and sorted. Finally, the sorted recommended words are screened using a predetermined post-strategy, and the screened recommended words are displayed. It should be noted that the words in the above vocabulary are the candidate keywords in the embodiment of the present application, and the recommended words obtained after the above screening are the target candidate keywords in the embodiment of the present application.

[0067] Among them, the above-mentioned predetermined post-strategy can be to screen the recommended words for sensitive words and display the recommended words that do not contain sensitive words. This application does not make any specific limitation on this.

[0068] In this way, after receiving the user question sent by the user, while displaying the answer corresponding to the user question to the user, the user can also be provided with recommended words with a high degree of similarity to the user question to meet the user's possible search needs during the search process.

[0069] It should be noted that the recommended words provided by this module must also be accepted by video search engines, that is, the data type of the recommended words provided must be the data type that video search engines can support and display. However, current search engines basically search by keyword matching, which also results in the current recommended words being some keywords, such as drama titles, celebrity names, genres, etc. Due to the limitations of the data types that search engines can accept, the recommended words provided by this module are also some keywords, and the information they contain is relatively simple, which will lead to the following problems: if users are not familiar with the recommended words provided, they may not understand the content expressed by the recommended words when they see them. For example, in the early days of the TV series "Kuang Biao", when users saw the recommended word "Kuang Biao", they would not be interested in clicking on it because they were not familiar with it. Therefore, there would be no search demand, which would affect user decision-making.

[0070] Based on this, how to improve users' interest in the displayed recommended words so as to increase users' search demand has become a technical problem that needs to be solved urgently.

[0071] In order to solve the above technical problems, the embodiments of the present application provide an information display method, device and electronic device.

[0072] The method can be applied to various user search scenarios, such as searching for movies and TV series on a network platform, or searching for names on a network platform. The method can be applied to various electronic devices, such as tablet computers, smartphones, and laptop computers (hereinafter referred to as electronic devices). The present application does not limit the application scenarios or execution entities of the method.

[0073] An information display method provided in an embodiment of the present application may include:

[0074] In response to a target search term input by a user, a candidate keyword matching the target search term is selected from each candidate keyword as a target candidate keyword; wherein each candidate keyword corresponds to at least one description text, and each description text is descriptive information of the information content that can be represented by the corresponding candidate keyword in an information dimension;

[0075] Determining user profile characteristics of the user;

[0076] Based on the user portrait feature, selecting a description text from each description text corresponding to the target candidate keyword as the target description text corresponding to the target candidate keyword;

[0077] Display recommendation information of the target search term; wherein the recommendation information includes the target candidate keyword and the target description text corresponding to the target candidate keyword.

[0078] In an information display method provided by an embodiment of the present application, each candidate keyword corresponds to at least one description text, and each description text is descriptive information of the information content that can be represented by the corresponding candidate keyword under an information dimension. In this way, after selecting a candidate keyword that matches the target search term input by the user from each candidate keyword as the target candidate keyword, based on the determined user portrait features, a description text is selected from each description text corresponding to the target candidate keyword as the target description text corresponding to the target candidate keyword, and recommendation information of the target search term is displayed, and the recommendation information includes the target candidate keyword and the target description text corresponding to the target candidate keyword. It can be seen that the information content displayed by the recommended information can be enriched through this solution, and the determined target description text is selected based on the user portrait features, and personalized recommendation of recommended information can be performed for different users, thereby increasing the user's interest in the displayed content and the user's search needs.

[0079] The following is a detailed introduction to an information display method provided in an embodiment of the present application in conjunction with the accompanying drawings.

[0080] Figure 2 A flow chart of an information display method provided in an embodiment of the present application is shown as follows: Figure 2 As shown, the method may include the following steps:

[0081] S201: In response to a target search word input by a user, a candidate keyword matching the target search word is selected from various candidate keywords as a target candidate keyword.

[0082] Each candidate keyword corresponds to at least one description text, and each description text is descriptive information of the information content that can be represented by the corresponding candidate keyword in one information dimension.

