Input associational word recommendation method and device, storage medium and electronic equipment

[0014] In order to make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be described clearly and completely in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. Based on the described embodiments of the present invention, all other embodiments obtained by a person of ordinary skill in the art without creative work shall fall within the protection scope of the present invention.

[0015] Unless otherwise defined, the technical terms or scientific terms used in the present invention should have the usual meanings understood by those with ordinary skills in the field to which the present invention belongs. The "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "include" and other similar words mean that the element or item appearing before the word encompasses the element or item listed after the word and its equivalents, but does not exclude other elements or items. Similar words such as "connected" or "connected" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "Down", "Left", "Right", etc. are only used to indicate the relative position relationship. When the absolute position of the described object changes, the relative position relationship may also change accordingly.

[0016] In order to keep the following description of the embodiments of the present invention clear and concise, the present invention omits detailed descriptions of known functions and known components.

[0017] The first embodiment of the present invention provides a recommendation method for inputting associated words. The process of the method is as follows: figure 1 As shown, steps S101 to S103 are included:

[0018] S101: Construct a set of related search terms of articles according to historical behavior data of a predetermined number of users.

[0019] When a user browses an article, it may be realized by searching the article through a certain search term, or it may be that after reading other articles, the article was viewed through the recommended content of other articles. Therefore, The embodiment of the present invention obtains the historical behavior data of the user related to the article, and then determines the related search term of the article.

[0020] The above-mentioned related search words can come from different words according to different historical behavior data. For example, when the historical behavior data is that an article is searched through the search term AA, when the article is browsed, the search term BB is entered in the search box, and another article searched by the search term BB is clicked, and then terminates operating. In this process, the related search term of a certain article can be the search term AA, the search term BB and the core word of another article.

[0021] When the aforementioned historical behavior data of many users is obtained, a large set of related search terms can be formed based on these historical behavior data, that is, a set of related search terms.

[0022] In specific implementation, the above steps need to be repeated, and then a set of corresponding related search terms can be constructed for all articles, and any one of these articles can be a predetermined article in the subsequent process.

[0023] S102: Detect whether a search word is received in the search box within a first predetermined time after browsing a predetermined article.

[0024] The trigger time point in the embodiment of the present invention is that after the user browses the predetermined article, it starts to detect whether the user will trigger the search box to perform the search operation. In specific implementation, the detection can be started after browsing a predetermined article and exiting from the browsing interface to the previous interface.

[0025] S103: When the search term is received, determine the input association word displayed in the input association word list according to the search term and the related search term set.

[0026] When the search term has been received, the associated search term that matches the search term can be found in the associated search term set, and then the associated search term is displayed as the input associated word in the input associated word list.

[0027] In specific implementation, some filtering rules can also be set so as to be able to recommend words that best match the user's search intent from the associated search word set to the user.

[0028] For example, determine all the related search words that match the search words in the related search term set to obtain the first input associated word set; select N related search terms in the first input associated word set according to the first predetermined rule, and Determine N associated search words as the input associated words displayed in the input associated word list; where N is the number of input associated words displayed at the first predetermined position in the input associated word list, and N is an integer greater than or equal to 1.

[0029] The above-mentioned first predetermined rule can be set according to specific needs, for example, it can be selected according to the sorting method of the highest number of occurrences when generating the related search term set, or selected from the search words that actually occur the search operation when generating the related search term set .

[0030] The embodiment of the present invention constructs a set of related search terms for the article in advance. When it is implemented, it detects whether the search box receives the search term after browsing the predetermined article. If it is received, it means that the user wants to search for a lot of content The probability is related to the article after reading. Therefore, the related search term that matches the received search term will be selected from the related search term set, and then the matched related search term will be displayed in the input association as the input association word Word list so that users can quickly implement search operations.

[0031] The embodiment of the present invention starts from the user’s search intention, and considers that if the user performs a search operation within a period of time after reading an article, the probability of searching for content related to the article is relatively high, so a set of related search terms is constructed. In this case, fast search can be realized by inputting associated words, which can truly predict what the user wants to input, and the user experience is better.

[0032] The second embodiment of the present invention provides a recommendation method for inputting associated words. The process of the method is as follows: figure 2 As shown, it includes steps S201 to S204:

[0033] S201: Construct a set of related search terms of a predetermined article according to historical behavior data of a predetermined number of users.

[0034] When a user browses an article, it may be realized by searching the article through a certain search term, or it may be that after reading other articles, the article was viewed through the recommended content of other articles. Therefore, The embodiment of the present invention obtains the historical behavior data of the user related to the article, and then determines the related search term of the article.

