CN116932906A - Search term pushing method, device, equipment and storage medium - Google Patents

Abstract

The application provides a search term pushing method, a device, equipment and a storage medium, wherein the method comprises the following steps: acquiring a historical query statement and a historical browsing record of a first user, and generating a first search word according to the historical query statement and the historical browsing record; constructing a first user portrait of the first user, acquiring a second user portrait similar to the first user portrait, and generating a second search term according to a historical query record of the second user corresponding to the second user portrait; generating a third search word according to the popular search word in the website at the current moment; merging and sequencing the first search word, the second search word and the third search word to obtain a first sequence; and pushing the search word according to the first sequence. The application has the technical effects that: and the search words are pushed in a personalized and differentiated mode, so that the pushing result is personalized and differentiated, and the user experience is improved.

Description

Search term pushing method, device, equipment and storage medium

Technical Field

The application relates to the technical field of data analysis, in particular to a search word pushing method, a device, equipment and a storage medium.

Background

In patent websites, due to the development of technology and the continuous application of patents, users need to spend a long time browsing and screening a large amount of patent information when inquiring related information, and the efficiency is low. In order to facilitate users to find information needed by the users more easily, in the prior art, a classification pushing technology is generally adopted, and patent information is sent to the users by classifying patent texts according to technical fields, types and the like.

By adopting the technology, the time spent by a user in inquiring related information can be reduced, but because of the difference among the individuals of the user, the classified pushing can not be performed according to the difference among the individuals of the user, and the pushing result lacks individuation and differentiation, so that the user experience is influenced.

Therefore, the application provides a search word pushing method for pushing search words in personalized and differentiated mode, so that pushing results are personalized and differentiated, and user experience is improved.

Disclosure of Invention

The application provides a search term pushing method, device, equipment and storage medium, which are used for personalized and differentiated pushing, so that pushing results are personalized and differentiated, and user experience is improved.

In a first aspect, the present application provides a search term pushing method, where the method includes: acquiring a historical query statement and a historical browsing record of a first user, and generating a first search word according to the historical query statement and the historical browsing record; constructing a first user portrait of the first user, acquiring a second user portrait similar to the first user portrait, and generating a second search term according to a historical query record of the second user corresponding to the second user portrait; generating a third search word according to the popular search word in the website at the current moment; merging and sequencing the first search word, the second search word and the third search word to obtain a first sequence; and pushing the search word according to the first sequence.

By adopting the technical scheme, a first search word is generated according to the historical query statement and the historical browsing record of the user; constructing a first user portrait, acquiring a second user portrait similar to the first user portrait, and generating a second search term according to a history query record of a second user corresponding to the second user portrait; then generating third search words according to the popular search words in the website at the current moment; and pushing the search word according to the generated first sequence and the first sequence according to the search word with the three dimensions. In summary, by combining the multidimensional information to push the information, the final pushing result is more accurate, and personalized and differentiated pushing is performed according to the differences among different users, so that the pushing result has personalized and differentiated properties, and the user experience is improved.

Optionally, the first search word includes a first sub-search word, and the generating the first search word according to the historical query statement and the historical browsing record includes: extracting keywords in the historical query sentences and the historical browsing records, and classifying the keywords to obtain a plurality of keyword sets; sorting the plurality of keyword sets according to the number of keywords in the plurality of keyword sets, and generating keyword set sorting; and generating a first sub-search word according to the keyword set ordering.

By adopting the technical scheme, the first search word comprises the first sub-search word, the keywords are classified by extracting the keywords in the historical query sentences and the historical browsing records, a keyword set is obtained, the keyword sets are ordered according to the number of the keywords in the keyword sets, and the first sub-search word is generated according to the ordering of the keyword sets. The method can acquire the first sub-search word more accurately, and is convenient for improving the accuracy of the pushed search word when the search word is pushed by combining the multidimensional information.

Optionally, the first search word includes a second sub-search word, and the generating the first search word according to the historical query statement and the historical browsing record includes: analyzing the historical query sentences and the historical browsing records of the user, and predicting the search intention of the user; and generating a second sub-search word according to the search intention of the user.