[0083] In this application, at least one corresponding description text is pre-set for each candidate keyword, and each description text is the description information of the information content that can be represented by the candidate keyword under an information dimension. That is to say, the text content of the description information of the information content that can be represented by a candidate keyword is different under different information dimensions. For example, the fairy tale drama starring star P and star Z is TV series Q. If TV series Q is used as a candidate keyword, the text content of the description information of the information content that can be represented by the candidate keyword under the star dimension is: the black and white duel between star P and star Z; the text content of the description information of the information content that can be represented by the candidate keyword under the subject dimension is: the annual fairy tale drama. Among them, the above-mentioned information dimensions can be film and television themes, actor introductions, plot outlines, etc. for film and television dramas, or they can be themes, character introductions, creative backgrounds, etc. for literary works. This embodiment of the application does not make specific limitations on this.

[0084] It should be noted that for the sake of convenience, the specific implementation method of determining each description text corresponding to any candidate keyword is detailed in steps A1-A2 below and will not be repeated here.

[0085] After receiving the target search term input by the user, the system selects candidate keywords that match the keywords contained in the target search term from the candidate keywords, as target candidate keywords. The target candidate keywords are user-provided recommendations related to the search term currently input by the user, thereby meeting the user's search needs and reducing the number of searches.

[0086] Optionally, the text similarity between the target search term and each candidate keyword is determined, and the candidate keyword with a similarity higher than a predetermined threshold is used as the target candidate keyword.

[0087] Optionally, each candidate keyword and at least one description text corresponding to each candidate keyword are stored in a predetermined vocabulary.

[0088] S202: Determine the user profile characteristics of the user.

[0089] In this application, in order to increase the user's interest in the provided target candidate keywords, the user's behavior data can be obtained, and the user's behavior data can be analyzed to obtain data information used to characterize the user's user preferences. Thus, by extracting text features from the above data information, the user's user portrait features can be determined.

[0090] Optionally, the user's historical search records are analyzed to obtain data information for characterizing the user's user preferences, and the user portrait features of the user are determined by extracting text features from the above data information.

[0091] S203: Based on the user portrait feature, a description text is selected from the description texts corresponding to the target candidate keyword as the target description text corresponding to the target candidate keyword.

[0092] In this application, based on the determined user portrait features, description texts are selected from the various description texts corresponding to the target candidate keywords as the target description texts corresponding to the target candidate keywords, so as to make personalized recommendations of the target description texts for different users, thereby increasing the user's interest in the target candidate keywords and the user's search needs.

[0093] For example, if the user portrait feature indicates that the user prefers police and gangster films, then a description text with the theme of police and gangster films is selected from the description texts corresponding to the target candidate keyword as the target description text corresponding to the target candidate keyword.

[0094] Optionally, in one implementation, Figure 3 A flow chart of another information display method provided in an embodiment of the present application is shown as follows: Figure 3 As shown, the above step S203, based on the user portrait features, selects a description text from each description text corresponding to the target candidate keyword as the target description text corresponding to the target candidate keyword, which may include:

[0095] S2031: For each description text corresponding to the target candidate keyword, determine the text features of the description text, and calculate the similarity between the text features of the description text and the user profile features;

[0096] S2032: Based on the obtained similarity corresponding to each description text, select a target description text corresponding to the target candidate keyword from the description texts corresponding to the target candidate keyword.

[0097] In this implementation, for each description text corresponding to the target candidate keyword, the text features of the description text are determined, and the similarity between the text features of the description text and the user portrait features is calculated to obtain the similarity corresponding to the description text. Then, based on each similarity obtained, the target description text corresponding to the target candidate keyword is selected from the description texts corresponding to the target candidate keyword.

[0098] Optionally, a similarity threshold is preset, and each description text having a similarity greater than the similarity threshold is determined as a target description text corresponding to the target candidate keyword.

[0099] In this implementation, the target description text corresponding to the target candidate keyword is determined based on the similarity between the user portrait features and the text features of each description text. Personalized recommendations of the target description text can be made for different users. While enriching the information content displayed by the recommended information, the user's interest in the target candidate keyword can be increased, thereby increasing the user's search needs.

[0100] S204: Displaying recommended information for the target search term;

[0101] The recommendation information includes target candidate keywords and target description texts corresponding to the target candidate keywords.

[0102] In this application, after determining the target candidate keywords and the target description text corresponding to the target candidate keywords, the recommendation information containing the target candidate keywords and the target description text corresponding to the target candidate keywords will be displayed as the recommendation information of the target search term for users to view.

