Information processing method and device, electronic device, and storage medium
By calculating the correlation between multiple types of text content and the entries to be searched and displaying them separately, the complex content in information search is solved, and the simplicity of information and search satisfaction are improved.
Patent Information
- Application Number
- CN202210371036.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-04-08
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2042-04-08
AI Technical Summary
In the information search scenario, the content displayed separately is too complicated, resulting in low information volume, visual confusion, and difficulty in highlighting key points, reducing the search satisfaction of the service object.
By obtaining target information matching the entries to be searched, the correlation is calculated based on the weights of various types of text content, and the text content matching the entries to be searched is selected and differentiated, thereby improving the matching degree and information simplicity.
It effectively reduces the amount of data that distinguishes the displayed content, enhances the display effect of important information, and improves the simplicity of information display and the search satisfaction of service objects.
Smart Images

Figure CN116932740B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of computer technology, and more specifically, to an information processing method and device, an electronic device, a storage medium, and a program product. Background Art
[0002] In the information search scenario, after searching for information matching the search terms, the searched information will be displayed on the search results display page, and the words matching the search terms in the information will be displayed separately. However, the information processing method in the related art usually has the problem that the content to be displayed separately is complicated, the actual amount of information is low, and it is easy to cause visual confusion. Summary of the invention
[0003] To solve the above-mentioned technical problems, the embodiments of the present application provide an information processing method and device, an electronic device, a storage medium, and a program product, which can improve the matching degree between the distinguished displayed content and the search terms, reduce the amount of data of the distinguished displayed content, make the information display more concise, and at the same time enhance the display effect of important information and improve the search satisfaction of the service object.
[0004] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by the practice of the present application.
[0005] According to one aspect of an embodiment of the present application, there is provided an information processing method, the method comprising:
[0006] Acquire target information matching the term to be searched, wherein the target information includes multiple types of text content;
[0007] Calculating the correlation between each type of text content included in the target information and the to-be-searched term according to the weights of the multiple types of text content;
[0008] Selecting a target type of text content from the multiple types of text content according to the correlation between the various types of text content and the to-be-searched terms;
[0009] The words in the text content of the target type that match the terms to be searched are displayed distinctively.
[0010] According to one aspect of an embodiment of the present application, there is provided an information processing device, the device comprising:
[0011] An acquisition module, configured to acquire target information matching the term to be searched, wherein the target information includes multiple types of text content;
[0012] A calculation module, configured to calculate the correlation between the various types of text content included in the target information and the to-be-searched terms according to the weights of the multiple types of text content;
[0013] A selection module configured to select a target type of text content from the multiple types of text content according to the correlation between the various types of text content and the to-be-searched terms;
[0014] The display module is configured to distinguish and display the words in the text content of the target type that match the search terms.
[0015] In one embodiment of the present application, the calculation module includes:
[0016] A first processing module is configured to process the to-be-searched terms to obtain the to-be-searched words;
[0017] A first calculation submodule is configured to calculate the initial correlation between the various types of text content and the terms to be searched according to the terms to be searched;
[0018] The second calculation submodule is configured to calculate the correlation between the various types of text content and the to-be-searched terms according to the initial correlation between the various types of text content and the to-be-searched terms and the weights of the multiple types of text content.
[0019] In one embodiment of the present application, the first calculation submodule includes:
[0020] A first search module is configured to search for a target word matching the to-be-searched word from the various types of text content;
[0021] The first determination module is configured to determine the initial correlation between the various types of text content and the to-be-searched terms according to the importance of the to-be-searched terms and the importance of target terms in the various types of text content that match the to-be-searched terms.
[0022] In one embodiment of the present application, the number of the target information includes multiple; the device further includes:
[0023] A second determination module is configured to determine the weight of each target information according to a matching strategy between the to-be-searched term and each target information;
[0024] A correlation calculation module, configured to calculate the correlation between each target information and the to-be-searched term according to the weight of each target information and the correlation between various types of text content contained in each target information and the to-be-searched term;
[0025] The information display module is configured to sort and display multiple target information according to the correlation between each target information and the term to be searched.
[0026] In one embodiment of the present application, the acquisition module includes:
[0027] A second processing module is configured to process the to-be-searched terms to obtain a to-be-searched word set;
[0028] A classification module, configured to classify the words in the to-be-searched word set to obtain a plurality of word subsets;
[0029] The search module is configured to respectively obtain target information matching the multiple word subsets, wherein one word subset corresponds to one matching strategy.
[0030] In one embodiment of the present application, the second processing module includes:
[0031] An identification module, configured to identify the intent of the term to be searched and obtain an intent tag of the term to be searched;
[0032] The word segmentation module is configured to perform word segmentation processing on the to-be-searched terms, and to construct the to-be-searched word set according to the intention tags and the words obtained by the word segmentation processing.
[0033] In one embodiment of the present application, the selection module includes:
[0034] A third determination module, configured to determine text content of a specified type and text content of other types except the specified type from the multiple types of text content;
[0035] A fourth determination module, configured to determine candidate types of text content from the other types of text content according to the correlation between the various types of text content and the to-be-searched terms;
[0036] The fifth determination module is configured to use the candidate type of text content and the designated type of text content as the target type of text content.
[0037] In one embodiment of the present application, the fourth determining module includes:
[0038] A first determination submodule is configured to screen out, from the other types of text content, text contents of initial candidate types whose corresponding correlation exceeds a correlation threshold value, according to the correlation between the various types of text contents and the terms to be searched;
[0039] The second determination submodule is configured to select a set number of initial candidate types of text content as the candidate type of text content in descending order of relevance.
[0040] In one embodiment of the present application, the display module includes:
[0041] A first type determination module is configured to determine a specified type of word from a set of words to be searched; the set of words to be searched includes words obtained by processing the words to be searched;
[0042] The first display submodule is configured to distinguish and display the words in the text content of the target type that match the words of the specified type.
[0043] In one embodiment of the present application, the display module further includes:
[0044] A second type determination module is configured to determine other types of words in the to-be-searched word set except for the specified type of words;
[0045] A candidate word search module is configured to search for words matching the other types of words from the target type of text content to obtain a candidate word set;
[0046] The second display submodule is configured to select a specified number of words from the candidate word set for distinguishing display.
[0047] In one embodiment of the present application, the display module includes:
[0048] An adjacent word determination module, configured to obtain a first word and a second word that are adjacent in position from the to-be-searched word;
[0049] a second search module configured to search for a third word matching the first word and a fourth word matching the second word from the text content of the target type;
[0050] a closeness determination module, configured to determine the closeness between the third word and the fourth word according to the position of the third word in the text content of the target type and the position of the fourth word in the text content of the target type;
[0051] The third display submodule is configured to determine words matching the to-be-searched terms from the text content of the target type if the determined closeness meets a preset condition, and to display the determined words distinctively.
[0052] In one embodiment of the present application, the compactness determination module includes:
[0053] a distance determination module configured to determine the distance between the third word and the fourth word according to the position of the third word in the text content of the target type and the position of the fourth word in the text content of the target type;
[0054] The closeness determination submodule is configured to determine the closeness between the third word and the fourth word according to the position importance of the third word and the fourth word and the distance between the third word and the fourth word.
[0055] According to one aspect of an embodiment of the present application, there is provided an electronic device, including:
[0056] one or more processors;
[0057] The storage device is used to store one or more computer programs, and when the one or more computer programs are executed by the one or more processors, the electronic device implements the information processing method as described above.
[0058] According to one aspect of an embodiment of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor of an electronic device, the electronic device implements the information processing method as described above.
[0059] According to one aspect of an embodiment of the present application, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the information processing method as described above is implemented.
[0060] In the technical solution provided in the embodiment of the present application, the correlation between the various types of text content contained in the target information and the terms to be searched is calculated according to the weights of different types of text content, so that the calculated correlation can reflect the importance of the various types of text content to the terms to be searched, so as to improve the accuracy of the correlation calculation. And by selecting the target type of text content from the multiple types of text content contained in the target information based on the correlation between the various types of text content and the terms to be searched, and distinguishing and displaying the words matching the terms to be searched in the text content of the target type, it is possible to select text content that is more relevant to the terms to be searched from the target information, thereby improving the matching degree between the distinguished display content and the terms to be searched, and also avoiding the problem of indistinct important information caused by indiscriminately distinguishing and displaying all types of text content in the target information, that is, the technical solution of the embodiment of the present application effectively reduces the amount of data for the distinguished display content, enhances the display effect of important information, and makes the information display more concise, thereby improving the search satisfaction of the service object.
[0061] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS
[0062] The drawings herein are incorporated into the specification and constitute a part of the specification, showing embodiments consistent with the present application, and together with the specification, are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work. In the drawings:
[0063] Figure 1 It is a schematic diagram of an implementation environment involved in this application;
[0064] Figure 2 is a flowchart of an information processing method shown in an exemplary embodiment of the present application;
[0065] Figure 3 is a flowchart of an information processing method shown in another exemplary embodiment of the present application;
[0066] Figure 4 is a flowchart of an information processing method shown in another exemplary embodiment of the present application;
[0067] Figure 5 is a flowchart of an information processing method shown in another exemplary embodiment of the present application;
[0068] Figure 6 is a flowchart of an information processing method shown in another exemplary embodiment of the present application;
[0069] Figure 7 is a flowchart of an information processing method shown in another exemplary embodiment of the present application;
[0070] Figure 8 is a flowchart of an information processing method shown in another exemplary embodiment of the present application;
[0071] Fig. 9 is a flowchart of an information processing method shown in another exemplary embodiment of the present application;
[0072] Fig.10 is a flowchart of an information processing method shown in another exemplary embodiment of the present application;
[0073] Fig.11 is a flowchart of an information processing method shown in another exemplary embodiment of the present application;
[0074] Fig.12 is a flowchart of an information processing method shown in another exemplary embodiment of the present application;
[0075] Fig.13 is a flowchart of an information processing method shown in another exemplary embodiment of the present application;
[0076] Fig.14 is a flowchart of an information processing method shown in another exemplary embodiment of the present application;
[0077] Fig.15 is a schematic diagram of another implementation environment involved in the present application;
[0078] Fig.16 is a schematic diagram of the structure of an information processing device shown in an exemplary embodiment of the present application;
[0079] Fig.17 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application is shown. DETAILED DESCRIPTION
[0080] Here, exemplary embodiments will be described in detail, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are only examples of devices and methods consistent with some aspects of the present application as detailed in the attached claims.