By adopting the technical scheme, the first search word comprises the second search word, the search intention of the user can be predicted according to the historical query statement and the historical browsing record, and the second sub-search word can be generated according to the search intention. The first search word comprises a first search word and a second search word, and searching is performed through multiple dimensions, so that the obtained first search word is more comprehensive, and the finally pushed first search word has diversity.

Optionally, the merging and sorting the first search word, the second search word and the third search word to obtain a first sequence includes: combining the first search word, the second search word and the third search word to obtain a search word set; acquiring a historical query record of the user, and counting one or more search words with highest user search frequency in the historical query record of the user to generate keywords; comparing the keywords with all search words in the search word set to obtain the similarity of all the search words, and sorting all the search words according to the similarity of all the search words to obtain a first sequence.

By adopting the technical scheme, the first search word, the second search word and the third search word are combined and ordered, then the search word pushing is performed according to the first sequence generated according to the search words with the three dimensions. In summary, by combining the multidimensional information to push the information, the final pushing result is more accurate, and personalized and differentiated pushing is performed according to the differences among different users, so that the pushing result has personalized and differentiated properties, and the user experience is improved.

Optionally, the pushing the search term according to the first sequence includes: acquiring the total number of search words in the first sequence; if the total number of the search words in the first sequence is lower than the preset number, the first sequence is directly pushed.

By adopting the technical scheme, when the total number of the search words in the first sequence is lower than the preset number, the first sequence is directly pushed. Because the number of the search words may be multiple, the number of the search words needs to be reduced on the premise of meeting the personalized and differentiated pushing results, and the situation that a great amount of time is required to be spent when users screen the required content due to excessive pushing contents is avoided.

Optionally, after the obtaining the total number of the search terms in the first sequence, the method further includes: if the total number of the search words in the first sequence exceeds the preset number, eliminating the search words in the part exceeding the preset number in the first sequence to obtain a first sequence to be pushed; acquiring the type of the search word in the first sequence to be pushed; if a plurality of search words with the same type exist in the first sequence to be pushed, only the search word with the forefront sequence in the first sequence to be pushed is reserved, and the rest one or more search words with the same type are removed to obtain a second sequence to be pushed; calculating the difference between the total number of search words in the first sequence to be pushed and the second sequence to be pushed to obtain a first number, and extracting the search words corresponding to the first number in the first sequence to the second sequence to be pushed to obtain a final push sequence; pushing the final push sequence.

Through adopting above-mentioned technical scheme, when the search term is too much, the system can carry out automatic adjustment, and when guaranteeing that the number of the search term of final propelling movement can not surpass preset quantity, also can guarantee the variety and the coverage of search term for the final propelling movement result is more accurate, accords with the user more needs.

Optionally, after pushing the search term according to the first sequence, the method further includes: acquiring feedback information filled by the user, wherein the feedback information comprises positive feedback information and negative feedback information; if the feedback information filled by the user is the positive feedback information, optimizing the first sequence to obtain a second sequence; and if the feedback information filled in by the user is the negative feedback information, the first sequence is adjusted to obtain a third sequence.

By adopting the technical scheme, after different search words are pushed to different users, a user feedback mechanism is set, feedback information comprises positive feedback information and negative feedback information, a first sequence is optimized according to the positive feedback information, and finally pushed search words are continuously optimized; and adjusting the first sequence according to the negative feedback information, so that the final pushing result meets the requirements of users, and the user experience is improved.

In a second aspect, the present application provides a search term pushing device, the device comprising: the device comprises a first generation module, a second generation module, a third generation module, an output module and a pushing module; the first generation module is used for acquiring historical query sentences and historical browsing records of a first user and generating first search words according to the historical query sentences and the historical browsing records; the second generation module is used for constructing a first user portrait of the first user, acquiring a second user portrait similar to the first user portrait, and generating a second search word according to a history query record of the second user corresponding to the second user portrait; the third generation module is used for generating third search words according to the popular search words in the website at the current moment; the output module is used for merging and sequencing the first search word, the second search word and the third search word to obtain a first sequence; the pushing module is used for pushing the search word according to the first sequence.