[0103] Optionally, in one implementation, Figure 4 A flow chart of another information display method provided in an embodiment of the present application is shown as follows: Figure 4 As shown, the above step S204, displaying the recommended information of the target search term, may include the following steps:

[0104] S2041: In response to the number of target description texts corresponding to the target candidate keyword being multiple, sorting the multiple target description texts according to a predetermined sorting method to obtain a target sequence corresponding to the target candidate keyword;

[0105] The predetermined sorting method includes a sorting method based on content popularity and / or a sorting method based on similarity between the multiple target description texts and user portrait features;

[0106] S2042: Using the target candidate keyword and the corresponding target sequence as recommendation information for the target search term;

[0107] S2043: Display recommended information.

[0108] In this implementation, when there are multiple target description texts corresponding to the target candidate keywords, the multiple target description texts may be sorted according to a predetermined sorting method to obtain a target sequence corresponding to the target candidate keywords.

[0109] When the above-mentioned predetermined sorting method includes a sorting method based on the similarity between the multiple target description texts and the user portrait features, the similarity between the multiple target description texts and the user portrait features can be determined, and the multiple target description texts can be sorted in order from high to low similarity to obtain a target sequence corresponding to the target candidate keywords.

[0110] When the above-mentioned predetermined sorting method includes a sorting method based on content popularity, the content popularity corresponding to the multiple target description texts can be determined, and the multiple target description texts can be sorted in order of content popularity from high to low to obtain a target sequence corresponding to the target candidate keywords.

[0111] When the predetermined sorting method includes a sorting method based on content popularity and a sorting method based on similarity between the multiple target description texts and user portrait features, the following two sorting methods may be used:

[0112] (1) First, multiple target description texts are sorted according to the similarity between the multiple target description texts and the user portrait features, and then they are sorted again in descending order according to the popularity of their corresponding content to obtain the target sequence corresponding to the target candidate keywords.

[0113] (2) First, multiple target description texts are sorted according to the content popularity corresponding to the multiple target description texts, and then they are sorted again in descending order according to their similarity with the user portrait features to obtain the target sequence corresponding to the target candidate keywords.

[0114] Optionally, based on the popularity of the content and / or based on the similarity between the multiple target description texts and the user portrait features, corresponding weights are set, and the multiple target description texts corresponding to the target candidate keywords are sorted according to the determined weights.

[0115] In this implementation, multiple target description texts corresponding to target candidate keywords are sorted according to a predetermined sorting method. In this way, when users browse, they can give priority to seeing the target description texts with the highest content popularity and / or the highest level of interest, thereby increasing the user's interest in the target candidate keywords and the user's search needs.

[0116] Optionally, the target description texts are ranked based on the determined exposure times and / or display times of the target description texts. It should be noted that when the description text corresponding to the candidate keyword is first obtained, since the description text lacks statistical features such as display and clicks, the statistical features of the candidate keyword can be used to initialize the statistical features of the description text, that is, the statistical features of the candidate keyword can be assigned to the description text.

[0117] Optionally, when the number of determined target candidate keywords is multiple, each target candidate keyword can be ranked based on the popularity of the content corresponding to the target candidate keyword and / or the similarity between the target candidate keyword and the user portrait feature.

[0118] In this implementation, when the number of determined target candidate keywords is multiple, each target candidate keyword can be sorted according to the above-mentioned sorting method, so that users can preferentially see the target candidate keywords with the highest content popularity and / or the highest interest level, thereby increasing the user's interest in the target candidate keywords and the user's search needs.

[0119] Optionally, the target candidate keywords are ranked based on the determined exposure times and / or display times of the target candidate keywords.

[0120] In an information display method provided by an embodiment of the present application, each candidate keyword corresponds to at least one description text, and each description text is descriptive information of the information content that can be represented by the corresponding candidate keyword under an information dimension. In this way, after selecting a candidate keyword that matches the target search term input by the user from each candidate keyword as the target candidate keyword, based on the determined user portrait features, a description text is selected from each description text corresponding to the target candidate keyword as the target description text corresponding to the target candidate keyword, and recommendation information of the target search term is displayed, and the recommendation information includes the target candidate keyword and the target description text corresponding to the target candidate keyword. It can be seen that the information content displayed by the recommended information can be enriched through this solution, and the determined target description text is selected based on the user portrait features, and personalized recommendation of recommended information can be performed for different users, thereby increasing the user's interest in the displayed content and the user's search needs.