[0035] The above-mentioned related search words can come from different words according to different historical behavior data. For example, when the historical behavior data is that an article is searched through the search term AA, when the article is browsed, the search term BB is entered in the search box, and another article searched by the search term BB is clicked, and then terminates operating. In this process, the related search term of a certain article can be the search term AA, the search term BB and the core word of another article.

[0036] When the aforementioned historical behavior data of many users is obtained, a large set of related search terms can be formed based on these historical behavior data, that is, a set of related search terms.

[0037] In specific implementation, the behavior data of any user within the second time after browsing the article is obtained; the related search terms of the article are obtained according to the behavior data; the related search term set is generated based on all the related search words obtained based on the behavior data of the number of users.

[0038] For example, when historical behavior data includes clicks on articles, clicks on videos, and triggered search operations, when analyzing historical behavior data, it is necessary to obtain the core words and clicks of articles that are clicked within the second time after the user exits the article browsing interface. The core word of the video and the search word that triggers the search operation to get the related search word of the article based on the core word and search word.

[0039] During implementation, the above steps need to be repeated, and then a set of corresponding related search terms can be constructed for all articles. Any one of these articles can be a predetermined article in the subsequent process.

[0040] S202: Detect whether the currently browsed article is the Pth article continuously read by the user based on the same core word within a third predetermined time, where P is an integer greater than or equal to 2. If it is, the currently browsed article is determined as a predetermined article, and S203 is executed; otherwise, S202 is continued.

[0041] If the user has been reading articles with the same core word for a certain period of time, if a search operation occurs at this time, the most easily received search words in the search box are the words related to these articles, and the set of related search terms above is The words related to each article determined by each article.

[0042] In the embodiment of the present invention, the process of detecting whether the user continuously read the same core word article can further accurately determine the search intention of the user that may occur, and bring a better user experience to the user.

[0043] S203: Detect whether a search word is received in the search box within a first predetermined time after browsing a predetermined article.

[0044] The trigger time point in the embodiment of the present invention is that after the user browses the predetermined article, it starts to detect whether the user will trigger the search box to perform the search operation. In specific implementation, the detection can be started after browsing a predetermined article and exiting from the browsing interface to the previous interface.

[0045] S204: In the case of receiving the search term, determine the input association word displayed in the input association word list according to the search term and the related search term set.

[0046] When the search term has been received, the associated search term that matches the search term can be found in the associated search term set, and then the associated search term is displayed as the input associated word in the input associated word list.

[0047] In specific implementation, some filtering rules can also be set so as to be able to recommend words that best match the user's search intent from the associated search word set to the user.

[0048] For example, determine all the related search words that match the search words in the related search term set to obtain the first input associated word set; select N related search terms in the first input associated word set according to the first predetermined rule, and Determine N associated search words as the input associated words displayed in the input associated word list; where N is the number of input associated words displayed at the first predetermined position in the input associated word list, and N is an integer greater than or equal to 1.

[0049] The above-mentioned first predetermined rule can be set according to specific needs. For example, it can be selected according to the sorting method that counts the number of times when the related search word set is generated, or it can be selected from the search words that actually perform the search operation when the related search word set is generated. .

[0050] In order to reduce the poor user experience caused by the possible misjudgment of search intent, the embodiment of the present invention may also include the following process when determining the input associated words displayed in the input associated word list according to the search term and the associated search term set : Determine the second input association word set according to the search term; select M input association words in the second input association word set according to the second predetermined rule, and determine the M input association word column as the input displayed in the input association word list Associated words; where M is the number of input associated words displayed at the second predetermined position in the input associated word list, and M is an integer greater than or equal to 1. In the specific configuration, the first predetermined position is usually located before the second predetermined position, so as to make it easier for the user to see the input associated words that may be more in line with their search intent.

[0051] Through the above process, the common input association word set is integrated with the related search word set, so that the user can see the content he wants to search in the input association word list, and realize fast search to the greatest extent.

[0052] The following is a comparison and description with a specific example.

[0053] Existing methods: 1. The user browses a series of articles; 2. Go to the search box to enter a search term, and the input association word list is the input association word obtained based on the popularity of the whole network and the dictionary tree sorting method, which has no relation to the article. For example, if the article is "Liu Cixin Three-body Movie: Amazon Invests 1 Billion", when the user enters "Liu" in the search box, the list of associated words will display: Liu Yifei, Liu Shishi, Andy Lau, Liu Haoran.