By adopting the technical scheme, a first search word is generated according to the historical query statement and the historical browsing record of the user; constructing a first user portrait, acquiring a second user portrait similar to the first user portrait, and generating a second search term according to a history query record of a second user corresponding to the second user portrait; then generating third search words according to the popular search words in the website at the current moment; and pushing the search word according to the generated first sequence and the first sequence according to the search word with the three dimensions. In summary, by combining the multidimensional information to push the information, the final pushing result is more accurate, and personalized and differentiated pushing is performed according to the differences among different users, so that the pushing result has personalized and differentiated properties, and the user experience is improved.

In a third aspect, the present application provides an electronic device, which adopts the following technical scheme: the search term pushing system comprises a processor, a memory, a user interface and a network interface, wherein the memory is used for storing instructions, the user interface and the network interface are used for communicating with other devices, and the processor is used for executing the instructions stored in the memory so as to enable the electronic device to execute a computer program of any search term pushing method.

In a fourth aspect, the present application provides a computer readable storage medium, which adopts the following technical solutions: a computer program capable of being loaded by a processor and executing any one of the search term pushing methods described above is stored.

In summary, the present application includes at least one of the following beneficial technical effects:

1. the information pushing is performed by combining the multidimensional information, so that the final pushing result is more accurate, personalized and differentiated pushing is performed according to the difference between different users, the pushing result is personalized and differentiated, and the user experience is improved;

2. after different search words are pushed for different users, a user feedback mechanism is set, feedback information comprises positive feedback information and negative feedback information, a first sequence is optimized according to the positive feedback information, and finally the pushed search words are continuously optimized; and adjusting the first sequence according to the negative feedback information, so that the final pushing result meets the requirements of users, and the user experience is improved.

Drawings

FIG. 1 is a flow chart of an implementation of one embodiment provided by an embodiment of the present application;

FIG. 2 is a schematic flow chart of a search term pushing method according to an embodiment of the present application;

FIG. 3 is a schematic structural diagram of a search term pushing device according to an embodiment of the present application;

fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Reference numerals illustrate: 1. a first generation module; 2. a second generation module; 3. a third generation module; 4. an output module; 5. a pushing module; 1000. an electronic device; 1001. a processor; 1002. a communication bus; 1003. a user interface; 1004. a network interface; 1005. a memory.

Detailed Description

In order to make the technical solutions in the present specification better understood by those skilled in the art, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is obvious that the described embodiments are only some embodiments of the present application, not all embodiments.

In describing embodiments of the present application, words such as "exemplary," "such as" or "for example" are used to mean serving as examples, illustrations or explanations. Any embodiment or design described herein as "illustrative," "such as" or "for example" is not necessarily to be construed as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "illustratively," "such as" or "for example," etc., is intended to present related concepts in a concrete fashion.

The execution subject of the present application includes, but is not limited to, computer devices, which can be applied to patent websites and other search apps, video apps, etc.; for convenience of description, the patent website is taken as an example for illustration, in the application, the application scenes are all defaults to the patent website under the condition that no special description exists, and other application scenes can refer to the patent website.

In patent websites, due to the development of technology and the continuous application of patents, users need to spend a long time browsing and screening a large amount of patent information when inquiring related information, wherein the patent information comprises patent documents, companies corresponding to the patent documents and mushroom information obtained by the patent documents, and redundant description is not made here; in view of the above problems, the present application provides a search term pushing method, which can provide some search terms or topics possibly related to the user's search according to the user's search history and the inputted keywords, so as to help the user to find the information they want more quickly; and users may have an uncertainty about what to search on a patent web site or may not know how to express their needs, by providing some search terms that may be relevant, users may more easily find the information they need and do not spend more time and effort searching.

As shown in fig. 1, fig. 1 is a flowchart of an implementation of an embodiment of the present application. The application can be understood mainly as two phases, recall and sort. In the recall stage, the system screens out a part of data which is possibly related from the massive data according to the input of the user and the context information, wherein the context information can be understood as the frequency of occurrence of the same search word or the search word of the same type in the history inquiry; in the sorting stage, after a part of data which is possibly related is screened out from the mass data, the recalled data is required to be sorted, and the most related data is arranged in front, so that a user can find out the required information more quickly.