[0121] Optionally, in one embodiment, a method for determining each description text corresponding to any candidate keyword may include the following steps:

[0122] Step A1: Determine the target data content associated with the candidate keyword;

[0123] The target data content is the search results that can be found when the candidate keyword is used as the search term;

[0124] Step A2: Perform text analysis on the target data content in each information dimension to obtain description texts corresponding to the candidate keywords.

[0125] In this embodiment, for any candidate keyword, the search results that can be found when the candidate keyword is used as a search term are determined as the target data content associated with the candidate keyword. Then, text analysis of the information content of each information dimension is performed on the determined target data content to obtain the description text corresponding to the candidate keyword.

[0126] It should be noted that the data content of the search results that can be searched can be presented in the form of text type and / or video type, which is not specifically limited in the embodiments of this application. For example, if the candidate keyword is star x, the search results obtained can be text content. In this case, the data content of the search results is presented in the form of text type, such as the name of the film and television series in which star x has participated. The search results obtained can also be video content. In this case, the data content of the search results is presented in the form of video type, such as Reuters videos of star x, highlight clips of star x in film and television series, etc.

[0127] Among them, each of the above-mentioned information dimensions can be a unified information dimension pre-set for all object types, such as subject matter and characters, etc.; it can also be different information dimensions pre-set for different object types. For example, the information dimensions pre-set for film and television dramas include film and television subject matter, actor introduction and plot summary, etc., and the information dimensions pre-set for literary works include work subject matter, character introduction, creative background, etc., and this embodiment of the present application does not make specific limitations on this.

[0128] Optionally, the candidate keyword is stored in a predetermined vocabulary in an entry format, and each description text corresponding to the candidate keyword can be added to the target entry where the candidate keyword is located in the form of a field.

[0129] In this specific implementation method, the description texts corresponding to each candidate keyword are determined in advance. In this way, when selecting the target description text corresponding to the target candidate keyword, it is sufficient to directly select from the description texts corresponding to the target candidate keyword, thereby improving the selection efficiency of the target description text.

[0130] Optionally, in one implementation, step A2, performing text analysis on the target data content of each information dimension to obtain description texts corresponding to the candidate keywords, may include the following steps:

[0131] Step A21: constructing a target question for interacting with a predetermined large language model using the target data content, the candidate keyword, and each information dimension;

[0132] The target question is: to instruct the large language model to analyze the descriptive text of the information content corresponding to the candidate keyword and represented under each information dimension from the target data content;

[0133] Step A22: Input the target question into the large language model to obtain the description texts corresponding to the candidate keywords.

[0134] In this implementation, a predetermined large language model can be used to generate the various descriptive texts corresponding to the candidate keywords. Therefore, before using the large language model to generate the descriptive texts, a target question for interacting with the predetermined large language model can be constructed using the target data content, the candidate keywords, and each information dimension. The target question is used to instruct the large language model to analyze the descriptive text corresponding to the candidate keywords and the information content represented under each information dimension from the target data content. In this way, after the constructed target question is input into the predetermined large language model, the predetermined large language model can generate the various descriptive texts corresponding to the candidate keywords.

[0135] Among them, the above-mentioned large language model can be LLM (Large Language Model), GTP-3 (Generative Pre-trained Transfoemer3, natural language processing model), BERT (Bidirectional Encoder Representations from Transformers, a pre-trained language representation model used to improve the understanding ability of the natural language processing system), etc., and this embodiment of the application does not make specific limitations on this.

[0136] In this implementation, by constructing a target question, the large language model, after receiving the target question, can analyze the descriptive text corresponding to the candidate keywords and the information content represented in each information dimension from the target data content as indicated by the target question, thereby obtaining the individual descriptive texts corresponding to the candidate keywords. This improves the relevance of the descriptive texts obtained in each information dimension with the candidate keywords, thereby increasing the likelihood of users continuing to click. Furthermore, generating descriptive text using the large language model can improve the efficiency of determining the descriptive text corresponding to any candidate keyword.