[0054] Embodiments of the present invention: 1. A user browses a series of articles; 2. Goes to the search box and enters a search term. Entering the associated word will introduce information related to the previous article based on the popularity of the entire network and the dictionary tree sorting, namely A collection of related search terms, giving priority to the display of input associated words that are related to both the article and the current search intent. For example, if the article is "Liu Cixin Three-body Movie: Amazon Invests 1 Billion", when the user enters "Liu" in the search box, the list of associated words will display: Liu Xinci, Liu Yifei, Liu Shishi, Andy Lau.

[0055] The embodiment of the present invention constructs a set of related search terms for the article in advance. When it is implemented, it detects whether the search box receives the search term after browsing the predetermined article. If it is received, it means that the user wants to search for a lot of content The probability is related to the article after reading. Therefore, the related search term that matches the received search term will be selected from the related search term set, and then the matched related search term will be displayed in the input association as the input association word Word list so that users can quickly implement search operations.

[0056] The embodiment of the present invention starts from the user’s search intention, and considers that if the user performs a search operation within a period of time after reading an article, the probability of searching for content related to the article is relatively high, so a set of related search terms is constructed. In this case, fast search can be realized by inputting associated words, which can truly predict what the user wants to input, and the user experience is better.

[0057] The third embodiment of the present invention provides a recommendation device for inputting associative words. The structure of the device is shown as follows: image 3 Shown, including:

[0058] The construction module 10 is used to construct a set of related search terms of the article according to the historical behavior data of a predetermined number of users; the detection module 20, coupled with the construction module 10, is used to detect whether the search box is received within the first predetermined time after browsing the predetermined article To the search term; the determination module 30, coupled with the detection module 20, is used to determine the input association word displayed in the input association word list according to the search term and the associated search term set when the search term is received.

[0059] When a user browses an article, it may be realized by searching the article through a certain search term, or it may be that after reading other articles, the article was viewed through the recommended content of other articles. Therefore, The embodiment of the present invention obtains the historical behavior data of the user related to the article, and then determines the related search term of the article.

[0060] The above-mentioned related search words can come from different words according to different historical behavior data. For example, when the historical behavior data is that an article is searched through the search term AA, when the article is browsed, the search term BB is entered in the search box, and another article searched by the search term BB is clicked, and then terminates operating. In this process, the related search term of a certain article can be the search term AA, the search term BB and the core word of another article.

[0061] When the aforementioned historical behavior data of many users is obtained, a large set of related search terms can be formed based on these historical behavior data, that is, a set of related search terms.

[0062] In a specific implementation, the construction module 10 needs to repeat the work, and then a set of corresponding related search terms can be constructed for all the articles, and any one of these articles can be a predetermined article in the subsequent process.

[0063] The building module is specifically used to: obtain the behavior data of any user within the second predetermined time after browsing the article; obtain the related search terms of the article according to the behavior data; generate based on all the related search terms obtained based on the behavior data of a predetermined number of users A collection of related search terms. Specifically, the core word of the article clicked by the predetermined user within the second predetermined time after browsing the predetermined article, the core word of the clicked video, and the search word that triggers the search operation are obtained to obtain the related search of the predetermined article according to the core word and the search word. word.

[0064] The trigger time point in the embodiment of the present invention is that after the user browses the predetermined article, it starts to detect whether the user will trigger the search box to perform the search operation. In specific implementation, the detection can be started after browsing a predetermined article and exiting from the browsing interface to the previous interface.

[0065] The aforementioned predetermined article may be the Pth article that the user reads continuously based on the same core word within the third predetermined time, and the detection module is also used to detect whether the currently browsed article is the user continuously based on the same core word within the third predetermined time Read the Pth article, and if the currently browsed article is the Pth article, the currently browsed article is determined as the predetermined article, where P is an integer greater than or equal to 2.

[0066] When the search term has been received, the associated search term that matches the search term can be found in the associated search term set, and then the associated search term is displayed as the input associated word in the input associated word list.

[0067] In specific implementation, some filtering rules can also be set so as to be able to recommend words that best match the user's search intent from the associated search word set to the user.

[0068] The determining module is specifically used to: determine all related search words matching the search word in the related search word set to obtain the first input associated word set; select N from the first input associated word set according to the first predetermined rule Associate search terms, and determine N associated search terms as input associated words displayed in the input associated word list; where N is the number of input associated words displayed at the first predetermined position in the input associated word list, and N is greater than or equal to An integer of 1.

[0069] The above-mentioned first predetermined rule can be set according to specific needs. For example, it can be selected according to the sorting method that counts the number of times when the related search word set is generated, or it can be selected from the search words that actually perform the search operation when the related search word set is generated. .

