A search result processing method and apparatus

Abstract

The application discloses a search result processing method and device, electronic equipment and a computer readable storage medium. The method comprises the following steps: obtaining a search word and first search results corresponding to the search word and pre-displayed on a search result page; determining one or more keywords corresponding to the search word; obtaining search logs corresponding to each keyword; determining whether each first search result reaches a preset user satisfaction degree according to the obtained search logs; and if not, performing a preset operation on the first search result that does not reach the preset user satisfaction degree. In the technical solution, the search logs of the keywords corresponding to the search word are used to determine whether the search result reaches the user satisfaction, and the results irrelevant to the search word or with low relevance in the search result are ensured to be used by the user, so as to avoid reducing the user experience due to the content irrelevant to the input search word or with low relevance in the search result.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, in particular to a search result processing method and device, electronic equipment and computer readable storage medium. BACKGROUND

[0002] With the rapid development of Internet technology and the sharp increase in information, users usually search for the required information resources through search. Generally speaking, search is a service of returning the most satisfactory results to users according to the input keywords. Nowadays, there are many search products that can provide search portals to realize search functions, such as browsers, search boxes, search software, etc.

[0003] Since users search for the required information resources through search, the search results returned after search and the sorting of search results will directly affect the satisfaction of users. If the search results contain irrelevant or low-relevance content to the entered search term, the user experience will be reduced. SUMMARY

[0004] In view of the above problems, the present application is proposed to provide a search result processing method, device, electronic equipment and computer readable storage medium which can overcome the above problems or at least partially solve the above problems.

[0005] According to one aspect of the present application, a search result processing method is provided, wherein the method comprises:

[0006] obtaining a search term and first search results corresponding to the search term and pre-displayed on a search result page;

[0007] determining one or more keywords corresponding to the search term;

[0008] obtaining search logs corresponding to each keyword, respectively;

[0009] judging whether each first search result reaches a preset user satisfaction degree according to the obtained search logs;

[0010] If not, performing a preset operation on the first search result that does not reach the preset user satisfaction degree.

[0011] Optionally, the method further comprises:

[0012] calculating a matching degree of each first search result and the search term;

[0013] performing the step of judging whether each first search result reaches a preset user satisfaction degree according to the obtained search logs on the first search result corresponding to the matching degree greater than or equal to a preset threshold;

[0014] If the matching degree of the first search result is less than the first threshold, it is determined that the first search result does not reach the preset user satisfaction degree, and the step of performing a preset operation on the first search result not reaching the preset user satisfaction degree is executed.

[0015] Optionally, the calculating the matching degree of each first search result and the search term comprises:

[0016] obtaining a title and an abstract of each first search result;

[0017] performing a word segmentation processing on the obtained search term to obtain a word segmentation corresponding to the search term;

[0018] calculating the matching degree of each first search result and the search term according to the word segmentation corresponding to the search term and the title and the abstract of each first search result.

[0019] Optionally, the judging whether each first search result reaches the preset user satisfaction degree according to the obtained search log comprises:

[0020] calculating a first user click ratio of a click amount of each first search result to a total click amount of all first search results according to user click data in the obtained search log;

[0021] determining a second search result corresponding to each keyword, and when the first search result is included in the second search result corresponding to a keyword, calculating a second user click ratio of the click amount of the first search result to a total click amount of all second search results corresponding to the keyword according to user click data in the obtained search log corresponding to the keyword;

[0022] judging whether each first search result reaches the preset user satisfaction degree according to the first user click ratio corresponding to each first search result and the second user click ratio corresponding to each first search result.

[0023] Optionally, the judging whether each first search result reaches the preset user satisfaction degree according to the first user click ratio corresponding to each first search result and the second user click ratio corresponding to each first search result comprises:

[0024] comparing the first user click ratio corresponding to each first search result and the second user click ratio corresponding to the first search result respectively;

[0025] if the second user click ratio is less than the first user click ratio, it is determined that the first search result does not reach the preset user satisfaction degree.