It should be noted that, the mass data may be obtained from a plurality of data sources, where the data sources include hive, es, redis, mysql; hive, es, redis, mysql is a common data source and data storage technology, and these data sources and storage technologies can be selected and used in combination according to requirements and scenes in practical application so as to meet different data processing and storage requirements, and can also be used for saving the behavior history of a user and various types of content data, obtaining recall results through a recall process, and obtaining the final result of predicting the user to want to search through a sequencing process.

Fig. 2 is a schematic flow chart of a search term pushing method provided by an embodiment of the present application. It should be understood that, although the steps in the flowchart of fig. 2 are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence as indicated by the arrows; the steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders; and at least some of the steps in fig. 1 may include a plurality of sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor does the order in which the sub-steps or stages are performed necessarily occur in sequence, but may be performed alternately or alternately with at least some of the other steps or sub-steps of other steps.

The application discloses a search term pushing method, which comprises S101-S105 as shown in FIG. 2.

S101, acquiring historical query sentences and historical browsing records of a first user, and generating a first search word according to the historical query sentences and the historical browsing records.

In one example, the first user may be a user who is currently pushing a search term, where when obtaining a history query sentence and a history browsing record, the first user may obtain the history query sentence and the history browsing record within a preset duration, where the preset duration may be within half a year or within one year; based on the obtained historical query sentences and the historical browsing records, search behavior and interest preferences of the user can be obtained, and then some search words possibly related to the user, namely first search words, are provided.

S102, constructing a first user portrait of the first user, acquiring a second user portrait similar to the first user portrait, and generating a second search term according to a history query record of the second user corresponding to the second user portrait.

In one example, a user representation refers to a model of user characteristics that comprehensively analyze and describe a user. The system can construct different user portraits according to different users by collecting, sorting and analyzing the personal information, behavior data, interests and hobbies and other multidimensional data of the users to form comprehensive cognition and description of the users. The first user portrait is a user portrait corresponding to the search word to be pushed currently, the second user portrait is a user portrait similar to the first user portrait, and one or more second user portraits can exist; and after the second user portrait is obtained, acquiring a history query record of a user corresponding to the second user portrait, obtaining search behavior and interest preference of the user corresponding to the second user portrait, and generating push words, namely second search words.

S103, generating a third search word according to the popular search word in the website at the current moment.

In one example, the popular search term in the website at the current moment can be understood as the popular search term or popular event in the website at the current moment, or a vocabulary automatically generated by a system when the information focused by the user is updated, and the popular vocabulary is summarized to obtain the third search term.

S104, merging the first search word, the second search word and the third search word, and then sequencing to obtain a first sequence.

In one example, after the first, second, and third search terms are obtained, all of the obtained search terms are combined. It should be noted that, the number of push words included in the first search word, the second search word and the third search word generated by different users is different, so that the user can set the number of push words by himself, for example, the user can set the number of search words included in the first search word by himself according to actual situations, the number of search words included in the first search word cannot exceed five, and after the first search word, the second search word and the third search word are combined, the total number of search words cannot exceed ten, which is, of course, specifically analyzed. After the first search word, the second search word and the third search word are combined, all the keywords need to be ranked, and the ranking is achieved through vectorization of the words, through similarity comparison between all the search words and the search words commonly used by users, the search words are ranked according to the similarity, and the higher the similarity is, the earlier the ranking is.

Similarity is obtained by using cosine similarity, which is a common text similarity calculation method that measures the similarity between two vectors by calculating the cosine value of the angle between them. The cosine similarity has a value ranging from-1 to 1, the closer the value is to 1 the more similar the two vectors are, the closer the value is to-1 the more dissimilar the two vectors are, and the value is 0 the two vectors are completely uncorrelated. The cosine similarity calculation formula is as follows: cosine_similarity (a, B) = (a.b)/(|a|b|). Of course, the calculation may also be performed using Jaccard similarity, which is a common text similarity calculation method that measures the similarity between two sets by calculating the ratio between their intersection and union. The Jaccard similarity calculation formula is as follows: j (A, B) = |A n B|/|A U B| wherein A and B respectively represent two sets, |A| and|B| respectively represent the number of elements of A and B, n represents the intersection of the two sets, and u represents the union of the two sets.

And after calculating the similarity of all the search words, sorting according to the similarity of each search word, wherein the higher the similarity is, the earlier the sorting is, the lower the similarity is, and after the sorting is, the sorting of all the search words is carried out, so that the first sequence is obtained.