[0081] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.
[0082] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.
[0083] It should also be noted that the "multiple" mentioned in this application refers to two or more than two. "And / or" describes the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship.
[0084] Before introducing the technical solutions of the embodiments of the present application, the nouns and terms involved in the embodiments of the present application are explained first. The nouns and terms involved in the embodiments of the present application are subject to the following interpretations.
[0085] In an information search scenario, after searching for information that matches the search terms, the searched information will be displayed on the search results display page, and the words in the information that match the search terms will be displayed separately, making the differentiated display content more complicated, and thus making the differentiated display content actually contain less effective information, unable to highlight the key points, reducing the visual attention of the service object, and causing the service object to be unable to quickly view the desired content. Moreover, the more complicated the differentiated display content is, the more likely it is to cause visual confusion, further reducing the search experience of the service object. Based on this, the embodiments of the present application provide a new information processing scheme that can reduce the amount of data for differentiated display content, enhance the display effect of important information, and make the information display more concise.
[0086] See also Figure 1 , Figure 1 1 is a schematic diagram of an implementation environment involved in the present application. The implementation environment includes a terminal device 100 and a server 200. The terminal device 100 and the server 200 communicate with each other through a wired or wireless network. The terminal device 100 can upload its own data to the server 200 or obtain data from the server 200.
[0087] Among them, the terminal device 100 may include but is not limited to smart phones, tablets, laptops, computers, intelligent voice interaction devices, smart home appliances, vehicle-mounted terminals, aircraft, etc.
[0088] Server 200 can be a server that provides various services. It can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network) and basic cloud computing services such as big data and artificial intelligence platforms. This is not restricted here.
[0089] It should be noted that Figure 1 The number of terminal devices 100 and servers 200 in the figure is only for illustration, and any number of terminal devices 100 and servers 200 may be provided according to actual needs.
[0090] In an exemplary embodiment, the information processing method provided in the embodiment of the present application can be executed by the terminal device 100.
[0091] Exemplarily, the terminal device 100 can obtain target information that matches the term to be searched, the target information including multiple types of text content, and then calculate the correlation between the various types of text content included in the target information and the term to be searched based on the weights of the multiple types of text content. Then, based on the correlation between the various types of text content and the term to be searched, the terminal device 100 can select the target type of text content from the multiple types of text content, and distinguish and display the words in the target type of text content that match the term to be searched. Through this information processing method, the calculated correlation can reflect the importance of various types of text content to the term to be searched, so as to improve the accuracy of the correlation calculation. By selecting the target type of text content from the multiple types of text content contained in the target information based on the correlation between the various types of text content and the term to be searched, and distinguishing and displaying the words matching the term to be searched in the target type of text content, it is possible to select text content that is more relevant to the term to be searched from the target information, thereby improving the matching degree between the distinguished displayed content and the term to be searched, and avoiding the problem of indistinct important information caused by indiscriminately distinguishing and displaying various types of text content in the target information, that is, effectively reducing the data volume of the distinguished displayed content, enhancing the display effect of important information, and making the information display more concise.
[0092] In another exemplary embodiment, the server 200 may have functions similar to those of the terminal device 100, thereby executing the information processing method provided in the embodiment of the present application. Exemplarily, the server 200 may obtain target information matching the term to be searched, the target information including multiple types of text content, and then, based on the weights of the multiple types of text content, calculate the correlation between the various types of text content included in the target information and the term to be searched, and then, based on the correlation between the various types of text content and the term to be searched, select the target type of text content from the multiple types of text content, and distinguish and display the words matching the term to be searched in the target type of text content.
[0093] In another exemplary embodiment, the terminal device 100 and the server 200 may also jointly execute the information processing method provided in the embodiment of the present application. Exemplarily, the terminal device 100 may obtain the term to be searched and send the term to be searched to the server 200. The server 200 may obtain target information matching the term to be searched, the target information containing multiple types of text content; according to the weights of the multiple types of text content, calculate the correlation between the various types of text content contained in the target information and the term to be searched; according to the correlation between the various types of text content and the term to be searched, select the target type of text content from the multiple types of text content; select the words matching the term to be searched from the text content of the target type, and send the determined words and the target information to the terminal device 100. Based on the data received from the server 200, the terminal device distinguishes and displays the words matching the term to be searched in the text content of the target type.
[0094] Figure 1 The technical solution of the illustrated embodiment can be applied to various application scenarios, including but not limited to search, cloud technology, artificial intelligence, smart transportation, assisted driving, etc. In practical applications, it can be adjusted accordingly according to the specific application scenario. For example, if applied to a cloud technology scenario, the server 200 can be a server located in the cloud, and the terminal device 100 can provide cloud services with the help of the computing power of the cloud, such as web search services, shopping website search services, etc. This is also the application scenario of the information processing method of the embodiment of the present application jointly executed by the terminal device 100 and the server 200 as described in the aforementioned embodiment.
[0095] If applied to smart transportation or assisted driving scenarios, the terminal device 100 may be a vehicle-mounted terminal, a navigation terminal, etc., and the information processing method is executed by the vehicle-mounted terminal or the navigation terminal. For example, the vehicle-mounted terminal may obtain the terms to be searched, and distinguish and display the words matching the terms to be searched in the text content of the target type; for another example, the information processing method may be applied to a map search scenario, where the terms to be searched may include terms used to describe the location that the service object wants to find, and the navigation terminal may obtain location information matching the terms, and determine the text content of the target type from the location information, and distinguish and display the words matching the terms in the text content of the target type.
[0096] It should be noted that in this application, when it involves data related to the service objects such as search terms and information to be searched, when the information processing method of this application is applied to specific products or technologies, the permission or consent of the service objects must be obtained, and the extraction, use and processing of the relevant data must comply with local safety standards and local laws and regulations.
[0097] See also Figure 2 , Figure 2is a flowchart of an information processing method shown in an exemplary embodiment of the present application. The method can be applied to Figure 1 The implementation environment shown, which can be Figure 1 The terminal device 100 in the implementation environment shown in the figure may also be executed by Figure 1 The server 200 in the implementation environment shown in the figure may also execute the command. Figure 1 The terminal device 100 and the server 200 in the illustrated implementation environment execute together.
[0098] like Figure 2 As shown, in an exemplary embodiment, the information processing method may include steps S210-S240, which are described in detail as follows:
[0099] Step S210, obtaining target information matching the term to be searched, wherein the target information includes multiple types of text content.
[0100] First of all, it should be explained that the terms to be searched include terms whose related information needs to be searched, which can be entered by the service object through the search box based on its own needs. For example, the term to be searched can be a word entered by the service object, or it can be a short text entered by the service object, or it can be text obtained by converting the voice input by the service object.
[0101] Secondly, information refers to the objects transmitted and processed by audio, messages, and communication systems. The target information includes information that matches the term to be searched, and its types include but are not limited to video information, music information, news information, picture information, etc. Based on different application scenarios, the type of target information is different. For example, if applied to a video search scenario, the target information includes video information; if applied to a music search scenario, the target information includes music information; if applied to a news search scenario, the target information includes news information; if applied to a web search scenario (for example, a browser search scenario), the target information includes video information, music information, picture information, etc.
[0102] In the embodiment of the present application, the target information includes multiple types of text content. For example, for video information, it includes different types of text content such as video title, video title alias, video summary, video tag, actor list, director, etc.; for music information, it includes different types of text content such as music name, singer, lyrics, etc.; for news information, it includes different types of text content such as news title, author, summary, news content, etc.; for picture information, it includes different types of text content such as picture name, picture tag, picture introduction, etc.
[0103] In the embodiment of the present application, after determining the term to be searched, information matching the term to be searched is searched from the content library, and the found information is recorded as target information to obtain target information matching the term to be searched. The specific process of obtaining target information matching the term to be searched can be flexibly set according to actual needs.
[0104] Step S220, calculating the correlation between the various types of text content included in the target information and the to-be-searched terms according to the weights of the various types of text content.
[0105] In the embodiment of the present application, corresponding weights may be set for the various types of text content included in the target information, and the weights may characterize the importance of the different types of text content. The specific setting method of the weights of the various types of text content may be flexibly set according to actual needs.
[0106] Optionally, the weights of various types of text content can be set according to the attention of the service object. In one example, the service object is usually more concerned about the content that is relatively front in the display page. Therefore, the corresponding weights of various types of text content can be set based on their positions in the display page, wherein the order of the positions is positively correlated with the weights, that is, the closer the position of the text content is, the greater the corresponding weight. For example, assuming that the target information includes video information, the video title, video tag and video summary are displayed in sequence from top to bottom in the display page, then the weight of the video title ≥ the weight of the video tag ≥ the weight of the video summary.