[0070] In order to reduce the poor user experience caused by the possible misjudgment of search intent, the determination module is specifically used to: determine the second input associated word set according to the search term; in the second input associated word set according to the second predetermined rule Select M input association words in the, and determine the M input association words column as the input association words displayed in the input association word list; where M is the number of input association words displayed in the second predetermined position in the input association word list, M is an integer greater than or equal to 1. In the specific configuration, the first predetermined position is usually located before the second predetermined position, so as to make it easier for the user to see the input associated words that may be more in line with their search intent.

[0071] Through the above process, the common input association word set is integrated with the related search word set, so that the user can see the content he wants to search in the input association word list, and realize fast search to the greatest extent.

[0072] The embodiment of the present invention constructs a set of related search terms for the article in advance. When it is implemented, it detects whether the search box receives the search term after browsing the predetermined article. If it is received, it means that the user wants to search for a lot of content The probability is related to the article after reading. Therefore, the related search term that matches the received search term will be selected from the related search term set, and then the matched related search term will be displayed in the input association as the input association word Word list so that users can quickly implement search operations.

[0073] The embodiment of the present invention starts from the user’s search intention, and considers that if the user performs a search operation within a period of time after reading an article, the probability of searching for content related to the article is relatively high, so a set of related search terms is constructed. In this case, fast search can be realized by inputting associated words, which can truly predict what the user wants to input, and the user experience is better.

[0074] The fourth embodiment of the present invention provides a storage medium storing a computer program, and when the computer program is executed by a processor, the method provided by any embodiment of the present invention is implemented, as follows: Steps S1 to S3:

[0075] S1, constructing a set of related search terms of articles according to historical behavior data of a predetermined number of users;

[0076] S2, detecting whether the search box receives the search term within the first predetermined time after browsing the predetermined article;

[0077] S3, in the case of receiving the search term, determine the input association word displayed in the input association word list according to the search term and the associated search term set.

[0078] The foregoing predetermined article may be the Pth article with the same core word that the user reads continuously within the third predetermined time, and P is an integer greater than or equal to 2.

[0079] When the computer program is executed by the processor to determine the input associated word displayed in the input associated word list according to the search term and the associated search term set, the processor specifically executes the following steps: determine the associated search term set that matches the search term All associated search words to obtain the first input associated word set; according to the first predetermined rule, select N associated search words from the first input associated word set, and determine the N associated search words as displayed in the input associated word list Input associated words; where N is the number of input associated words displayed at the first predetermined position in the input associated word list, and N is an integer greater than or equal to 1.

[0080] When the computer program is executed by the processor to determine the input association word displayed in the input association word list according to the search term and the associated search term set, the processor also executes the following steps: determining the second input association word set according to the search term; The second predetermined rule selects M input association words in the second input association word set, and determines the M input association word columns as the input association words displayed in the input association word list; where M is the first input association word list 2. The number of input association words displayed at a predetermined position, where M is an integer greater than or equal to 1.

[0081] When the computer program is executed by the processor to construct a set of related search terms of the article based on the historical behavior data of a predetermined number of users, the processor further specifically executes the following steps: Obtain the behavior data of any user within a second predetermined time after browsing the article ; Obtain the related search terms of the article according to the behavior data; generate a related search term set based on all the related search words obtained based on the behavior data of a predetermined number of users.

[0082] Wherein, the first predetermined position is located before the second predetermined position. Related search terms include at least one of the following: core words of the clicked article, core words of the clicked video, and search words that trigger a search operation.

[0083] The predetermined article is determined by the following method: detecting whether the currently browsed article is the Pth article continuously read by the user based on the same core word within the third predetermined time, where P is an integer greater than or equal to 2; the currently viewed article is In the case of article P, the article currently browsed is determined as a predetermined article.

[0084] The embodiment of the present invention starts from the user’s search intention, and considers that if the user performs a search operation within a period of time after reading an article, the probability of searching for content related to the article is relatively high, so a set of related search terms is constructed. In this case, fast search can be realized by inputting associated words, which can truly predict what the user wants to input, and the user experience is better.

[0085] Optionally, in this embodiment, the foregoing storage medium may include, but is not limited to: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic Various media that can store program codes, such as discs or optical discs. Optionally, in this embodiment, the processor executes the method steps described in the foregoing embodiment according to the program code stored in the storage medium. Optionally, for specific examples in this embodiment, reference may be made to the examples described in the above-mentioned embodiments and optional implementation manners, and details are not described herein again in this embodiment. Obviously, those skilled in the art should understand that the above-mentioned modules or steps of the present invention can be implemented by a general computing device, and they can be concentrated on a single computing device or distributed on a network composed of multiple computing devices. Above, alternatively, they can be implemented with program codes executable by the computing device, so that they can be stored in the storage device for execution by the computing device, and in some cases, can be executed in a different order than here. Perform the steps shown or described, or fabricate them into individual integrated circuit modules separately, or fabricate multiple modules or steps of them into a single integrated circuit module for implementation. In this way, the present invention is not limited to any specific combination of hardware and software.