S105, pushing search words according to the first sequence.

In one example, the number of search terms pushed varies from user to user, and too many pushes may result in the user spending a lot of time and effort in screening and knowing relevant information; too little pushing may also cause the user to miss important information; therefore, when relevant information is pushed, a user can select the number of the pushed search words according to the actual situation of the user and the actual needs.

It should be noted that, the pushed words not only consider the similarity, but also need to ensure the number of the final search results, the accuracy of the search results, and the diversity and coverage of the search results, where the diversity may include but is not limited to companies, patents, policies, etc., and the user may set itself according to the actual situation of the user, so that excessive details are not needed.

The first search word comprises a first sub-search word, and the first search word is generated according to the historical query statement and the historical browsing record, and comprises the following steps: extracting keywords in the historical query sentences and the historical browsing records, and classifying the keywords to obtain a plurality of keyword sets; sorting the plurality of keyword sets according to the number of keywords in the plurality of keyword sets, and generating keyword set sorting; and generating a first sub-search word according to the keyword set ordering.

In one example, by extracting keywords in the history query sentence and the history browsing record, for convenience of description, the keywords are listed as a "method" and a "device", then the times of the "method" and the "device" appearing in the history query sentence and the history browsing record are extracted, two sets of sets are generated, one set is a "method" set, and the other set is a "device" set, the number of keywords contained in the two sets is obtained, if the number of keywords in the "method" set is greater than the number of keywords in the "device" set, the "method" set is arranged before the "device" set, then the search word is generated, the pushed keywords can be mainly considered as a "method", then the "device" or only the "method" of pushing the keywords is used, and of course, in practical application, a plurality of keywords may exist, and one or more keywords may be selected according to the requirement to be pushed. It should be noted that, the keywords may be set by themselves, one or more keywords may be set, and then the same words or words of the same type are ranked, where the words of the same type may be understood as "communication" and "soft-pass" being one type, and then the first sub-search word is generated.

The first search word comprises a second sub-search word, and the first search word is generated according to the historical query statement and the historical browsing record, and comprises the following steps: analyzing historical query sentences and historical browsing records of a user, and predicting search intention of the user; and generating a second sub-search word according to the search intention of the user.

In one example, the search intent of the user may be predicted based on the historical query statement and the historical browsing record, e.g., the patents that the user frequently searches for are related to unmanned aerial vehicle communications, then it may be predicted that the user may need to learn a large number of related patents or companies, etc., and at the time of pushing, the keyword may be pushed as "unmanned aerial vehicle" and/or "communication", where "unmanned aerial vehicle" and/or "communication" is the second sub-search term.

The step of merging and sequencing the first search word, the second search word and the third search word to obtain a first sequence includes:

combining the first search word, the second search word and the third search word to obtain a search word set; acquiring a historical query record of a user, counting one or more search words with highest user search frequency in the historical query record of the user, and generating keywords; comparing the keywords with all the search words in the search word set to obtain the similarity of all the search words, and sorting all the search words according to the similarity of all the search words to obtain a first sequence.

In one example, after the first search word, the second search word and the third search word are combined, a set, that is, a set of search words is obtained; then, counting one or more search words with highest search frequency of the user in the historical query record of the user, wherein the search word with highest frequency is communication, and the communication can be set as a keyword at the moment; and comparing all the search words in the search word set with the keywords to obtain the similarity of all the search words and the keywords, wherein the specific calculation method can refer to the embodiment, and then the search words are ranked according to the similarity, the higher the similarity is, the more front the ranking is, the lower the similarity is, the more rear the ranking is, and the ranking result is the first sequence.

According to a first sequence, pushing search terms comprises the following steps: acquiring the total number of search words in the first sequence; if the total number of the search words in the first sequence is lower than the preset number, the first sequence is directly pushed.

In one example, after the first sequence is obtained, search word pushing is required, in general, different users may have requirements on the number of the pushed search words, there may be users who only know about a small range of patent related transactions that the users want to know, and some users may need to know about patent related transactions in different fields, for which the users can set themselves according to actual situations; in the application, the number of the search words in the first sequence can be obtained, if the total number of the search words is lower than the preset number, the first sequence is directly pushed completely, and the preset number can be set according to the actual situation.