[0137] Optionally, in one implementation, the above step A1, determining the target data content associated with the candidate keyword, may include the following steps:

[0138] Step A11: determining search results obtained when the candidate keyword is used as a search term;

[0139] Step A12: determining the search results that meet the predetermined determination conditions as target data content associated with the candidate keyword;

[0140] The search results that meet the predetermined determination conditions are: all search results obtained through the search, or search results obtained through the search whose content is released within a predetermined time period.

[0141] In this implementation, the candidate keyword is used as a search term to perform a search, and based on the search results obtained, the search results that meet the predetermined determination conditions are determined as target data content associated with the candidate keyword.

[0142] When the search results that meet the predetermined determination condition are all the search results obtained through the search, all the search results obtained through the search can be used as target data content associated with the candidate keyword.

[0143] For example, the candidate keyword is "introduction to drama Q", and the corresponding search results include "introduction to drama Q's work", "introduction to drama Q's series" and "introduction to the movie version of drama Q". At this time, "introduction to drama Q's work", "introduction to drama Q's series" and "introduction to the movie version of drama Q" can all be used as target data content associated with the candidate keyword.

[0144] When the search results that meet the predetermined determination conditions are search results whose content was published within a predetermined time period, all search results whose content was published within the predetermined time period can be used as target data content associated with the candidate keyword. The predetermined time period can be the last day, the last seven days, the last month, etc., and this embodiment of the application does not specifically limit this.

[0145] Optionally, in a network platform, a search is performed using the candidate keyword as a search term to obtain search results.

[0146] Optionally, the candidate keyword is used as a search term to search in a pre-built data set to obtain search results, wherein the data set stores data information associated with the candidate keyword.

[0147] In this implementation, the search results obtained by searching with the candidate keywords as the search terms are used as the basis for determining the target data content, so as to enhance the relevance between the determined target data content and the candidate keywords.

[0148] Next, an information display method provided by an embodiment of the present application is specifically introduced in conjunction with a specific embodiment using film and television dramas as a business scenario. Figure 5 This is a flowchart of a specific embodiment provided by the present application. The user question is the target search term in the present application, the predetermined term is the predetermined vocabulary in the present application, which can also be called a vocabulary, the user preference is the user profile feature in the present application, and the basic data information is the data information in the pre-built data set in the present application, which can also be called meta-information.

[0149] S501: Obtain user questions;

[0150] S502: Information recall; that is, recalling the recommended words corresponding to the user question and multiple description texts corresponding to the recommended words from the vocabulary; wherein the recommended words corresponding to the user question are the target candidate keywords in this application.

[0151] Specifically, before executing the above process, the following steps are also included:

[0152] Step 1: Generate description text. Specifically: First, generate the corresponding description text for all movies and TV series. Since there is a lot of information at the bottom of movies and TV series, and the information that each user is interested in is not exactly the same. For example, Figure 6 A schematic diagram of generating multiple description texts for a film or TV series is provided in an embodiment of the present application, wherein the multiple description texts include description text 1, description text 2 and description text 3. Taking the film or TV series "xx" as an example, a person who likes star y should reflect the name of star y when recommending "xx", that is, the corresponding description text 1 can be "xx": The black and white contest between star y and star w; a person who likes police and gangster dramas should reflect the subject matter of the film and television drama when recommending "xx", that is, the corresponding description text 2 can be "xx": The annual police and gangster blockbuster; a person who likes to watch the recently popular film and television dramas should reflect the new and popular film and television dramas when recommending "xx", that is, the corresponding description text 3 can be "xx": The hottest police and gangster drama in recent times.

[0153] Therefore, based on the underlying information of the film and television drama, descriptive texts under different information dimensions are generated, for example, Figure 6 When the information dimension is star, the description text is "xx": a black and white contest between star y and star w; when the information dimension is subject matter, the description text is "xx": the annual police and gangster blockbuster; when the information dimension is new and hot, the description text is "xx": the hottest police and gangster drama in recent times.

[0154] In this way, although the underlying layer still uses the title of the film or TV series as the search term in the actual request, the descriptive text of different information dimensions generated can display the information content that the user is interested in when displaying the recommended words, so as to achieve personalized recommendation of the recommended content and increase the possibility of users continuing to click.

[0155] Step 2: vocabulary construction, specifically: adding the generated description text to the predetermined vocabulary, specifically adding it to the vocabulary in the form of a field and to the candidate keywords associated with the description text, so that the generated description text participates in recall and sorting together with the candidate keywords.