[0086] The fifth embodiment of the present invention provides an electronic device, such as Figure 4 As shown, the electronic device includes at least a memory 901 and a processor 902. The memory 901 stores a computer program. When the processor 902 executes the computer program on the memory 901, the method provided by any embodiment of the present invention is implemented. The program steps are as follows S11 to S13:

[0087] S11, constructing a collection of related search terms of articles according to historical behavior data of a predetermined number of users;

[0088] S12, detecting whether the search box receives the search term within the first predetermined time after exiting from the browsing interface of the predetermined article;

[0089] S13: In the case of receiving the search term, determine the input association word displayed in the input association word list according to the search term and the associated search term set.

[0090] When the processor 902 executes the computer program stored on the memory 901 for determining the input associated word displayed in the associated search word list based on the search term and the associated search term set, it specifically executes the following computer program: All related search words that match to obtain the first input associated word set; select N related search words from the first input associated word set according to the first predetermined rule, and determine the N related search words as the input associated word list The input associated words displayed in, where N is the number of input associated words displayed at the first predetermined position in the input associated word list, and N is an integer greater than or equal to 1.

[0091] When the processor 902 executes the computer program stored on the memory 901 for determining the input association word displayed in the input association word list based on the search term and the associated search term set, it specifically executes the following computer program: determining the second input association word set according to the search term ; According to the second predetermined rule, select M input association words in the second input association word set, and determine the M input association word columns as the input association words displayed in the input association word list; where M is the input association word list The number of input association words displayed in the second predetermined position in the middle, M is an integer greater than or equal to 1.

[0092] When the processor 902 executes the computer program stored on the memory 901 for constructing an article's associated search term set based on the historical behavior data of a predetermined number of users, the processor 902 specifically executes the following computer program: obtain any user's information within a second predetermined time after browsing the article Behavioral data; obtain the related search terms of the article according to the behavior data; generate a related search term set based on all the related search terms obtained based on the behavior data of a predetermined number of users.

[0093] When the processor 902 executes the computer program stored on the memory 901, it also executes the following computer program for determining a predetermined article: detecting whether the currently browsed article is the Pth article continuously read by the user based on the same core word within the third predetermined time, Where P is an integer greater than or equal to 2; in the case that the currently browsed article is the Pth article, the currently browsed article is determined as the predetermined article.

[0094] Wherein, the first predetermined position is located before the second predetermined position. Related search terms include at least one of the following: core words of the clicked article, core words of the clicked video, and search words that trigger a search operation.

[0095] The embodiment of the present invention starts from the user’s search intention, and considers that if the user performs a search operation within a period of time after reading an article, the probability of searching for content related to the article is relatively high, so a set of related search terms is constructed. In this case, fast search can be realized by inputting associated words, which can truly predict what the user wants to input, and the user experience is better.

[0096] In addition, although the exemplary embodiments have been described herein, the scope includes any and all implementations with equivalent elements, modifications, omissions, combinations (for example, crossover schemes of various embodiments), adaptations, or changes based on the present invention example. The elements in the claims will be interpreted broadly based on the language adopted in the claims, and are not limited to the examples described in this specification or during the implementation of the present disclosure, and the examples will be interpreted as non-exclusive. Therefore, this specification and examples are intended to be regarded as examples only, and the true scope and spirit are indicated by the following claims and the full scope of their equivalents.

[0097] The above description is intended to be illustrative and not restrictive. For example, the above examples (or one or more of them) can be used in combination with each other. For example, a person of ordinary skill in the art may use other embodiments when reading the above description. In addition, in the foregoing specific embodiments, various features may be grouped together to simplify the present invention. This should not be construed as an intent that an unclaimed disclosed feature is necessary for any claim. On the contrary, the subject matter of the present invention may be less than all the features of a specific disclosed embodiment. Thus, the following claims are incorporated herein as examples or embodiments in the detailed description, wherein each claim independently serves as a separate embodiment, and it is considered that these embodiments can be combined with each other in various combinations or permutations. The scope of the present invention should be determined with reference to the appended claims and the full scope of equivalents entitled by these claims.

[0098] A number of embodiments of the present invention have been described in detail above, but the present invention is not limited to these specific embodiments. Those skilled in the art can make many variations and modified embodiments based on the concept of the present invention. These variations and modifications All should fall within the scope of protection claimed by the present invention.