[0026] Optionally, the performing a preset operation on the first search result not reaching the preset user satisfaction degree comprises:

[0027] deleting the first search result not reaching the preset user satisfaction degree.

[0028] or,

[0029] decreasing the display order of the first search result which does not reach the preset user satisfaction in the search result display page;

[0030] or,

[0031] performing corresponding operation on the first search result which does not reach the preset user satisfaction according to the processing method configured by the user.

[0032] Optionally, the decreasing the display order of the first search result which does not reach the preset user satisfaction in the search result display page comprises:

[0033] arranging the first search result which does not reach the preset user satisfaction after the first search result which reaches the preset user satisfaction after random sorting.

[0034] According to another aspect of the present application, a processing device for search result is provided, wherein the device comprises:

[0035] a search word obtaining unit adapted to obtain a search word and a first search result corresponding to the search word which is pre-displayed in a search result page;

[0036] a determining unit adapted to determine one or more keywords corresponding to the search word;

[0037] a search log obtaining unit adapted to obtain a search log corresponding to each keyword respectively;

[0038] a judging unit adapted to judge whether each first search result reaches a preset user satisfaction according to the obtained search log;

[0039] a processing unit adapted to perform a preset operation on the first search result which does not reach the preset user satisfaction if the first search result does not reach the preset user satisfaction.

[0040] Optionally, the device further comprises:

[0041] a calculating unit adapted to calculate the matching degree between each first search result and the search word;

[0042] the judging unit is adapted to perform the step of judging whether each first search result reaches the preset user satisfaction according to the obtained search log on the first search result corresponding to the matching degree greater than or equal to a preset threshold;

[0043] the processing unit is adapted to directly determine that the first search result corresponding to the matching degree less than the preset threshold does not reach the preset user satisfaction, and perform the step of performing the preset operation on the first search result which does not reach the preset user satisfaction.

[0044] Optionally,

[0045] The computing unit is adapted to acquire the title and abstract of each first search result, perform word segmentation processing on the acquired search word, acquire the segmented words corresponding to the search word, and calculate the matching degree of each first search result and the search word according to the segmented words corresponding to the search word and the title and abstract of each first search result.

[0046] Optionally,

[0047] The judging unit is adapted to calculate the first user click ratio of the click volume of each first search result to the total click volume of all first search results according to the user click data in the acquired search log, determine the second search result corresponding to each keyword, calculate the second user click ratio of the click volume of the first search result to the total click volume of all second search results corresponding to the keyword according to the user click data in the search log corresponding to the keyword when the first search result is included in the second search result corresponding to the keyword, and judge whether each first search result reaches the preset user satisfaction degree according to the first user click ratio corresponding to each first search result and the second user click ratio corresponding to each first search result.

[0048] Optionally,

[0049] The judging unit is adapted to compare the first user click ratio corresponding to each first search result and the second user click ratio corresponding to the first search result respectively, and determine that the first search result does not reach the preset user satisfaction degree if the second user click ratio is less than the first user click ratio.

[0050] Optionally,

[0051] The processing unit is adapted to delete the first search result that does not reach the preset user satisfaction degree, or reduce the display order of the first search result that does not reach the preset user satisfaction degree in the search result display page, or perform corresponding operations on the first search result that does not reach the preset user satisfaction degree according to the processing device configured by the user.

[0052] Optionally,

[0053] The processing unit is adapted to arrange the first search result that does not reach the preset user satisfaction degree after the search result that reaches the preset user satisfaction degree after random sorting.

[0054] According to another aspect of the present application, an electronic device is provided, wherein the electronic device comprises:

[0055] a processor; and

[0056] a memory arranged to store computer-executable instructions that, when executed, cause the processor to perform the method according to the preceding.

[0057] According to still another aspect of the present application, there is provided a computer-readable storage medium, wherein the computer-readable storage medium stores one or more programs, which, when executed by a processor, implement the method according to the preceding.