[0156] It should be noted that in the initial stage of adding the description text to the predetermined vocabulary, since the description text lacks statistical features such as display and clicks, the candidate keywords corresponding to the description text can be used to initialize the statistical features of the description text, that is, the statistical features of the candidate keywords associated with the description text are assigned to the description text.

[0157] Optionally, a large language model is used to generate a description text. Specifically, the candidate keyword and the data information corresponding to the candidate keyword are input into the large language model to obtain the description text corresponding to the candidate keyword, and the obtained description text is added to the predetermined word library. For example, Figure 5 As shown, the title of the film or TV series and the data information corresponding to the film or TV series (i.e., the basic data information in this application) are input into the LLM large language model, so that the LLM large language model generates a descriptive text associated with the film or TV series, and the obtained descriptive text is added to the predetermined vocabulary.

[0158] S503: Information sorting; that is, sorting the recommended words. Specifically, when multiple recommended words are obtained, the recommended words can be sorted based on the exposure of the recommended words, that is, the number of times the recommended words are exposed and / or displayed, or the similarity between the recommended words and the user's questions.

[0159] S504: Execute the post-strategy; that is, use the post-strategy to enhance the weight of multiple description texts corresponding to the recommended words. Specifically: determine the user preference (that is, the user portrait feature in the embodiment of the present application), and calculate the similarity between the user preference and the description text, and enhance the weight of the description text with high similarity, so that the display position of the description text can be sorted in the front.

[0160] For example, Figure 7 A schematic diagram of a calculation process for the similarity between a user's preference information and a description text provided in an embodiment of the present application. In which, user behavior 1, user behavior 2, and user behavior 3 are obtained from the user preference information (i.e., the historical search records in the embodiment of the present application), and meta information 1, meta information 2, and meta information 3 are analyzed from user behavior 1, user behavior 2, and user behavior 3, respectively. Then, after text vectorization is performed on meta information 1, meta information 2, and meta information 3, the text features used to characterize the user's preference (the user portrait features in the embodiment of the present application) are merged to obtain the text features. After that, the text features of the user's preference and the similarity between the text features obtained after text vectorization of the description text are calculated to obtain the similarity result between the two text features. Thus, based on the determined similarity result, the description text with high similarity is weighted.

[0161] S505: Information display; that is, displaying recommended words and the elevated description text. Specifically, each description text is assigned to the user question entered by the user so that it can be searched. This means that the search engine supports displaying the recommended words corresponding to the user question and the extracted description text. In other words, the displayed recommended words and elevated description text are data types that can be accepted by the search engine. The recommended words and elevated description text are the recommended content in the embodiments of this application.

[0162] In this specific embodiment, by adding descriptive text to candidate keywords, the information content displayed in the recommended information under different information dimensions is enriched, providing users with more information to choose from, increasing the user's interest in the displayed information, as well as the user's search needs, thereby improving the user's usage experience.

[0163] Based on the above method embodiment, the present application embodiment also provides an information display device, such as Figure 8 FIG. 1 is a schematic diagram of the structure of an information display device provided in an embodiment of the present application, wherein the device includes:

[0164] The selection module 810 is configured to select, in response to a target search term input by a user, a candidate keyword that matches the target search term from each candidate keyword as a target candidate keyword; wherein each candidate keyword corresponds to at least one description text, and each description text is descriptive information of the information content that can be represented by the corresponding candidate keyword in an information dimension;

[0165] A first determining module 820 is configured to determine a user profile feature of the user;

[0166] A second determining module 830 is configured to select a description text from the description texts corresponding to the target candidate keyword based on the user portrait feature as a target description text corresponding to the target candidate keyword;

[0167] The display module 840 is used to display the recommendation information of the target search term; wherein the recommendation information includes the target candidate keyword and the target description text corresponding to the target candidate keyword.