[0107] In another example, the service object is usually more concerned about the content with larger fonts in the display page. Therefore, the corresponding weights of various types of text content can be set based on the font sizes of the text content in the display page, wherein the font size is positively correlated with the weight, that is, the larger the font of the text content, the larger the corresponding weight. For example, assuming that the target information includes video information, in the display page, the font of the video title ≥ the font of the video summary ≥ the font of the cast list, then the weight of the video title ≥ the weight of the video summary ≥ the weight of the cast list. Of course, in other embodiments of the present application, the weights of various types of text content can also be set based on other methods, and the specific setting method of the weight is not limited here.
[0108] In an embodiment of the present application, after obtaining target information that matches the term to be searched, the weights of the various types of text content included in the target information can be obtained, and based on the weights of the various types of text content, the correlation between each type of text content and the term to be searched can be calculated to obtain the correlation between each type of text content contained in the target information and the term to be searched.
[0109] Step S230 , selecting target type of text content from multiple types of text content according to the correlation between each type of text content and the term to be searched.
[0110] In an embodiment of the application, the target type of text content includes text content selected from multiple types of text content included in the target information.
[0111] In some optional embodiments, the specific selection method can be flexibly set according to actual needs. In one example, the text content with the greatest correlation can be selected from the multiple types of text content contained in the target information as the target type of text content. For example, assuming that the music information includes the music name, singer and lyrics, the correlation between the music name and the search term ≥ the correlation between the singer and the search term ≥ the correlation between the lyrics and the search term, then the music name is used as the target type of text content.
[0112] Step S240: Distinguish and display the words in the text content of the target type that match the search term.
[0113] In an embodiment of the present application, after selecting the target type of text content from the multiple types of text content contained in the target information, words matching the search terms are searched from the target type of text content, and the searched words are displayed distinctively to distinguish the searched words from other words, so that the service object can pay more attention to the searched words.
[0114] In some optional embodiments, the specific manner of distinguishing display can be flexibly set according to actual needs, and optionally includes but is not limited to at least one of the following manners:
[0115] Changing the color of the words, that is, changing the color of the words in the target type of text content that match the to-be-searched terms to make them different from the colors of other words in the target type of text content. For example, the color of the words in the target type of text content that match the to-be-searched terms can be changed to red;
[0116] Changing the background of the words, that is, changing the background of the words matching the search terms in the target type of text content to make them different from the backgrounds of other words in the target type of text content;
[0117] Changing the brightness of the words, that is, changing the brightness of the words in the target type of text content that match the to-be-searched terms to make them different from the brightness of other words in the target type of text content, for example, the brightness of the words in the target type of text content that match the to-be-searched terms can be increased;
[0118] Changing the font size of words, that is, changing the font size of words in the target type's text content that match the terms to be searched, to make them different from the font sizes of other words in the target type's text content. For example, the words in the target type's text content that match the terms to be searched can be enlarged.
[0119] exist Figure 1 In the illustrated embodiment, the correlation between the various types of text content contained in the target information and the terms to be searched is calculated according to the weights of the different types of text content, so that the calculated correlation can reflect the importance of the various types of text content to the terms to be searched, so as to improve the accuracy of the correlation calculation. And by selecting the target type of text content from the multiple types of text content contained in the target information based on the correlation between the various types of text content and the terms to be searched, and distinguishing and displaying the words in the target type of text content that match the terms to be searched, it is possible to select text content that is more relevant to the terms to be searched from the target information, thereby improving the matching degree between the distinguished displayed content and the terms to be searched, and also avoiding the problem of indistinct important information caused by indiscriminately distinguishing and displaying all types of text content in the target information, that is, the technical solution of the embodiment of the present application effectively reduces the amount of data for the distinguished displayed content, enhances the display effect of important information, and makes the information display more concise.
[0120] In an exemplary embodiment, see Figure 3 , Figure 3 is a flowchart of an information processing method shown in another exemplary embodiment of the present application. The method can be applied to Figure 1 The implementation environment shown, which can be Figure 1 The terminal device 100 in the implementation environment shown in the figure may also be executed by Figure 1 The server 200 in the implementation environment shown in the figure may also execute the command. Figure 1 The terminal device 100 and the server 200 in the implementation environment shown in FIG. Figure 3 As shown, the information processing method includes steps S211-S212, and steps S220-S240, which are described in detail as follows:
[0121] Step S211, processing the search terms to be searched to obtain a set of words to be searched.
[0122] In an embodiment of the present application, the to-be-searched terms may be processed to obtain words, and a to-be-searched word set may be created based on the obtained words.
[0123] The specific method for processing the search terms can be flexibly set according to actual needs.
[0124] For example, in an optional implementation, the process of processing the search terms to obtain the set of words to be searched may include: performing word segmentation processing on the search terms, and constructing the set of words to be searched based on the words obtained by word segmentation. The search terms may be segmented at different word segmentation granularities. It should be understood that the word segmentation granularity is used to characterize the number of Chinese characters contained in a Chinese word.
[0125] In another optional implementation, the process of processing the search terms to obtain the set of search terms may include: identifying the intent of the search terms to obtain the intent tags of the search terms; and constructing the set of search terms based on the intent tags. In one example, the information includes tags, for example, video information includes video tags, and music information includes music tags. The intent tag may be at least one of the tags included in the information.
[0126] In another optional implementation, the process of processing the search terms to obtain the set of words to be searched may include: identifying the intent of the search terms to obtain the intent tags of the search terms to be searched; performing word segmentation on the search terms, and constructing the set of words to be searched based on the intent tags and the words obtained by the word segmentation. That is, the set of words to be searched includes not only the words obtained by the word segmentation, but also the intent tags.
[0127] Step S212: Acquire target information that matches the set of words to be searched.
[0128] After determining the set of words to be searched, information matching the words in the set of words to be searched is searched from the content library, and the searched information is used as target information.
[0129] In order to improve the search speed, in some implementations, the information in the content library may be segmented in advance, and an inverted index file may be created based on the words obtained by the segmentation process, so as to find target information matching the set of words to be searched based on the inverted index file.
[0130] Among them, the inverted index file may include at least one of the following data: a word, a word length, an information ID (Identity document) containing the word, the importance of the word in the information, an ID of the text content containing the word, and the position of the word in the text content.
[0131] In an example, assuming that a piece of information is recorded as a document, and the different types of text content contained in the information are recorded as different index fields, the inverted index file can be as follows: Figure 4As shown, the inverted index file includes an index field: term, a byte offset, a byte length, and a data file, wherein the data file includes term bytes corresponding to the term, the index field: term refers to a term in a certain index field, the byte offset refers to the starting position and the ending position of the term byte corresponding to the term, and the byte length refers to the length of the term byte corresponding to the term; the term bytes include inverse text frequency index (idf) data, multiple skip list node data, wherein the inverse text frequency index data can be a 4-byte floating point number (4 bytes float) for storing the inverse text frequency index of the term, and the skip list node data includes the last local identification number data (last local id, used to record the identification number of the last document contained in the previous skip list node of the skip list node, the last local identification number data can be a 32-bit integer data), the node length (used to record the length of the skip list node, which can be a 32-bit integer data), and multiple document items (document item, used to record relevant data of a document containing a word); a document item includes a document item length (used to record the length of the document item, which can be a 32-bit integer data), a document differential identifier (delta id, which can be an integer variable), a term importance (document term weight, used to record the importance of a term in a document, which can be a 4-byte floating point number), other relevant data (which can be used to record other relevant data of a document, for example, it can include the click-through rate of the document, the number of index fields containing the term in the document, and other relevant data can be 8-bit integer data), multiple index field data (used to record relevant information of index fields containing the term in the document), and the index field data includes an index field identifier (field id, used to record the id of the index field containing the term in the document, which can be an 8-bit integer data), a position number (offset size, used to record the number of times a term appears in the index field), and multiple position data (used to record the position of the term in the index field, which can be a 32-bit integer data).
[0132] exist Figure 3 In the illustrated embodiment, by first processing the search terms to be searched to obtain a set of words to be searched and then acquiring target information matching the set of words to be searched, the search speed of the target information can be improved.
[0133] It should be noted that: Figure 3 The specific implementation details of steps S220 to S240 shown in FIG. Figure 2 Steps S220 to S240 shown are not described in detail.
[0134] In an exemplary embodiment, see Figure 5 , Figure 5 is a flowchart of an information processing method shown in another exemplary embodiment of the present application. The method can be applied to Figure 1 The implementation environment shown, which can be Figure 1 The terminal device 100 in the implementation environment shown in the figure may also be executed by Figure 1 The server 200 in the implementation environment shown in the figure may also execute the command. Figure 1 The terminal device 100 and the server 200 in the implementation environment shown in FIG. Figure 5 As shown, the information processing method includes step S211, step S310-step S320, step S220-step S240, which are described in detail as follows:
[0135] Step S310: classify the words in the to-be-searched word set to obtain a plurality of word subsets.
[0136] exist Figure 5 In the illustrated embodiment, after determining the set of words to be searched, the words in the set of words to be searched can be classified to obtain multiple word subsets. The specific classification method can be flexibly set according to actual needs. For example, the words in the set of words to be searched can be classified based on the importance of the words, the part of speech of the words, etc. It should be noted that the importance of the words can be determined based on the TF (Term Frequency) and / or IDF (Inverse Document Frequency) of the words. In an example, the set of words to be searched can be divided into intention word subsets, entity word subsets, core word subsets and other word subsets according to whether they are intention labels, entity words and core words. The intention word subsets include the intention labels in the set of words to be searched, the entity word subsets include the entity words in the set of words to be searched, the core word subsets include the core words in the set of words to be searched, and the other word subsets include the words in the set of words to be searched except the intention labels, core words and entity words, wherein entity words refer to words used to represent objectively existing and distinguishable matters, including but not limited to nouns, such as names of people, names of organizations, names of places, etc.; core words refer to words whose importance is greater than a set importance threshold, wherein the importance threshold can be flexibly set according to actual needs, for example, it can be set to 0.4, etc.