[0058] According to the technical solution of the present application, the search term and the first search results corresponding to the pre-show of the search term in the search result page are obtained; one or more keywords corresponding to the search term are determined; search logs corresponding to each keyword are obtained; whether each first search result reaches a preset user satisfaction degree is determined according to the obtained search logs; and if not, a preset operation is performed on the first search result that does not reach the preset user satisfaction degree. It can be seen that in the technical solution, whether the search result reaches the user satisfaction is determined through the search logs of the keywords corresponding to the search term, and the results irrelevant to the search term or with low relevance in the search result are guaranteed to be used by the user, so as to avoid reducing the user experience due to the inclusion of irrelevant content or content with low relevance to the entered search term in the search result.

[0059] The above description is only a summary of the technical solution of the present application. In order to enable the technical means of the present application to be more clearly understood, the present application can be implemented according to the content of the specification, and in order to enable the above and other purposes, features and advantages of the present application to be more apparent and easy to understand, the following specific embodiments of the present application are described. BRIEF DESCRIPTION OF DRAWINGS

[0060] Various other advantages and benefits will become apparent to those of ordinary skill in the art, upon reading the following detailed description of the preferred embodiment. The accompanying drawings are included to provide a description of preferred embodiments, and are not meant to limit the present application. Furthermore, the same reference numerals are used throughout the several drawings to denote similar or equivalent parts. In the drawings:

[0061] Figure 1 A flowchart of a processing method of a search result according to an embodiment of the present application is shown;

[0062] Figure 2 A structural diagram of a processing device of a search result according to an embodiment of the present application is shown;

[0063] Figure 3 A structural diagram of an electronic device according to an embodiment of the present application is shown;

[0064] Figure 4 A structural diagram of a computer-readable storage medium according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0065] Exemplary embodiments of the present disclosure will be described in greater detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it is understood that the present disclosure can be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the present disclosure to those skilled in the art.

[0066] Figure 1 A flowchart of a method for processing search results according to an embodiment of the present disclosure is shown. As shown in the figure, the method comprises: Figure 1

[0067] In step S110, the search term and the first search result corresponding to the search term and pre-displayed in the search result page are obtained.

[0068] After the user searches with the search term, the search results determined according to the search term will be displayed in the search result page. In this embodiment, in order to further process the search results to solve the problem that the search results contain content irrelevant or less relevant to the entered search term, which will reduce the user experience, the search term and the first search result corresponding to the search term and pre-displayed in the search result page are obtained. The search results displayed in the search result page include one or more, so the first search result here is also one or more.

[0069] In step S120, one or more keywords corresponding to the search term are determined.

[0070] When the user searches, the search term will be input in the search entry. Considering that the search term can be a word or a sentence, in this embodiment, the keywords corresponding to the search term are also determined, for example, the user inputs the search term "pong", and it is determined that the keyword corresponding to the search term is "pong"; the user inputs the search term "python or and the priority of and", which is a sentence, so it is determined that the keywords corresponding to the search term are "python", "or", "and" and "priority".

[0071] The above examples are only to illustrate that one search term can correspond to one or more keywords, and the determination of one or more keywords corresponding to the search term in actual application can adopt the scheme in the prior art.

[0072] In step S130, the search log corresponding to each keyword is obtained.

[0073] ​When the user performs a search, a search log is formed, which includes the user's operation behavior during the search process, for example, the search log includes user id, keywords searched by the user, whether there is a click behavior, click position, stay duration, etc. Through the search log, the behavior of each user to each search result under a keyword can be determined. If the number of times of clicking by the user based on a search result under a keyword is more, it means that the search result with more click times is more in line with the user's demand when the user searches the keyword. That is, through the search log, whether the user is satisfied with each search result under each keyword can be obtained.

[0074] In this embodiment, when the keyword corresponding to the search word is determined, the search log corresponding to the keyword is filtered from the search log.

[0075] In step S140, whether each first search result reaches the preset user satisfaction degree is judged according to the obtained search log.

[0076] According to the above description, because the search information of the user is recorded in the search log, whether each first search result obtained in step S110 reaches the preset user satisfaction degree can be determined. Here, the preset user satisfaction degree can be a specific numerical value set, and then in the judgment process, the specific satisfaction degree value of each first search result can be calculated according to the obtained search log. Alternatively, whether each first search result reaches the preset user satisfaction degree can also be judged according to other judgment data (for example, the number of clicks of the user on each first search result).