[0168] In an information display method provided by an embodiment of the present application, each candidate keyword corresponds to at least one description text, and each description text is descriptive information of the information content that can be represented by the corresponding candidate keyword under an information dimension. In this way, after selecting a candidate keyword that matches the target search term input by the user from each candidate keyword as the target candidate keyword, based on the determined user portrait features, a description text is selected from each description text corresponding to the target candidate keyword as the target description text corresponding to the target candidate keyword, and recommendation information of the target search term is displayed, and the recommendation information includes the target candidate keyword and the target description text corresponding to the target candidate keyword. It can be seen that the information content displayed by the recommended information can be enriched through this solution, and the determined target description text is selected based on the user portrait features, and personalized recommendation of recommended information can be performed for different users, thereby increasing the user's interest in the displayed content and the user's search needs.

[0169] Optionally, in one implementation, a method for determining each description text corresponding to any candidate keyword includes:

[0170] Determining target data content associated with the candidate keyword; wherein the target data content is the search results that can be searched when the candidate keyword is used as a search term;

[0171] A text analysis of the information content of each information dimension is performed on the target data content to obtain each description text corresponding to the candidate keyword.

[0172] Optionally, in one implementation, performing text analysis on the target data content of each information dimension to obtain each description text corresponding to the candidate keyword includes:

[0173] A target question for interacting with a predetermined large language model is constructed using the target data content, the candidate keyword, and each information dimension; wherein the target question is used to instruct the large language model to analyze, from the target data content, a descriptive text of the information content represented by the candidate keyword and the information dimension, according to each information dimension;

[0174] The target question is input into the large language model to obtain description texts corresponding to the candidate keywords.

[0175] Optionally, in one implementation, determining the target data content associated with the candidate keyword includes:

[0176] Determine the search results obtained when the candidate keyword is used as a search term;

[0177] The search results that meet the predetermined determination conditions are determined as the target data content associated with the candidate keyword; wherein the search results that meet the predetermined determination conditions are: all search results obtained by the search, or search results whose content is released within a predetermined time period.

[0178] Optionally, in one implementation, the second determining module 830 is specifically configured to:

[0179] For each description text corresponding to the target candidate keyword, determine the text features of the description text, and calculate the similarity between the text features of the description text and the user portrait features;

[0180] Based on the obtained similarity corresponding to each description text, a target description text corresponding to the target candidate keyword is selected from the description texts corresponding to the target candidate keyword.

[0181] Optionally, in one implementation, the display module 840 is specifically configured to:

[0182] In response to the target candidate keyword corresponding to a plurality of target description texts, the plurality of target description texts are sorted according to a predetermined sorting method to obtain a target sequence corresponding to the target candidate keyword; wherein the predetermined sorting method includes a sorting method based on content popularity and / or a sorting method based on similarity between the plurality of target description texts and the user profile feature;

[0183] Using the target candidate keyword and the corresponding target sequence as recommendation information for the target search term;

[0184] The recommendation information is displayed.

[0185] The present application also provides an electronic device, such as Figure 9 As shown, it includes a processor 901, a communication interface 902, a memory 903 and a communication bus 904, wherein the processor 901, the communication interface 902, and the memory 903 communicate with each other through the communication bus 904.

[0186] Memory 903, used for storing computer programs;

[0187] The processor 901 is configured to implement any of the information display methods provided in the above-mentioned embodiments of the present application when executing the program stored in the memory 903 .

[0188] The communication bus mentioned in the terminal can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is used in the figure, but this does not mean that there is only one bus or only one type of bus.

[0189] The communication interface is used for communication between the above terminal and other devices.

[0190] The memory may include random access memory (RAM) or non-volatile memory, such as at least one disk storage. Alternatively, the memory may be at least one storage device located away from the processor.

[0191] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0192] In another embodiment provided in the present application, a computer-readable storage medium is further provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the information display method described in any one of the above embodiments is implemented.

[0193] In another embodiment provided by the present application, a computer program product including instructions is also provided, which, when executed on a computer, enables the computer to execute the information display method described in any one of the above embodiments.

[0194] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When software is used for implementation, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrations. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).

[0195] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0196] Each embodiment in this specification is described in a related manner. Similar portions between the various embodiments can be referenced to each other. Each embodiment focuses on the differences between the other embodiments. In particular, since the apparatus embodiments, electronic device embodiments, computer-readable storage medium embodiments, and computer program product embodiments are generally similar to the method embodiments, their descriptions are relatively simple. For related portions, reference can be made to the descriptions of the method embodiments.

[0197] The above description is only a preferred embodiment of the present application and is not intended to limit the scope of protection of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application are included in the scope of protection of the present application.