[0137] Step S320 , respectively obtaining target information matching multiple word subsets, wherein one word subset corresponds to one matching strategy.
[0138] In this embodiment, after obtaining multiple word subsets, target information matching the multiple word subsets is searched respectively, wherein one word subset corresponds to one matching strategy, thereby obtaining target information matching the term to be searched through multiple matching strategies. Optionally, target information matching the multiple word subsets can be obtained in parallel, thereby improving the efficiency of obtaining the target information.
[0139] It should be noted that, in the present embodiment, different matching strategies are obtained based on word subsets. In other embodiments, different matching strategies may be created in other ways.
[0140] exist Figure 5 In the illustrated embodiment, the words in the search word set are first classified to obtain multiple word subsets; then, target information matching the multiple word subsets is obtained respectively, wherein one word subset corresponds to one matching strategy, so that the target information can be searched through different matching strategies, thereby improving the comprehensiveness of the target information.
[0141] It should be noted that: Figure 5 The specific implementation details of step S211 shown can be referred to Figure 3 In step S211 shown, Figure 5 The specific implementation details of steps S220 to S240 shown in FIG. Figure 2 Steps S220 to S240 shown are not described in detail.
[0142] In an exemplary embodiment, see Figure 6 , Figure 6 is a flowchart of an information processing method shown in another exemplary embodiment of the present application. The method can be applied to Figure 1 The implementation environment shown, which can be Figure 1 The terminal device 100 in the implementation environment shown in the figure may also be executed by Figure 1 The server 200 in the implementation environment shown in the figure may also execute the command. Figure 1 The terminal device 100 and the server 200 in the implementation environment shown in FIG. Figure 6 As shown, the information processing method includes step S210, step S221-step S223, step S230-step S240, which are described in detail as follows:
[0143] Step S221, processing the search terms to be searched to obtain the words to be searched.
[0144] In this embodiment, after determining the to-be-searched term, the to-be-searched term can be processed to obtain the to-be-searched word. The specific processing method can refer to the record of the aforementioned step S211, which will not be repeated here. The to-be-searched word is a word in the to-be-searched word set.
[0145] Step S222, calculating the initial correlation between various types of text content and the terms to be searched according to the terms to be searched.
[0146] After the words to be searched are obtained, the initial correlation between various text contents contained in the target information and the words to be searched is calculated according to the words to be searched.
[0147] The specific method of calculating the initial correlation between various text contents and the terms to be searched based on the terms to be searched can be flexibly set according to actual needs.
[0148] Step S223, calculating the correlation between each type of text content and the term to be searched according to the initial correlation between each type of text content and the term to be searched, and the weights of multiple types of text content.
[0149] After obtaining the initial correlation between the various types of text content contained in the target information and the terms to be searched, the correlation between the various types of text content and the terms to be searched can be calculated based on the initial correlation between the various types of text content and the terms to be searched and the weights of the various types of text content. In an optional implementation, the correlation between the various types of text content and the terms to be searched is calculated as follows:
[0150] score(m,n)=field_weight n *score ′ (m,n)
[0151] Among them, score(m,n) represents the correlation between the nth type of text content in the mth target information and the search term, and field_weight n The weight of the text content of the nth type, score ′ (m,n) represents the initial correlation between the n-th type of text content in the m-th target information and the term to be searched.
[0152] exist Figure 6 In the illustrated embodiment, the search terms are first processed to obtain the words to be searched, and then the initial correlations between various types of text contents and the search terms are calculated based on the words to be searched. Then, based on the initial correlations between various types of text contents and the search terms, as well as the weights of various types of text contents, the correlations between various types of text contents and the search terms are calculated, thereby improving the accuracy of the correlations between various types of text contents and the search terms.
[0153] It should be noted that: Figure 6 The specific implementation details of steps S210, S230-S240 shown in FIG. Figure 2Step S210, step S230-step S240 shown are not repeated here.
[0154] In an exemplary embodiment, see Figure 7 , Figure 7 is a flowchart of an information processing method shown in another exemplary embodiment of the present application. The method can be applied to Figure 1 The implementation environment shown, which can be Figure 1 The terminal device 100 in the implementation environment shown in the figure may also be executed by Figure 1 The server 200 in the implementation environment shown in the figure may also execute the command. Figure 1 The terminal device 100 and the server 200 in the implementation environment shown in FIG. Figure 7 As shown, the information processing method includes step S210, step S221, step S410-step S420, step S223 and step S230-step S240, which are described in detail as follows:
[0155] Step S410: Find target words matching the searched words from various text contents.
[0156] In this embodiment, a target word matching the to-be-searched word is found from various text contents included in the target information.
[0157] Step S420, determining the initial correlation between each type of text content and the term to be searched based on the importance of the term to be searched and the importance of the target term matching the term to be searched in each type of text content.
[0158] After the target word is determined, the initial correlation between each type of text content and the term to be searched is determined based on the importance of the term to be searched and the importance of the target word that matches the term to be searched in each type of text content, thereby improving the accuracy of the initial correlation between each type of text content and the term to be searched.
[0159] The specific method for determining the initial relevance can be flexibly set according to actual needs. In an optional implementation, the initial relevance between various types of text content and the terms to be searched can be determined according to the following formula:
[0160]
[0161] Among them, score′(m,n) represents the initial correlation between the nth type of text content in the mth target information and the search term, q represents the set of words to be searched, and d nIt represents the target word set that matches the searched word found from the n-th type of text content in the m-th target information, w(t)*idf represents the importance of the t-th word, where w(t) represents the word frequency.
[0162] exist Figure 7 In the embodiment shown, target words matching the words to be searched are first found from various types of text content, and then the initial correlation between each type of text content and the words to be searched is determined based on the importance of the words to be searched and the importance of the target words matching the words to be searched in each type of text content. This allows the calculated initial correlation to reflect the importance of the text content to the search terms, thereby further improving the accuracy of the correlation calculation.
[0163] It should be noted that: Figure 7 The specific implementation details of steps S210, S230-S240 shown in FIG. Figure 2 Steps S210, S230-S240 shown, Figure 7 The specific implementation details of step S221 and step S223 shown in FIG. Figure 6 Step S221 and step S223 shown are not repeated here.
[0164] In an exemplary embodiment, see Figure 8 , Figure 8 is a flowchart of an information processing method shown in another exemplary embodiment of the present application. The method can be applied to Figure 1 The implementation environment shown, which can be Figure 1 The terminal device 100 in the implementation environment shown in the figure may also be executed by Figure 1 The server 200 in the implementation environment shown in the figure may also execute the command. Figure 1 The terminal device 100 and the server 200 in the implementation environment shown in FIG. Figure 8 As shown, the information processing method includes steps S210-S220, steps S231-S233 and step S240, which are described in detail as follows:
[0165] Step S231 : determining text content of a specified type and text content of other types except the specified type from multiple types of text content.
[0166] Among them, the specified type of text content includes pre-set text content that needs to be displayed distinguishably for the words it contains that match the search terms. For example, the text content with the largest weight can be set to the specified type of text content, or, since the title is usually more important, the title can be set to the text content of the specified content.
[0167] In this embodiment, text content of a specified type and text content of other types except the specified type are determined from multiple types of text content included in the target information.
[0168] Step S232, determining candidate types of text content from other types of text content according to the correlation between each type of text content and the term to be searched.
[0169] After determining other types of text content from the multiple types of text content included in the target information, candidate types of text content can be determined from other types of text content according to the correlation between each type of text content and the search term. The specific determination method can be flexibly set according to actual needs.
[0170] For example, in an optional implementation, the corresponding text content with the greatest correlation may be selected from other types of text content as the candidate type of text content.
[0171] Step S233: taking the candidate type text content and the designated type text content as the target type text content.
[0172] In this embodiment, after determining the designated type of text content and the candidate type of text content from the multiple types of text content included in the target information, the designated type of text content and the candidate type of text content are used as the target type of text content.
[0173] exist Figure 8 In the illustrated embodiment, a designated type of text content and other types of text content except the designated type are first determined from a plurality of types of text content, and then candidate types of text content are determined from other types of text content based on the correlation between each type of text content and the term to be searched, and then the candidate types of text content and the designated type of text content are used as target types of text content, thereby enabling both the words in the text content with a high correlation with the term to be searched and the words in the text content of the designated type to be displayed distinctively, thereby enabling the service object to be reminded of the designated type of text content while ensuring the correlation between the distinguished displayed content and the term to be searched, thereby facilitating the service object's memory.
[0174] It should be noted that: Figure 8 The specific implementation details of steps S210-S220 and step S240 shown in FIG. Figure 2 Steps S210 to S220 and step S240 are shown and will not be described in detail.
[0175] In an exemplary embodiment, see Fig. 9 , Fig. 9is a flowchart of an information processing method shown in another exemplary embodiment of the present application. The method can be applied to Figure 1 The implementation environment shown, which can be Figure 1 The terminal device 100 in the implementation environment shown in the figure may also be executed by Figure 1 The server 200 in the implementation environment shown in the figure may also execute the command. Figure 1 The terminal device 100 and the server 200 in the implementation environment shown in FIG. Fig. 9 As shown, the information processing method includes steps S210-S220, step S231, step S510-S520, step S233 and step S240, which are described in detail as follows:
[0176] Step S510 , based on the correlation between each type of text content and the term to be searched, select the initial candidate type of text content whose corresponding correlation exceeds the correlation threshold from other types of text content.