[0077] In step S150, if not, a preset operation is performed on the first search result that does not reach the preset user satisfaction degree.

[0078] If the preset user satisfaction degree is not reached, it means that the first search result is irrelevant to the entered search word or has low relevance, and then a preset operation can be performed on the first search result that does not reach the preset user satisfaction degree, so as to ensure that the search result displayed to the user meets the user's demand, or the search result arranged in the front displayed to the user meets the user's demand. The search result corresponding to the search word after the technical solution is displayed in the search result page, that is, the final search result displayed to the user is the processed search result, which ensures the user experience.

[0079] It can be seen that in this embodiment, whether the search result reaches the user satisfaction is determined through the search log of the keyword corresponding to the search word, and the result irrelevant to the search word or having low relevance in the search result is ensured to avoid reducing the user experience due to the irrelevant content or the content with low relevance to the entered search word in the search result.

[0080] In one embodiment of the present application, Figure 1 The method further includes: calculating the matching degree of each first search result with the search term; for the first search result corresponding to the matching degree greater than or equal to the preset threshold, performing the step of judging whether each first search result reaches the preset user satisfaction degree according to the obtained search log; for the first search result corresponding to the matching degree less than the preset threshold, directly determining that the first search result does not reach the preset user satisfaction degree, and performing the step of performing a preset operation on the first search result that does not reach the preset user satisfaction degree.

[0081] In the present embodiment, the matching degree of each first search result with the search term is first calculated. If the matching degree of the first search result corresponding to the matching degree less than the preset threshold is low, the step of judging whether each first search result reaches the preset user satisfaction degree is not needed, and the corresponding operation can be directly performed. In this way, the waste of system resources can be reduced, and the processing efficiency can be ensured.

[0082] For the first search result corresponding to the matching degree greater than or equal to the preset threshold, the step of judging whether each first search result reaches the preset user satisfaction degree according to the obtained search log is performed. The search result that is irrelevant to the search term or has low relevance and does not meet the user demand can be further filtered out from the first search result. The first search result is checked from the matching degree and the user satisfaction degree, and the search result displayed to the user is further ensured to meet the user demand.

[0083] For example, the first search result corresponding to the obtained search term includes search result 1, search result 2 and search result 3. The matching degrees of the search term with search result 1, search result 2 and search result 3 are 80%, 45% and 65% respectively. The preset threshold is 60%. The search result 2 is directly subjected to the corresponding operation. The search result 1 and the search result 3 are subjected to the corresponding operation according to the obtained search log to judge whether the search result 1 and the search result 3 reach the preset user satisfaction degree.

[0084] Specifically, the above-mentioned calculation of the matching degree of each first search result with the search term includes: obtaining the title and the abstract of each first search result; performing a word segmentation processing on the obtained search term to obtain the word segmentation corresponding to the search term; and calculating the matching degree of each first search result with the search term according to the word segmentation corresponding to the search term and the title and the abstract of each first search result.

[0085] In the present embodiment, the matching degree of each first result with the search term is calculated by matching the word segmentation of the search term with the title and the abstract of each first search result. For example, the matching degree can be calculated by judging the probability of each word segmentation appearing in the title and the abstract of the search result.

[0086] In one embodiment of the present application, Figure 1 The step S140 of judging whether each first search result reaches the preset user satisfaction degree according to the obtained search log includes: calculating a first user click ratio of the click amount of each first search result to the total click amount of all first search results according to the user click data in the obtained search log; determining the second search result corresponding to each keyword, and when the first search result is included in the second search result corresponding to a keyword, calculating a second user click ratio of the click amount of the first search result to the total click amount of all second search results corresponding to the keyword according to the user click data in the search log corresponding to the keyword; and judging whether each first search result reaches the preset user satisfaction degree according to the first user click ratio corresponding to each first search result and the second user click ratio corresponding to each first search result.