After obtaining the total number of the search words in the first sequence, the method further comprises: if the total number of the search words in the first sequence exceeds the preset number, eliminating the search words in the part exceeding the preset number in the first sequence to obtain a first sequence to be pushed; acquiring the type of the search word in the first sequence to be pushed; if a plurality of search words with the same type exist in the first sequence to be pushed, only the search word with the forefront sequence in the first sequence to be pushed is reserved, and the rest one or more search words with the same type are removed to obtain a second sequence to be pushed; calculating the difference between the total number of search words in the first sequence to be pushed and the total number of search words in the second sequence to be pushed to obtain a first number, and extracting the search words corresponding to the first number in the first sequence to the second sequence to be pushed to obtain a final pushing sequence; and pushing the final push sequence.

In another example, if the total number of search words in the first sequence exceeds the preset number, if the preset number is five, and the total number of search words in the first sequence is ten, since the search words in the first sequence are arranged in sequence, the five search words ranked later need to be removed, and only the five search words ranked first remain; then the types of the five search words ranked in front are obtained, whether the five search words ranked in front have the same type of search words is judged, if the five search words ranked in front have two search words of the same type, such as communication and soft pass can be considered as the search words of the same type, then the search words ranked in back are deleted, if a plurality of search words of the same type exist, only the search word ranked in front is reserved, and the rest search words are removed, so that a second sequence to be pushed is obtained; and calling the corresponding number of search words from the five search words ranked at the back to a second sequence to be pushed according to the number of the search words removed. For example, when one search word is removed from the search words with the front ranking, extracting the search word with the sixth ranking to the second sequence to be pushed, sequentially extracting a corresponding number of search words to the second sequence to be pushed according to the number of the search words to be pushed, so as to obtain a final push sequence, and finally pushing the final push sequence.

According to the first sequence, after pushing the search term, the method further comprises the following steps: acquiring feedback information filled by a user, wherein the feedback information comprises positive feedback information and negative feedback information; if the feedback information filled by the user is positive feedback information, optimizing the first sequence to obtain a second sequence; and if the feedback information filled in by the user is negative feedback information, the first sequence is adjusted to obtain a third sequence.

In one example, after pushing the search term, feedback information filled by the user can be obtained, the feedback information comprises positive feedback information and negative feedback information, if the feedback information is positive feedback information, the positive feedback information can be recorded so as to be convenient for future reference, the product, service and business flow can be continuously improved according to the positive feedback information, and the pushing system is optimized according to the positive feedback information, so that the pushed search term is more accurate and more accords with the requirement of the user; if the feedback information is negative feedback information, the pushed keywords are adjusted according to the negative feedback information, if the search words which can be fed back and pushed are inaccurate or the number of the search words is too large, at the moment, the system can push according to the negative feedback information, so that the user problem is solved, and the user experience is improved.

Based on the method, the application also discloses a search word pushing device, as shown in fig. 3, and fig. 3 is a schematic structural diagram of an enterprise patent competition situation monitoring device according to an embodiment of the application.

An enterprise patent competition situation monitoring device, comprising: the device comprises a first generating module 1, a second generating module 2, a third generating module 3, an output module 4 and a pushing module 5; the first generation module 1 is used for acquiring historical query sentences and historical browsing records of a first user and generating first search words according to the historical query sentences and the historical browsing records; the second generation module 2 is used for constructing a first user portrait of a first user, acquiring a second user portrait similar to the first user portrait, and generating a second search term according to a historical query record of the second user corresponding to the second user portrait; the third generation module 3 is configured to generate a third search term according to the popular search term in the website at the current moment; the output module 4 is used for merging and sequencing the first search word, the second search word and the third search word to obtain a first sequence; the pushing module 5 is configured to perform search term pushing according to the first sequence.

It should be noted that: in the device provided in the above embodiment, when implementing the functions thereof, only the division of the above functional modules is used as an example, in practical application, the above functional allocation may be implemented by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules, so as to implement all or part of the functions described above. In addition, the embodiments of the apparatus and the method provided in the foregoing embodiments belong to the same concept, and specific implementation processes of the embodiments of the method are detailed in the method embodiments, which are not repeated herein.