[0177] The specific value of the correlation threshold can be flexibly set according to actual needs, for example, it can be set to 80%, 90%, etc.
[0178] After determining other types of text content from the multiple types of text content included in the target information, the initial candidate type of text content is screened out from the other types of text content according to whether the corresponding correlation exceeds the correlation threshold, wherein the correlation between the initial candidate type of text content and the term to be searched exceeds the correlation threshold. For example, assuming that the correlation threshold is 90, the other types of text content include video titles, video tags, and directors, wherein the correlation between the video title and the term to be searched is 98%, the correlation between the video tag and the term to be searched is 60%, and the correlation between the director and the term to be searched is 95%, then the initial candidate type of text content includes video titles and directors.
[0179] Step S520 , selecting a set number of initial candidate types of text content as candidate types of text content in descending order of relevance.
[0180] The set number includes the number of text contents of the candidate types, and the specific value thereof can be flexibly set according to actual needs, for example, it can be set to 2, 1, etc.
[0181] After determining the text content of the initial candidate type, a set number of text contents of the initial candidate type are selected from the text content of the initial candidate type in descending order of relevance, and the selected text contents of the initial candidate type are used as the text contents of the candidate type, so as to distinguish and display the words in the text content with high relevance to the term to be searched, and improve the relevance between the distinguished displayed content and the term to be searched. For example, assuming that the text content of the initial candidate type includes a video title and a director, wherein the relevance of the video title to the term to be searched is greater than the relevance of the director to the term to be searched, and the set number is 1, then the text content of the selected candidate type includes the video title.
[0182] exist Fig. 9 In the illustrated embodiment, based on the correlation between each type of text content and the terms to be searched, initial candidate type of text content whose corresponding correlation exceeds a correlation threshold is screened out from other types of text content, and then a set number of initial candidate type of text content are selected in descending order of correlation as candidate type of text content, so that text content with a higher correlation with the terms to be searched is used as target type of text content, thereby improving the matching degree between the distinguished displayed content and the terms to be searched.
[0183] It should be noted that: Fig. 9 The specific implementation details of steps S210-S220 and step S240 shown in FIG. Figure 2 Steps S210 to S220, and step S240 are shown. Fig. 9 The specific implementation details of step S231 and step S233 shown in FIG. Figure 8 Step S231 and step S233 shown are not repeated here.
[0184] In an exemplary embodiment, see Fig.10 , Fig.10 is a flowchart of an information processing method shown in another exemplary embodiment of the present application. The method can be applied to Figure 1 The implementation environment shown, which can be Figure 1 The terminal device 100 in the implementation environment shown in the figure may also be executed by Figure 1 The server 200 in the implementation environment shown in the figure may also execute the command. Figure 1 The terminal device 100 and the server 200 in the implementation environment shown in FIG. Fig.10 As shown, the information processing method includes steps S210-S230 and steps S241-S242, which are described in detail as follows:
[0185] Step S241, determining a designated type of word from a set of words to be searched; the set of words to be searched includes words obtained by processing the search terms.
[0186] It should be noted that the specific method for obtaining the set of words to be searched can be found in the aforementioned step S211, which will not be repeated here.
[0187] The designated type words include pre-set words that need to be displayed in a differentiated manner from words that match them in the target type of text content. The designated type words can be flexibly set according to actual needs. For example, since core words, entity words, and intent labels can better reflect the content that the service object wants to find, the designated type words can be set to at least one of core words, entity words, and intent labels.
[0188] Step S242: Distinguish and display the words in the target type of text content that match the words of the specified type.
[0189] In this embodiment, after determining the specified type of words from the set of words to be searched corresponding to the search term, words matching the specified type of words are searched from the target type of text content, and the searched words are displayed distinctively.
[0190] exist Fig.10 In the illustrated embodiment, a specified type of word is determined from a set of words to be searched; the set of words to be searched includes words obtained by processing the search terms, and words in the target type of text content that match the specified type of words are distinguished and displayed. Since the specified type of words are not any type of words, the words in the target type of text content that match the specified type of words are distinguished and displayed, which can further improve the matching degree between the distinguished displayed content and the search terms.
[0191] It should be noted that: Fig.10 The specific implementation details of steps S210 to S230 shown in FIG. Figure 2 Steps S210 to S230 shown are not described in detail.
[0192] In an exemplary embodiment, see Fig.11 , Fig.11 is a flowchart of an information processing method shown in another exemplary embodiment of the present application. The method can be applied to Figure 1 The implementation environment shown, which can be Figure 1 The terminal device 100 in the implementation environment shown in the figure may also be executed by Figure 1 The server 200 in the implementation environment shown in the figure may also execute the command. Figure 1 The terminal device 100 and the server 200 in the implementation environment shown in FIG. Fig.11 As shown, the information processing method includes steps S210 to S230, and steps S241 to S245, which are described in detail as follows:
[0193] Step S243: determining other types of words in the to-be-searched word set except for the designated type of words.
[0194] Other types of words include words in the to-be-searched word set except for the specified type of words.
[0195] In this embodiment, after determining the specified type of words from the set of words to be searched, other types of words may also be determined.
[0196] Step S244, searching for words that match other types of words from the target type of text content to obtain a set of candidate words.
[0197] In this embodiment, after determining other types of words, words matching other types of words are searched from the target type of text content, and a candidate word set is constructed based on the searched words.
[0198] Step S245, selecting a specified number of words from the candidate word set for distinguishing display.
[0199] The specified number can be flexibly set according to actual needs, for example, it can be set to 5, 10, etc., or it can also be set to 50%, 40%, etc. of the total number of words included in the candidate word set.
[0200] In order to avoid the situation where too many words are displayed in a differentiated manner, resulting in the service object being unable to grasp the key points, in this embodiment, after determining the candidate word set corresponding to the text content of the target type, a specified number of words are selected from the candidate word set for differentiated display. Among them, a specified number of words can be selected from the candidate word set for differentiated display in the order of the words from front to back in the text content of the target type. For example, assuming that the text content of the target type includes "I am... stars... moon... sun", the candidate word set includes {I, stars, moon, sun}, and the specified number is 3, then "I", "stars" and "moon" in the text content of the target type are displayed in a differentiated manner.
[0201] exist Fig.11 In the illustrated embodiment, words in the target type's text content that match words of a specified type are displayed differentially, and the number of words in the target type's text content that match words of other types that are displayed differentially is limited, thereby ensuring the degree of match between the differentially displayed content and the terms to be searched, reducing the amount of data in the differentially displayed content, and increasing the amount of information in the differentially displayed content.
[0202] It should be noted that: Fig.11 The specific implementation details of steps S210 to S230 shown in FIG. Figure 2 Steps S210 to S230 are shown. Fig.11 The specific implementation details of steps S241-S242 shown can be referred to Fig.10 Steps S241 to S242 shown are not repeated here.
[0203] In an exemplary embodiment, see Fig.12 , Fig.12 is a flowchart of an information processing method shown in another exemplary embodiment of the present application. The method can be applied to Figure 1 The implementation environment shown, which can be Figure 1 The terminal device 100 in the implementation environment shown in the figure may also be executed by Figure 1 The server 200 in the implementation environment shown in the figure may also execute the command. Figure 1 The terminal device 100 and the server 200 in the implementation environment shown in FIG. Fig.12 As shown, the information processing method includes steps S210 to S230, and steps S610 to S640, which are described in detail as follows:
[0204] Step S610: Acquire a first word and a second word that are adjacent to each other from the words to be searched.
[0205] In this embodiment, the search term may be segmented to obtain a word sequence, and the first word and the second word that are adjacent to each other may be found from the word sequence.
[0206] Step S620: Find a third word matching the first word and a fourth word matching the second word from the text content of the target type.
[0207] In this embodiment, after obtaining the first word and the second word that are adjacent to each other from the search term, a third word that matches the first word is found from the text content of the target type, and a fourth word that matches the second word is found from the text content of the target type.
[0208] Step S630: Determine the closeness between the third word and the fourth word according to the position of the third word in the text content of the target type and the position of the fourth word in the text content of the target type.
[0209] After the third word and the fourth word are determined from the target type of text content, the closeness between the third word and the fourth word can be determined according to the positions of the third word and the fourth word in the target type of text content, wherein the closeness can represent the distance difference between the third word and the fourth word.
[0210] The specific method of determining the closeness between the third word and the fourth word can be flexibly set according to actual needs.
[0211] For example, in an optional implementation, the closeness between the third word and the fourth word can be determined based on the distance between the third word and the fourth word, wherein the distance and the closeness can be negatively correlated. In one example, the inverse of the distance between the third word and the fourth word can be used as the closeness between the third word and the fourth word.
[0212] Step S640: If the determined closeness meets the preset condition, words matching the to-be-searched terms are determined from the text content of the target type, and the determined words are displayed distinctively.
[0213] The preset condition can be flexibly set according to actual needs. For example, it can be set to that the tightness exceeds the tightness threshold.
[0214] After determining the closeness of the third word and the fourth word, if the closeness meets the preset condition, the words matching the to-be-searched terms in the target type of text content are displayed in a differentiated manner. Among them, only the third word and the fourth word may be displayed in a differentiated manner, or all words matching the to-be-searched terms may be displayed in a differentiated manner, or the manner of displaying the words matching the to-be-searched terms in the target type of text content in a differentiated manner may also refer to the aforementioned steps S241 to S245.
[0215] It should be noted that, in the present embodiment, there may be multiple groups of first and second words that are adjacent to each other, and correspondingly, there may be multiple groups of third and fourth words. When the closeness of the multiple groups of third and fourth words meets the preset conditions, the words that match the search terms in the text content of the target type can be displayed distinguishably.