[0087] As described above, the search log includes the operation behavior of the user in the search process. In the present embodiment, the user behavior information in the search log is used to determine the user click ratio of each first search result based on the keyword and the user click ratio based on all first search results, and then to judge whether each first search result meets the preset user satisfaction degree. Because the search log includes the data of the click position of the user, it can be determined which search result is clicked by the user, and then the user click data of each search result can be determined.

[0088] Specifically, the step of judging whether each first search result reaches the preset user satisfaction degree according to the first user click ratio corresponding to each first search result and the second user click ratio corresponding to each first search result includes: comparing the first user click ratio corresponding to each first search result with the second user click ratio corresponding to the first search result respectively; and if the second user click ratio is less than the first user click ratio, it is determined that the first search result does not reach the preset user satisfaction degree.

[0089] It is considered that if the second user click ratio is less than the first user click ratio, it means that the search result may appear in the first search result with the click number superposition, but based on the keyword, the search result cannot meet the user demand, and the appearance of the search result in the first search result cannot meet the user demand either; if the second user click ratio is greater than or equal to the first user click ratio, it means that the search result is not affected by the click number superposition, and based on the keyword, the search result meets the user demand, so that the appearance of the search result in the first search result also meets the user demand, and it is determined to reach the preset user satisfaction degree.

[0090] In one specific example, the search word corresponds to keyword 1 and keyword 2. Search result 1, search result 2 and search result 3 correspond to keyword 1; search result 2, search result 4 and search result 5 correspond to keyword 2. According to the search log of keyword 1, the click volume of search result 1 is 100, the click volume of search result 2 is 200, and the click volume of search result 3 is 500; the total click number based on keyword 1 is 800, and the second user click ratio corresponding to search result 1 is 0.125, the second user click ratio corresponding to search result 2 is 0.25, and the second user click ratio corresponding to search result 3 is 0.625. According to the search log of keyword 2, the click volume of search result 2 is 200, the click volume of search result 4 is 400, and the click volume of search result 5 is 200; the total click number based on keyword 2 is 800, and the second user click ratio corresponding to search result 2 is 0.25, the second user click ratio corresponding to search result 4 is 0.5, and the second user click ratio corresponding to search result 5 is 0.25. The first search result obtained includes search result 2 (click volume 200+200), search result 3 (click volume 500) and search result 4 (click volume 400), the total click volume based on the search word is 1300, and the first user click ratio of search result 2 is 0.31, the first user click ratio of search result 3 is 0.38, and the first user click ratio of search result 4 is 0.31. It can be seen that the second user click ratio of search result 2 (0.25) is less than the first user click ratio (0.31), the second user click ratio of search result 3 (0.625) is greater than the first user click ratio (0.38), and the second user click ratio of search result 4 (0.5) is greater than the first user click ratio (0.31). Therefore, search result 2 here is determined to not reach the preset user satisfaction.

[0091] In one embodiment of the present application, Figure 1 The step S150 of the method shown includes the following operations of the first search result not reaching the preset user satisfaction: deleting the first search result not reaching the preset user satisfaction; or, reducing the display order of the first search result not reaching the preset user satisfaction in the search result display page; or, according to the processing method configured by the user, performing corresponding operations on the first search result not reaching the preset user satisfaction.

[0092] To ensure that the search results displayed to the user are in line with the user's needs, in this embodiment, the search results that do not reach the preset user satisfaction are processed in one of three ways. This includes deleting, i.e. not displaying the search result; or reducing the display order, for example, if the search result originally displayed in the third place, it is determined that it does not reach the preset user satisfaction, then the search result is displayed in the 10th place. Or, the user customizes the processing method, for example, in the form of marking, adding the word "low matching degree" after the title of the search result, so that the user can ignore this search result.

[0093] Further, the above-mentioned reducing the display order of the first search result that does not reach the preset user satisfaction in the search result display page includes: arranging the first search result that does not reach the preset user satisfaction after the search result that reaches the preset user satisfaction after random sorting.