Referring to fig. 4, a schematic structural diagram of an electronic device is provided in an embodiment of the present application. As shown in fig. 4, the electronic device 1000 may include: at least one processor 1001, at least one network interface 1004, a user interface 1003, a memory 1005, at least one communication bus 1002.

Wherein the communication bus 1002 is used to enable connected communication between these components.

The user interface 1003 may include a Display screen (Display) and a Camera (Camera), and the optional user interface 1003 may further include a standard wired interface and a wireless interface.

The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface), among others.

Wherein the processor 1001 may include one or more processing cores. The processor 1001 connects various parts within the entire server using various interfaces and lines, performs various functions of the server and processes data by executing or executing instructions, programs, code sets, or instruction sets stored in the memory 1005, and calling data stored in the memory 1005. Alternatively, the processor 1001 may be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), programmable logic array (Programmable Logic Array, PLA). The processor 1001 may integrate one or a combination of several of a central processing unit (Central Processing Unit, CPU), an image processor (Graphics Processing Unit, GPU), and a modem, etc. The CPU mainly processes an operating system, a user interface, an application program and the like; the GPU is used for rendering and drawing the content required to be displayed by the display screen; the modem is used to handle wireless communications. It will be appreciated that the modem may not be integrated into the processor 1001 and may be implemented by a single chip.

The Memory 1005 may include a random access Memory (Random Access Memory, RAM) or a Read-Only Memory (Read-Only Memory). Optionally, the memory 1005 includes a non-transitory computer readable medium (non-transitory computer-readable storage medium). The memory 1005 may be used to store instructions, programs, code, sets of codes, or sets of instructions. The memory 1005 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the above-described respective method embodiments, etc.; the storage data area may store data or the like involved in the above respective method embodiments. The memory 1005 may also optionally be at least one storage device located remotely from the processor 1001. As shown in fig. 4, an operating system, a network communication module, a user interface module, and an application program of a search term pushing method may be included in the memory 1005 as a computer storage medium.

In the electronic device 1000 shown in fig. 4, the user interface 1003 is mainly used for providing an input interface for a user, and acquiring data input by the user; and the processor 1001 may be configured to invoke an application in the memory 1005 that stores a search term pushing method that, when executed by one or more processors, causes the electronic device to perform the method as described in one or more of the embodiments above.

An electronic device readable storage medium storing instructions. When executed by one or more processors, cause an electronic device to perform the method as described in one or more of the embodiments above.

It should be noted that, for simplicity of description, the foregoing method embodiments are all described as a series of acts, but it should be understood by those skilled in the art that the present application is not limited by the order of acts described, as some steps may be performed in other orders or concurrently in accordance with the present application. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all of the preferred embodiments, and that the acts and modules referred to are not necessarily required for the present application.

In the foregoing embodiments, the descriptions of the embodiments are emphasized, and for parts of one embodiment that are not described in detail, reference may be made to related descriptions of other embodiments.

In the several embodiments provided by the present application, it should be understood that the disclosed apparatus may be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative, such as the division of the units, merely a logical function division, and there may be additional manners of dividing the actual implementation, such as multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some service interface, device or unit indirect coupling or communication connection, electrical or otherwise.

The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.

The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable memory. Based on this understanding, the technical solution of the present application may be embodied essentially or partly in the form of a software product, or all or part of the technical solution, which is stored in a memory, and includes several instructions for causing a computer device (which may be a personal computer, a server, a network device, or the like) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned memory includes: various media capable of storing program codes, such as a U disk, a mobile hard disk, a magnetic disk or an optical disk.

The foregoing is merely exemplary embodiments of the present disclosure and is not intended to limit the scope of the present disclosure. That is, equivalent changes and modifications are contemplated by the teachings of this disclosure, which fall within the scope of the present disclosure. Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a scope and spirit of the disclosure being indicated by the claims.

Claims (10)

1. The search word pushing method is characterized by comprising the following steps of:

acquiring a historical query statement and a historical browsing record of a first user, and generating a first search word according to the historical query statement and the historical browsing record;

constructing a first user portrait of the first user, acquiring a second user portrait similar to the first user portrait, and generating a second search term according to a historical query record of the second user corresponding to the second user portrait;

Generating a third search word according to the popular search word in the website at the current moment;

merging and sequencing the first search word, the second search word and the third search word to obtain a first sequence;

and pushing the search word according to the first sequence.