[0216] exist Fig.12 In the illustrated embodiment, a first word and a second word adjacent in position are obtained from the term to be searched, the closeness between the third word and the fourth word is determined according to the positional importance of the third word and the fourth word and the distance between the third word and the fourth word, and the closeness between the third word and the fourth word is determined according to the position of the third word in the text content of the target type and the position of the fourth word in the text content of the target type. If the determined closeness meets a preset condition, a word matching the term to be searched is determined from the text content of the target type, and the determined word is displayed distinctively, thereby improving the matching degree between the distinctively displayed content and the term to be searched, and making the distinctively displayed content more concentrated, avoiding the problem that the distinctively displayed content is too scattered, resulting in a lack of emphasis, reducing the visual attention of the service object, and further reducing the search experience of the service object.
[0217] It should be noted that: Fig.12 The specific implementation details of steps S210 to S230 shown in FIG. Figure 2 Steps S210 to S230 shown are not described in detail.
[0218] In an exemplary embodiment, see Fig.13 , Fig.13 is a flowchart of an information processing method shown in another exemplary embodiment of the present application. The method can be applied to Figure 1 The implementation environment shown, which can be Figure 1 The terminal device 100 in the implementation environment shown in the figure may also be executed by Figure 1 The server 200 in the implementation environment shown in the figure may also execute the command. Figure 1 The terminal device 100 and the server 200 in the implementation environment shown in FIG. Fig.13 As shown, the information processing method may include steps S210-S230, steps S610-S620, steps S631-S632, and step S640, which are described in detail as follows:
[0219] Step S631, determining the distance between the third word and the fourth word according to the position of the third word in the target type of text content and the position of the fourth word in the target type of text content.
[0220] The distance between the third word and the fourth word is used to represent the distance between the third word and the fourth word, and it can be the number of characters between the third word and the fourth word.
[0221] The distance between the third word and the fourth word may be determined according to the positions of the third word and the fourth word in the text content of the target type.
[0222] Step S632: Determine the closeness between the third word and the fourth word according to the position importance of the third word and the fourth word and the distance between the third word and the fourth word.
[0223] Among them, position importance is used to represent the importance of the position. It should be understood that the closer the word is to the front, the higher the attention of the service object, and the more important it is. Therefore, the position importance of a word can be determined according to the front and back positions of the word, wherein the front and back positions of the word are proportional to the position importance, that is, the position importance of the beginning of the text is higher than that of the end of the text.
[0224] The position importance of the third word is determined according to the position of the third word in the text content of the target type.
[0225] The position importance of the fourth word is determined according to the position of the fourth word in the text content of the target type.
[0226] After determining the distance between the third word and the fourth word, the closeness between the third word and the fourth word can be determined by the position importance of the third word and the fourth word and the distance between the third word and the fourth word. In one example, the closeness between the third word and the fourth word can be determined according to the following method:
[0227]
[0228] Among them, tpi(t i , t j ) represents the closeness between the i-th word and the j-th word, that is, the closeness between the third word and the fourth word, Characterizes the position importance of the i-th word and the j-th word, which can be the importance of the reference position, and the reference position can be the position of the i-th word, the position of the j-th word, or the middle position between the i-th word and the j-th word; dist[t i ,t j ] represents the distance between the i-th word and the j-th word.
[0229] exist Fig.13 In the illustrated embodiment, the distance between the third word and the fourth word is first determined based on the position of the third word in the text content of the target type and the position of the fourth word in the text content of the target type, and then the closeness between the third word and the fourth word is determined based on the positional importance of the third word and the fourth word and the distance between the third word and the fourth word. This can improve the matching degree between the differentiated display content and the search terms, and make the differentiated display content more concentrated and located at a relatively forward position in the text content of the target type, thereby avoiding the problem that the differentiated display content is too dispersed, resulting in a lack of emphasis, reducing the visual attention of the service object, and further reducing the search experience of the service object.
[0230] It should be noted that: Fig.13 The specific implementation details of steps S210 to S230 shown in FIG. Figure 2 Steps S210 to S230 are shown. Fig.13 The specific implementation details of steps S610-S620 and step S640 shown in FIG. Fig.12 Steps S610 to S620 and step S640 are shown and will not be described in detail.
[0231] In another exemplary embodiment, Figure 2In step S240 of the illustrated embodiment, the process of distinguishing and displaying the words in the target type of text content that match the to-be-searched terms may also include steps 1 to 3, which are described in detail as follows:
[0232] Step 1: Find multiple words to be displayed that match the search term from the text content of the target type.
[0233] Step 2: determining the closeness between the multiple words to be displayed based on the positions of the multiple words to be displayed in the text content of the target type.
[0234] After finding multiple words to be displayed that match the search terms in the target type of text content, the closeness between the multiple words to be displayed can be determined. In an optional implementation, multiple word groups can be determined from the multiple words to be displayed, each word group includes two words that are adjacent in the target type of text content; and the closeness of each word group is determined; for example, assuming that the positions of the multiple words to be displayed in the target type of text content are A, B, C, and D, then the closeness between AB, the closeness between BC, and the closeness between CD are calculated; wherein, the specific method of calculating the closeness between two words can be found in the aforementioned step S630, which will not be repeated here.
[0235] Step three: if the closeness between multiple words to be displayed meets the specified conditions, the words matching the search terms in the target type of text content are displayed separately.
[0236] The specified conditions can be flexibly set according to actual needs. In an optional embodiment, the specified conditions include that the closeness of each word group is greater than the closeness threshold. Alternatively, the specified conditions include that there is at least one word group whose closeness is greater than the closeness threshold. Alternatively, the specified conditions include that the average closeness of multiple word groups is greater than the closeness threshold.
[0237] In this embodiment, if the closeness between multiple words to be displayed meets the specified conditions, then the distinctive display of the words in the text content of the target type that match the terms to be searched may include: distinctively displaying the word groups in the text content of the target type whose corresponding closeness is greater than the closeness threshold; or, based on the aforementioned steps S241-S245, distinctively displaying the words in the text content of the target type that match the terms to be searched.
[0238] In this exemplary embodiment, multiple words to be displayed that match the search terms are found from the text content of the target type, and the closeness between the multiple words to be displayed is determined based on their positions in the text content of the target type. If the closeness between the multiple words to be displayed meets specified conditions, the words in the text content of the target type that match the search terms are displayed distinctively, thereby avoiding the problem that the differentiated display content is too scattered, resulting in a lack of emphasis, reducing the visual attention of the service object, and further reducing the search experience of the service object.
[0239] In an exemplary embodiment, see Fig.14 , Fig.14 is a flowchart of an information processing method shown in another exemplary embodiment of the present application. The method can be applied to Figure 1 The implementation environment shown, which can be Figure 1 The terminal device 100 in the implementation environment shown in the figure may also be executed by Figure 1 The server 200 in the implementation environment shown in the figure may also execute the command. Figure 1 The terminal device 100 and the server 200 in the implementation environment shown in FIG. Fig.14 As shown, under the condition that the amount of target information includes multiple, the information processing method may include steps S210 to S270, which are described in detail as follows:
[0240] Step S250, determining the weight of each target information according to the matching strategy between the search term and each target information.
[0241] It should be noted that in step S210, target information matching the search terms can be obtained through different matching strategies. For example, as in the aforementioned steps S310-S320, a word subset corresponds to a matching strategy. In this embodiment, different weights are set for different matching strategies, and the specific setting method can be flexibly set according to actual needs. For example, assuming that multiple matching strategies include an intention matching strategy corresponding to an intention word subset, an entity word matching strategy corresponding to an entity word subset, a core word matching strategy corresponding to a core word subset, and other word matching strategies corresponding to other word subsets, since the content desired by the service object can be better found based on the intention label, entity word and core word, it can be set to the weight of the intention matching strategy> the weight of the entity word matching strategy> the weight of the core word matching strategy> the weight of the other word matching strategy. In an example, the weight of the intention matching strategy, the weight of the entity word matching strategy, the weight of the core word matching strategy, and the weight of the other word matching strategy can be set to 4, 2, 1.5, and 1, respectively.
[0242] In this embodiment, after obtaining multiple target information matching the term to be searched, the matching strategy between the term to be searched and each target information can be determined respectively, and the weight of each target information can be determined based on the matching strategy. For example, assuming that the weight of the intent matching strategy, the weight of the entity word matching strategy, the weight of the core word matching strategy, and the weight of other word matching strategies are set to 4, 2, 1.5, and 1 respectively, target information 1 is determined based on the intent matching strategy, and target information 2 is obtained based on the core word matching strategy, then the weight of target information 1 is 4, and the weight of target information 2 is 1.5.
[0243] Step S260, calculating the correlation between each target information and the term to be searched according to the weight of each target information and the correlation between various types of text content contained in each target information and the term to be searched.
[0244] In this embodiment, after determining the weight of each target information, the correlation between each target information and the to-be-searched term can be calculated based on the weight of each target information and the correlation between the various text contents contained in each target information and the to-be-searched term. The specific determination method can be flexibly set according to actual needs. In one example, the correlation between each target information and the to-be-searched term can be determined based on the following method:
[0245]
[0246] Among them, score(m) represents the correlation between the mth target information and the search term, strategy_weight m represents the weight of the m-th target information, and N represents the number of text contents contained in the m-th target information.
[0247] Step S270, sorting and displaying the multiple target information according to the correlation between each target information and the term to be searched.