[0094] For example, the first search result includes 13 search results, search result 1, search result 2 and search result 3 are determined as not reaching the preset user satisfaction, then search result 1, search result 2 and search result 3 are randomly sorted as search result 2, search result 3 and search result 1, respectively arranged in the 11th, 12th and 13th place for display.

[0095] Figure 2 The structure diagram of the search result processing device according to an embodiment of the present application is shown. As shown in Figure 2 The search result processing device 200 includes:

[0096] The search term acquisition unit 210 is adapted to acquire the search term and the first search result corresponding to the search term pre-displayed in the search result page.

[0097] After the user searches with the search term, the search result determined according to the search term will be displayed in the search result page. In this embodiment, in order to further process the search result to solve the problem that the search result contains content irrelevant or with low relevance to the entered search term, which will reduce the user experience, the search term and the first search result corresponding to the search term pre-displayed in the search result page will be acquired. The search result displayed in the search result page includes one or more, so the first search result here is also one or more.

[0098] The determination unit 220 is adapted to determine one or more keywords corresponding to the search term.

[0099] When the user performs a search, a search term is input in the search entry. Considering that the search term can be a word or a sentence, in this embodiment, the key words corresponding to the search term are also determined. For example, if the user inputs the search term "pong", it is determined that the key words corresponding to the search term are "pong"; if the user inputs the search term "python or and the priority of and", it is determined that the key words corresponding to the search term are "python", "or", "and" and "priority of and".

[0100] The above examples are only for illustrating that one search term can correspond to one or more key words. In actual applications, the one or more key words corresponding to the search term can be determined by using the solutions in the prior art.

[0101] The search log obtaining unit 230 is adapted to obtain the search logs corresponding to the respective key words.

[0102] When the user performs a search, a search log is formed, which contains the operation behaviors of the user in the search process. For example, the search log includes the user id, the key words searched by the user, whether there is a click behavior, the click position, the stay duration and other information. Through the search log, the behaviors of the users to the search results under a key word can be determined. If the number of times of clicking by the user based on a search result under a key word is large, it indicates that the search result with the large number of times of clicking is more in line with the user demand when the user searches the key word. That is, through the search log, whether the user is satisfied with the search results under the respective key words can be obtained.

[0103] In this embodiment, after the key words corresponding to the search term are determined, the search logs corresponding to the respective key words are filtered from the search log.

[0104] The judging unit 240 is adapted to judge whether the respective first search results reach the preset user satisfaction degree according to the obtained search logs.

[0105] According to the above description, because the search information of the user is recorded in the search log, whether the respective first search results obtained in step S110 reach the preset user satisfaction degree can be determined. Here, the preset user satisfaction degree can be a specific numerical value. In the judging process, the specific satisfaction degree value of the respective first search results can be calculated according to the obtained search log. Alternatively, whether the respective first search results reach the preset user satisfaction degree can also be judged according to other judging data (for example, the number of times of clicking by the user to the respective first search results).

[0106] The processing unit 250 is adapted to perform a preset operation on the first search result that does not reach the preset user satisfaction degree if the first search result does not reach the preset user satisfaction degree.

[0107] If the first search result does not reach the preset user satisfaction, it is indicated that the first search result is irrelevant to the entered search term or has low relevance, and then a preset operation is performed on the first search result that does not reach the preset user satisfaction, so as to ensure that the search result displayed to the user meets the user demand or the search result arranged in the front displayed to the user meets the user demand. The search result corresponding to the search term after the technical solution is displayed in the search result page, that is, the final displayed search result is processed, and the search result reaching the preset user satisfaction is displayed to the user, thereby ensuring the user experience.

[0108] It can be seen that in the embodiment, whether the search result reaches the user satisfaction is determined through the search log of the keyword corresponding to the search term, the result irrelevant to the search term or having low relevance in the search result is ensured, and the user experience is ensured to avoid reducing the user experience due to the content irrelevant to the entered search term or having low relevance in the search result.

[0109] In an embodiment of the present application, Figure 2 The apparatus shown further comprises:

[0110] The computing unit is adapted to calculate the matching degree of each first search result and the search term.