2. The method for pushing search terms according to claim 1, wherein the first search terms include first sub-search terms, and the generating the first search terms according to the historical query statement and the historical browsing record includes:

extracting keywords in the historical query sentences and the historical browsing records, and classifying the keywords to obtain a plurality of keyword sets;

sorting the plurality of keyword sets according to the number of keywords in the plurality of keyword sets, and generating keyword set sorting;

and generating a first sub-search word according to the keyword set ordering.

3. The method for pushing search terms according to claim 1, wherein the first search term includes a second sub-search term, and the generating the first search term according to the historical query statement and the historical browsing record includes:

analyzing the historical query sentences and the historical browsing records of the user, and predicting the search intention of the user;

And generating a second sub-search word according to the search intention of the user.

4. The method for pushing search terms according to claim 1, wherein the merging and sorting the first search term, the second search term and the third search term to obtain a first sequence includes:

combining the first search word, the second search word and the third search word to obtain a search word set;

acquiring a historical query record of the user, and counting one or more search words with highest user search frequency in the historical query record of the user to generate keywords;

comparing the keywords with all search words in the search word set to obtain the similarity of all the search words, and sorting all the search words according to the similarity of all the search words to obtain a first sequence.

5. The method for pushing search terms according to claim 1, wherein the pushing search terms according to the first sequence includes:

acquiring the total number of search words in the first sequence;

if the total number of the search words in the first sequence is lower than the preset number, the first sequence is directly pushed.

6. The method for pushing search terms according to claim 5, further comprising, after the obtaining the total number of search terms in the first sequence:

if the total number of the search words in the first sequence exceeds the preset number, eliminating the search words in the part exceeding the preset number in the first sequence to obtain a first sequence to be pushed;

acquiring the type of the search word in the first sequence to be pushed;

if a plurality of search words with the same type exist in the first sequence to be pushed, only the search word with the forefront sequence in the first sequence to be pushed is reserved, and the rest one or more search words with the same type are removed to obtain a second sequence to be pushed;

calculating the difference between the total number of search words in the first sequence to be pushed and the second sequence to be pushed to obtain a first number, and extracting the search words corresponding to the first number in the first sequence to the second sequence to be pushed to obtain a final push sequence;

pushing the final push sequence.

7. The method for pushing search terms according to claim 1, wherein after the pushing search terms according to the first sequence, the method further comprises:

Acquiring feedback information filled by the user, wherein the feedback information comprises positive feedback information and negative feedback information;

if the feedback information filled by the user is the positive feedback information, optimizing the first sequence to obtain a second sequence;

and if the feedback information filled in by the user is the negative feedback information, the first sequence is adjusted to obtain a third sequence.

8. A search term pushing device, the device comprising: the device comprises a first generation module (1), a second generation module (2), a third generation module (3), an output module (4) and a pushing module (5); wherein, the liquid crystal display device comprises a liquid crystal display device,

the first generation module (1) is used for acquiring historical query sentences and historical browsing records of a first user and generating first search words according to the historical query sentences and the historical browsing records;

the second generation module (2) is used for constructing a first user portrait of the first user, acquiring a second user portrait similar to the first user portrait, and generating a second search word according to a history query record of the second user corresponding to the second user portrait;

the third generation module (3) is used for generating third search words according to popular search words in the website at the current moment;

The output module (4) is used for merging and sequencing the first search word, the second search word and the third search word to obtain a first sequence;

the pushing module (5) is used for pushing the search word according to the first sequence.

9. An electronic device comprising a processor (1001), a memory (1005), a user interface (1003) and a network interface (1004), the memory (1005) being configured to store instructions, the user interface (1003) and the network interface (1004) being configured to communicate to other devices, the processor (1001) being configured to execute the instructions stored in the memory to cause the electronic device to perform the method of any of claims 1-7.

10. A computer readable storage medium, characterized in that a computer program is stored which can be loaded by a processor and which performs the method according to any of claims 1-7.