[0248] In this embodiment, after determining the correlation between each target information in the multiple target information and the term to be searched, the multiple target information is sorted and displayed based on the determined correlation, wherein the order of sorting and the correlation may be positively correlated, that is, the greater the correlation between the target information and the term to be searched, the higher the display position of the target information. In other words, in the search result display page, the multiple target information is sorted and displayed according to the correlation between each target information and the term to be searched; and the words matching the term to be searched in the text content of the target type contained in each target information are displayed separately.
[0249] exist Fig.14In the illustrated embodiment, the weight of each target information can be determined based on the matching strategy between the term to be searched and each target information; the correlation between each target information and the term to be searched is calculated based on the weight of each target information and the correlation between various types of text content contained in each target information and the term to be searched; and based on the correlation between each target information and the term to be searched, multiple target information are sorted and displayed, thereby improving the accuracy of the correlation between the target information and the term to be searched, and displaying the target information searched based on a better matching strategy in a front position, thereby improving the accuracy of the search results.
[0250] It should be noted that: Fig.14 The specific implementation details of steps S210 to S240 shown in FIG. Figure 2 Steps S210 to S240 shown are not described in detail.
[0251] The following is a specific example of the information processing method of the present application. In this embodiment, the information processing method is applied to a video search scenario as an example. Fig.15 As shown, Fig.15 This is a specific implementation scenario of the information processing method in this embodiment, which may include an intent recognition module, a search service, and a database, wherein an inverted index file is stored in the database.
[0252] Among them, the information processing method mainly includes the offline index building process and the online search process.
[0253] During the offline index construction process, video information is recorded as video documents, and different types of text content are recorded as different index domains. For example, a video document includes multiple index domains such as video title, introduction, cast list, video tag, etc. The word segmentation system can be used to segment the different index domains included in the video documents in the video library to obtain word sets of different index domains, and create an inverted index file based on the word set, and store the created inverted index file in the database, where the inverted index file includes data such as words, word length, word importance, and video document id containing the word. These data can be stored in the inverted index file in a specified format, and each index domain has its corresponding inverted index.
[0254] The online search process may include steps 1 to 5, which are described in detail below:
[0255] Step 1: The search service requests the intent recognition module to obtain the intent label and word segmentation information of the query term.
[0256] The search service can obtain the search terms input by the service object, and initiate a request to the intent recognition module based on the search terms; after receiving the request, the intent recognition module can identify the intent of the search terms to obtain an intent label, use different segmentation granularities to segment the search terms to obtain segmentation information, and send the intent label and segmentation information to the search service, wherein the segmentation information includes words obtained by segmenting the search terms based on fine granularity (the number of words is less than a preset value), entity words in the words obtained by segmenting the search terms based on coarse granularity (the number of words is greater than a preset value), the importance of the words, the idf of the words, etc.
[0257] Step 2: The search service sends corresponding matching strategies in parallel based on the results returned by the intent recognition module.
[0258] Among them, after the search service obtains the intent label and word segmentation information, it divides the words in the word segmentation information into core words, entity words and other words, among which the core words are words with an importance greater than 0.4; then, multiple matching strategies are issued in parallel, among which the multiple matching strategies include: intent matching strategy generated based on intent label, entity word matching strategy generated based on entity words, core word matching strategy generated based on core words and other word matching strategy generated based on other words, among which, the priority of intent matching strategy>the priority of entity word matching strategy>the priority of entity word matching strategy>the priority of other word matching strategy, and the weight of intent matching strategy, entity word matching strategy, core word matching strategy and other word matching strategy are 4.0, 2.0, 1.5 and 1.0 respectively. In this way, video documents with high relevance to intent label, entity word and entity word can be placed in front of the video search result display page, thereby improving the matching degree between search results and search terms.
[0259] Step 3: Based on the issued matching strategy, the corresponding target video document is recalled from each index domain, and the correlation between the search term and different index domains in the target video document is calculated.
[0260] Among them, the inverted index file can be traversed according to the search terms corresponding to the matching strategy, so as to obtain a list of target video documents containing terms in the search term set, and then calculate the correlation between different index domains contained in the target video document and the search term set, wherein the specific calculation method of the correlation can be referred to the above record, which will not be repeated here. The search term set includes the intent label and the terms in the word segmentation information.
[0261] Step 4: According to the correlation between different index domains contained in the target video document and the set of words to be searched, a target index domain is determined from the target video document, and the target index domain is marked in red.
[0262] The red logo means changing the color of the words to red.
[0263] Among them, the index domain with the greatest correlation with the set of words to be searched and exceeding the correlation threshold can be determined from the index domains included in the target video document except the video title, and the determined index domain and the video title are used as the target index domain, and the words matching the core words, entity words, and intent tags in the target index domain are marked in red, and the words matching other words are found from the target index domain, and the first 5 words among the found words are marked in red.
[0264] In an optional implementation, if the target video document is recalled based on an intent matching strategy, the words in the video tag of the target video document that match the intent tag can be directly marked in red, thereby improving the search experience of the service object.
[0265] Step 5, calculating the relevance between each target video document and the search term, and displaying multiple target video documents in descending order of relevance.
[0266] The specific method of calculating the correlation between each target video document and the term to be searched can be found in the above records and will not be repeated here.
[0267] See also Fig.16 , Fig.16 FIG. 1 is a block diagram of an information processing device shown in an exemplary embodiment of the present application. Fig.16 As shown, the device comprises:
[0268] The acquisition module 1601 is configured to acquire target information matching the term to be searched, wherein the target information includes multiple types of text content;
[0269] A calculation module 1602 is configured to calculate the correlation between various types of text content included in the target information and the to-be-searched terms according to the weights of the various types of text content;
[0270] A selection module 1603, configured to select a target type of text content from multiple types of text content according to the correlation between each type of text content and the term to be searched;
[0271] The display module 1604 is configured to distinguish and display the words in the text content of the target type that match the search term.
[0272] In another exemplary embodiment, the calculation module 1602 includes:
[0273] A first processing module is configured to process the search terms to obtain the words to be searched;
[0274] A first calculation submodule is configured to calculate the initial correlation between various types of text content and the terms to be searched according to the terms to be searched;
[0275] The second calculation submodule is configured to calculate the correlation between each type of text content and the to-be-searched term based on the initial correlation between each type of text content and the to-be-searched term and the weights of multiple types of text content.
[0276] In another exemplary embodiment, the first computing submodule includes:
[0277] A first search module is configured to search for target words matching the searched words from various text contents;
[0278] The first determination module is configured to determine the initial correlation between each type of text content and the term to be searched according to the importance of the term to be searched and the importance of the target term matching the term to be searched in each type of text content.
[0279] In another exemplary embodiment, the number of target information includes a plurality; and the apparatus further includes:
[0280] A second determination module is configured to determine the weight of each target information according to a matching strategy between the search term and each target information;
[0281] A relevance calculation module, configured to calculate the relevance between each target information and the term to be searched according to the weight of each target information and the relevance between various text contents contained in each target information and the term to be searched;
[0282] The information display module is configured to sort and display multiple target information according to the correlation between each target information and the search term.
[0283] In another exemplary embodiment, the acquisition module 1601 includes:
[0284] A second processing module is configured to process the search terms to obtain a set of words to be searched;
[0285] A classification module, configured to classify the words in the search word set to obtain a plurality of word subsets;
[0286] The search module is configured to respectively obtain target information matching multiple word subsets, wherein one word subset corresponds to one matching strategy.
[0287] In another exemplary embodiment, the second processing module includes:
[0288] An identification module configured to identify the intent of the search term to be searched and obtain an intent label of the search term;
[0289] The word segmentation module is configured to perform word segmentation on the search terms and construct a set of words to be searched based on the intent tags and the words obtained by the word segmentation.
[0290] In another exemplary embodiment, the selection module 1603 includes:
[0291] A third determination module, configured to determine text content of a specified type and text content of other types except the specified type from the multiple types of text content;
[0292] A fourth determination module is configured to determine candidate types of text content from other types of text content based on the correlation between each type of text content and the term to be searched;
[0293] The fifth determination module is configured to use the candidate type of text content and the designated type of text content as the target type of text content.
[0294] In another exemplary embodiment, the fourth determining module includes:
[0295] A first determination submodule is configured to screen out, from other types of text content, text content of an initial candidate type whose corresponding correlation exceeds a correlation threshold value, based on the correlation between each type of text content and the term to be searched;
[0296] The second determination submodule is configured to select a set number of initial candidate types of text content as candidate types of text content in descending order of relevance.
[0297] In another exemplary embodiment, the display module 1604 includes:
[0298] A first type determination module is configured to determine a specified type of word from a set of words to be searched; the set of words to be searched includes words obtained by processing the search terms;
[0299] The first display submodule is configured to distinguish and display the words matching the designated type of words in the target type of text content.
[0300] In another exemplary embodiment, the display module 1604 further includes:
[0301] A second type determination module is configured to determine other types of words in the set of words to be searched except for the specified type of words;
[0302] A candidate word search module is configured to search for words that match other types of words from the target type of text content to obtain a candidate word set;
[0303] The second display submodule is configured to select a specified number of words from the candidate word set for distinguishing display.
[0304] In another exemplary embodiment, the display module 1604 includes:
[0305] An adjacent word determination module, configured to obtain a first word and a second word that are adjacent in position from the to-be-searched word;
[0306] A second search module is configured to search for a third word matching the first word and a fourth word matching the second word from the text content of the target type;
[0307] a closeness determination module configured to determine the closeness between the third word and the fourth word according to the position of the third word in the text content of the target type and the position of the fourth word in the text content of the target type;
[0308] The third display submodule is configured to determine words matching the to-be-searched terms from the text content of the target type if the determined closeness meets a preset condition, and to display the determined words distinctively.