[0111] The judging unit 240 is adapted to perform the step of judging whether each first search result reaches the preset user satisfaction according to the obtained search log for the first search result corresponding to the matching degree greater than or equal to the preset threshold.

[0112] The processing unit 250 is adapted to directly determine that the first search result corresponding to the matching degree less than the preset threshold does not reach the preset user satisfaction, and perform the step of performing a preset operation on the first search result that does not reach the preset user satisfaction.

[0113] In the embodiment, the matching degree of each first search result and the search term is first calculated, if the first search result corresponding to the matching degree less than the preset threshold, it is indicated that the first search result has low relevance to the search term, and then the step of whether the preset user satisfaction is reached is not needed to be performed, and the corresponding operation can be directly performed. In this way, the waste of system resources can be reduced, and the processing efficiency is ensured.

[0114] For the first search result corresponding to the matching degree greater than or equal to the preset threshold, the step of judging whether each first search result reaches the preset user satisfaction according to the obtained search log is performed, the search result irrelevant to the search term or having low relevance and not meeting the user demand in the first search result is further filtered out, the first search result is further ensured from the matching degree and the user satisfaction, and the search result displayed to the user is ensured to meet the user demand.

[0115] For example, the first search results corresponding to the obtained search word include search result 1, search result 2 and search result 3, the matching degrees of the search word with search result 1, search result 2 and search result 3 are respectively 80%, 45% and 65%, the preset threshold is 60%, then the search result 2 is directly operated, and the search result 1 and the search result 3 are operated according to the obtained search log to determine whether the search result 1 and the search result 3 reach the preset user satisfaction.

[0116] Specifically, the above-mentioned computing unit is adapted to obtain the title and the abstract of each first search result; perform word segmentation processing on the obtained search word to obtain the word segmentation corresponding to the search word; and calculate the matching degree of each first search result with the search word according to the word segmentation corresponding to the search word and the title and the abstract of each first search result.

[0117] In the embodiment, the matching degree of each first result with the search word is calculated by matching the word segmentation of the search word with the title and the abstract of each first search result. For example, when the matching degree is calculated, the calculation can be performed by judging the probability of each word segmentation appearing in the title and the abstract of the search result.

[0118] In one embodiment of the present application, Figure 2 The judgment unit 240 shown is adapted to calculate the first user click ratio of the click volume of each first search result to the total click volume of all first search results according to the user click data in the obtained search log; determine the second search result corresponding to each keyword, and when the first search result is included in the second search result corresponding to a keyword, calculate the second user click ratio of the click volume of the first search result to the total click volume of all second search results corresponding to the keyword according to the user click data in the search log corresponding to the keyword; and judge whether each first search result reaches the preset user satisfaction according to the first user click ratio corresponding to each first search result and the second user click ratio corresponding to each first search result.

[0119] As described above, the search log includes the operation behavior of the user in the search process. In the embodiment, the user behavior information in the search log is used to determine the user click ratio of each first search result based on the keyword and the user click ratio based on all first search results, and then to judge whether each first search result meets the preset user satisfaction. Because the search log includes the data of the click position of the user, it can be determined which search result is clicked by the user, and then the user click data of each search result can be determined.

[0120] In particular, the judging unit is adapted to compare the first user click ratio corresponding to each first search result and the second user click ratio corresponding to the first search result respectively; if the second user click ratio is less than the first user click ratio, it is determined that the first search result does not reach the preset user satisfaction degree.

[0121] It is considered that if the second user click ratio is less than the first user click ratio, it means that the search result may appear in the first search result with the click number superposition, but based on the keyword, the search result cannot meet the user demand, and the search result appearing in the first search result cannot meet the user demand; if the second user click ratio is greater than or equal to the first user click ratio, it means that the search result is not affected by the click number superposition, and based on the keyword, the search result meets the user demand, so the search result appearing in the first search result also meets the user demand, and it is determined to reach the preset user satisfaction degree.