Claims

1. An information display method, characterized in that: The method comprises: In response to a target search term input by a user, a candidate keyword matching the target search term is selected from each candidate keyword as a target candidate keyword; wherein each candidate keyword corresponds to at least one description text, and each description text is descriptive information of the information content that can be represented by the corresponding candidate keyword in an information dimension; Determining user profile characteristics of the user; Based on the user portrait feature, selecting a description text from each description text corresponding to the target candidate keyword as the target description text corresponding to the target candidate keyword; Display recommendation information of the target search term; wherein the recommendation information includes the target candidate keyword and the target description text corresponding to the target candidate keyword.

2. The method according to claim 1, characterized in that Methods for determining the description texts corresponding to any candidate keyword include: Determining target data content associated with the candidate keyword; wherein the target data content is the search results that can be searched when the candidate keyword is used as a search term; A text analysis of the information content of each information dimension is performed on the target data content to obtain each description text corresponding to the candidate keyword.

3. The method according to claim 2, characterized in that The text analysis of the information content of each information dimension of the target data content to obtain each description text corresponding to the candidate keyword includes: A target question for interacting with a predetermined large language model is constructed using the target data content, the candidate keyword, and each information dimension; wherein the target question is used to instruct the large language model to analyze, from the target data content, a descriptive text of the information content represented by the candidate keyword and the information dimension, according to each information dimension; The target question is input into the large language model to obtain description texts corresponding to the candidate keywords.

4. The method according to claim 2, characterized in that The step of determining the target data content associated with the candidate keyword includes: Determine the search results obtained when the candidate keyword is used as a search term; The search results that meet the predetermined determination conditions are determined as the target data content associated with the candidate keyword; wherein the search results that meet the predetermined determination conditions are: all search results obtained by the search, or search results whose content is released within a predetermined time period.

5. The method according to claim 1, wherein The selecting, based on the user portrait feature, a description text from each description text corresponding to the target candidate keyword as the target description text corresponding to the target candidate keyword includes: For each description text corresponding to the target candidate keyword, determine the text features of the description text, and calculate the similarity between the text features of the description text and the user portrait features; Based on the obtained similarity corresponding to each description text, a target description text corresponding to the target candidate keyword is selected from the description texts corresponding to the target candidate keyword.

6. The method according to claim 1, characterized in that The display of the recommendation information of the target search term includes: In response to the target candidate keyword corresponding to a plurality of target description texts, the plurality of target description texts are sorted according to a predetermined sorting method to obtain a target sequence corresponding to the target candidate keyword; wherein the predetermined sorting method includes a sorting method based on content popularity and / or a sorting method based on similarity between the plurality of target description texts and the user profile feature; Using the target candidate keyword and the corresponding target sequence as recommendation information for the target search term; The recommendation information is displayed.

7. An information display device, characterized in that: The device comprises: A selection module is configured to select, in response to a target search term input by a user, a candidate keyword that matches the target search term from each candidate keyword as a target candidate keyword; wherein each candidate keyword corresponds to at least one description text, and each description text is descriptive information of the information content that can be represented by the corresponding candidate keyword in an information dimension; A first determining module, configured to determine a user profile feature of the user; A second determining module is configured to select a description text from each description text corresponding to the target candidate keyword based on the user portrait feature as a target description text corresponding to the target candidate keyword; A display module is used to display the recommendation information of the target search term; wherein the recommendation information includes the target candidate keyword and the target description text corresponding to the target candidate keyword.

8. The device according to claim 7, characterized in that Methods for determining the description texts corresponding to any candidate keyword include: Determining target data content associated with the candidate keyword; wherein the target data content is the search results that can be searched when the candidate keyword is used as a search term; Performing text analysis on the target data content of each information dimension to obtain description texts corresponding to the candidate keywords; and / or, The second determining module is specifically configured to: For each description text corresponding to the target candidate keyword, determine the text features of the description text, and calculate the similarity between the text features of the description text and the user portrait features; Based on the obtained similarity corresponding to each description text, a target description text corresponding to the target candidate keyword is selected from the description texts corresponding to the target candidate keyword.

9. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; Memory for storing computer programs; A processor, configured to implement the method according to any one of claims 1 to 6 when executing a program stored in a memory.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images