[0309] In another exemplary embodiment, the compactness determination module includes:
[0310] a distance determination module configured to determine the distance between the third word and the fourth word according to the position of the third word in the text content of the target type and the position of the fourth word in the text content of the target type;
[0311] The closeness determination submodule is configured to determine the closeness between the third word and the fourth word according to the position importance of the third word and the fourth word and the distance between the third word and the fourth word.
[0312] It should be noted that the information processing device provided in the above embodiment and the information processing method provided in the above embodiment belong to the same concept, wherein the specific manner in which each module and unit performs operations has been described in detail in the method embodiment and will not be repeated here.
[0313] An embodiment of the present application also provides an electronic device, comprising: one or more processors; a storage device for storing one or more computer programs, when the one or more computer programs are executed by one or more processors, the electronic device implements the information processing method provided in the above-mentioned embodiments.
[0314] Fig.17 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application is shown. The electronic device may be Figure 1The terminal device or server shown.
[0315] It should be noted that Fig.17 The computer system 1700 of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.
[0316] like Fig.17 As shown, the computer system 1700 includes a central processing unit (CPU) 1701, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 1702 or a computer program loaded from a storage part 1708 to a random access memory (RAM) 1703, such as executing the information processing method described in the above embodiment. Various computer programs and data required for system operation are also stored in RAM 1703. CPU 1701, ROM 1702 and RAM 1703 are connected to each other via a bus 1704. An input / output (I / O) interface 1705 is also connected to the bus 1704.
[0317] In some embodiments, the following components are connected to the I / O interface 1705: an input section 1706 including a keyboard, a mouse, etc.; an output section 1707 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 1708 including a hard disk, etc.; and a communication section 1709 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 1709 performs communication processing via a network such as the Internet. A drive 1710 is also connected to the I / O interface 1705 as needed. A removable medium 1711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1710 as needed, so that a computer program read therefrom is installed into the storage section 1708 as needed.
[0318] In particular, according to an embodiment of the present application, a computer program that implements the information processing method can be carried on a computer-readable medium, and the computer program can be downloaded and installed from a network through the communication part 1709 and / or installed from a removable medium 1711.
[0319] It should be noted that the computer-readable medium shown in the embodiment of the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a computer program, which may be used by an instruction execution system, device or device or used in combination with it. The computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a computer-readable computer program is carried, and the propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer program contained in the computer-readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, etc., or any suitable combination of the foregoing.
[0320] The flowchart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present application. Wherein, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of the boxes in the block diagram or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and a computer program.
[0321] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. The names of these units do not, in some cases, constitute limitations on the units themselves.
[0322] Another aspect of the present application further provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor of an electronic device, the electronic device implements the information processing method as described above. The computer-readable storage medium may be included in the electronic device described in the above embodiment, or may exist independently without being assembled into the electronic device.
[0323] Another aspect of the present application further provides a computer program product, the computer program product comprising a computer program, and when the computer program is executed by a processor, the information processing method provided in each of the above embodiments is implemented. The computer program may be stored in a computer-readable storage medium.
[0324] The above content is only a preferred exemplary embodiment of the present application and is not intended to limit the implementation scheme of the present application. A person skilled in the art can easily make corresponding changes or modifications based on the main concept and spirit of the present application. Therefore, the scope of protection of the present application shall be based on the scope of protection required by the claims.
Claims
1. An information processing method, characterized in that: The method comprises: Acquire target information matching the term to be searched, wherein the target information includes multiple types of text content; Calculating the correlation between each type of text content included in the target information and the to-be-searched term according to the weights of the multiple types of text content; Selecting a target type of text content from the multiple types of text content according to the correlation between the various types of text content and the to-be-searched terms; Distinguishing and displaying the words in the text content of the target type that match the search terms; The step of displaying the words in the target type text content that match the to-be-searched terms in a differentiated manner includes: Finding a plurality of words to be displayed that match the search term from the text content of the target type; Determining the closeness between the multiple words to be displayed based on the positions of the multiple words to be displayed in the text content of the target type; If the closeness between the multiple words to be displayed meets the specified conditions, the words matching the to-be-searched terms in the text content of the target type are displayed separately.
2. The method according to claim 1, characterized in that The step of calculating the correlation between the various types of text content included in the target information and the to-be-searched terms according to the weights of the multiple types of text content includes: Processing the to-be-searched terms to obtain the to-be-searched words; Calculating the initial correlation between the various types of text content and the terms to be searched based on the terms to be searched; The correlation between the various types of text content and the to-be-searched terms is calculated based on the initial correlation between the various types of text content and the to-be-searched terms and the weights of the multiple types of text content.
3. The method according to claim 2, characterized in that The calculating the initial correlation between the various types of text content and the terms to be searched according to the terms to be searched includes: Finding target words matching the words to be searched from the various text contents; The initial correlation between the various types of text content and the terms to be searched is determined according to the importance of the terms to be searched and the importance of target terms in the various types of text content that match the terms to be searched.
4. The method according to claim 1, characterized in that The number of the target information includes multiple; the method also includes: Determining the weight of each target information according to a matching strategy between the to-be-searched term and each target information; Calculate the correlation between each target information and the term to be searched according to the weight of each target information and the correlation between various types of text content contained in each target information and the term to be searched; According to the correlation between each target information and the term to be searched, multiple target information are sorted and displayed.
5. The method according to claim 4, characterized in that Get target information that matches the search term, including: Processing the to-be-searched terms to obtain a to-be-searched word set; Classifying the words in the to-be-searched word set to obtain a plurality of word subsets; Target information matching the multiple word subsets is obtained respectively, wherein one word subset corresponds to one matching strategy.
6. The method according to claim 5, characterized in that The step of processing the to-be-searched terms to obtain a to-be-searched word set includes: Identify the intent of the term to be searched and obtain the intent label of the term to be searched; The to-be-searched terms are segmented, and the to-be-searched term set is constructed based on the intention tags and the terms obtained by the segmentation process.
7. The method according to claim 1, characterized in that The selecting a target type of text content from the multiple types of text content according to the correlation between the various types of text content and the to-be-searched terms includes: Determining text content of a specified type and text content of other types except the specified type from the multiple types of text content; Determining candidate types of text content from the other types of text content according to the correlation between the various types of text content and the terms to be searched; The text content of the candidate type and the text content of the designated type are used as the text content of the target type.
8. The method according to claim 7, characterized in that The step of determining candidate types of text content from the other types of text content according to the correlation between the various types of text content and the terms to be searched includes: According to the correlation between the various types of text content and the to-be-searched terms, selecting the initial candidate types of text content whose corresponding correlation exceeds the correlation threshold from the other types of text content; A set number of initial candidate types of text content are selected in descending order of relevance as the candidate type of text content.
9. The method according to claim 1, characterized in that The step of displaying the words matching the to-be-searched terms in the text content of the target type in a distinguishable manner further includes: Determining a specified type of word from a set of words to be searched; the set of words to be searched includes words obtained by processing the words to be searched; The words in the target type of text content that match the words of the specified type are displayed distinctively.
10. The method according to claim 9, characterized in that The step of displaying the words matching the to-be-searched terms in the text content of the target type in a distinguishable manner further includes: Determining other types of words in the to-be-searched word set except for the specified type of words; Searching for words matching the other types of words from the target type of text content to obtain a candidate word set; A specified number of words are selected from the candidate word set for distinguishing and displaying.
11. The method according to claim 1, characterized in that The step of searching the target type of text content for a plurality of words to be displayed that match the search term includes: Acquire a first word and a second word that are adjacent in position from the to-be-searched words; Searching for a third word matching the first word and a fourth word matching the second word from the text content of the target type; The determining the closeness between the multiple words to be displayed based on the positions of the multiple words to be displayed in the text content of the target type includes: Determining the closeness between the third word and the fourth word according to the position of the third word in the text content of the target type and the position of the fourth word in the text content of the target type; If the closeness between the multiple words to be displayed meets the specified condition, the words matching the to-be-searched terms in the text content of the target type are displayed distinctively, including: If the closeness between the third word and the fourth word meets a preset condition, a word matching the to-be-searched term is determined from the text content of the target type, and the determined words are displayed distinctively.
12. The method according to claim 11, characterized in that The determining the closeness between the third word and the fourth word according to the position of the third word in the text content of the target type and the position of the fourth word in the text content of the target type includes: Determining a distance between the third word and the fourth word according to a position of the third word in the text content of the target type and a position of the fourth word in the text content of the target type; The closeness between the third word and the fourth word is determined according to the position importance of the third word and the fourth word and the distance between the third word and the fourth word.
13. An information processing device, characterized in that: The device comprises: An acquisition module, configured to acquire target information matching the term to be searched, wherein the target information includes multiple types of text content; A calculation module, configured to calculate the correlation between the various types of text content included in the target information and the to-be-searched terms according to the weights of the multiple types of text content; A selection module configured to select a target type of text content from the multiple types of text content according to the correlation between the various types of text content and the to-be-searched terms; A display module configured to distinguish and display the words in the text content of the target type that match the to-be-searched terms; The step of displaying the words in the target type text content that match the to-be-searched terms in a differentiated manner includes: Finding a plurality of words to be displayed that match the search term from the text content of the target type; Determining the closeness between the multiple words to be displayed based on the positions of the multiple words to be displayed in the text content of the target type; If the closeness between the multiple words to be displayed meets the specified conditions, the words matching the to-be-searched terms in the text content of the target type are displayed separately.
14. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more computer programs, which, when executed by the one or more processors, enables the electronic device to implement the information processing method as described in any one of claims 1 to 12.
15. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor of an electronic device, the electronic device implements the information processing method described in any one of claims 1 to 12.
16. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the information processing method according to any one of claims 1 to 12 is implemented.