[0122] In a specific example, the search word corresponds to keyword 1 and keyword 2. There are search result 1, search result 2 and search result 3 corresponding to keyword 1; there are search result 2, search result 4 and search result 5 corresponding to keyword 2. According to the obtained search log of keyword 1, the click volume of search result 1 is 100, the click volume of search result 2 is 200, and the click volume of search result 3 is 500; the total click number based on keyword 1 is 800, and the second user click ratio corresponding to search result 1 is 0.125, the second user click ratio corresponding to search result 2 is 0.25, and the second user click ratio corresponding to search result 3 is 0.625. According to the obtained search log of keyword 2, the click volume of search result 2 is 200, the click volume of search result 4 is 400, and the click volume of search result 5 is 200; the total click number based on keyword 2 is 800, and the second user click ratio corresponding to search result 2 is 0.25, the second user click ratio corresponding to search result 4 is 0.5, and the second user click ratio corresponding to search result 5 is 0.25. The obtained first search result includes search result 2 (click volume 200+200), search result 3 (click volume 500) and search result 4 (click volume 400), and the total click volume based on the search word is 1300, and the first user click ratio of search result 2 is 0.31, the first user click ratio of search result 3 is 0.38, and the first user click ratio of search result 4 is 0.31. It can be seen that the second user click ratio (0.25) of search result 2 is less than the first user click ratio (0.31), the second user click ratio (0.625) of search result 3 is greater than the first user click ratio (0.38), and the second user click ratio (0.0.5) of search result 4 is greater than the first user click ratio (0.31). Therefore, search result 2 here is determined to not reach the preset user satisfaction degree.

[0123] In an embodiment of the present application, Figure 2 The processing unit 250 is adapted to delete the first search result that does not reach the preset user satisfaction degree, or reduce the display order of the first search result that does not reach the preset user satisfaction degree in the search result display page, or perform corresponding operation on the first search result that does not reach the preset user satisfaction degree according to the processing device configured by the user.

[0124] In order to ensure that the search result displayed to the user meets the user's demand, in the embodiment, the search result that does not reach the preset user satisfaction degree is processed in one of the three ways. The processing includes deleting, i.e. not displaying the search result, or reducing the display order, for example, the search result is originally displayed in the third position, and it is judged that it does not reach the preset user satisfaction degree, then the search result is displayed in the 10th position. Or, the user defines the processing mode, for example, in the form of marking, adding the word "low matching degree" after the title of the search result, so that the user can ignore the search result.

[0125] Further, the processing unit is adapted to arrange the first search result that does not reach the preset user satisfaction degree after the search result that reaches the preset user satisfaction degree after random sorting.

[0126] For example, the first search result includes 13 search results, and the search result 1, the search result 2 and the search result 3 are determined as not reaching the preset user satisfaction degree, then the search result 1, the search result 2 and the search result 3 are randomly sorted as the search result 2, the search result 3 and the search result 1, and are arranged in the 11th position, the 12th position and the 13th position for display.

[0127] In summary, according to the technical scheme of the present application, the search term and the first search result corresponding to the search term are obtained, one or more keywords corresponding to the search term are determined, the search log corresponding to each keyword is obtained, whether each first search result reaches the preset user satisfaction degree is judged according to the obtained search log, and if not, the first search result that does not reach the preset user satisfaction degree is subjected to a preset operation. It can be seen that in the technical scheme, whether the search result reaches the user's satisfaction is determined by the search log of the keyword corresponding to the search term, and the result in the search result that is irrelevant to the search term or has low relevance is ensured to meet the user's experience, so as to avoid reducing the user experience due to the content irrelevant to the input search term or having low relevance in the search result.

[0128] It should be noted that:

[0129] The algorithms and displays presented herein are not inherently related to any particular computer, virtual apparatus, or other apparatus. Various general purpose systems can be used with programs in accordance with the teachings herein, or it can prove convenient to construct more specialized apparatus to perform the required method steps. The required structure for a variety of these systems will be apparent from the description above. In addition, the present application is not intended to be limited to a particular programming language. It will be appreciated that a variety of programming languages can be used to implement the teachings of the application as described herein, and any references below to specific languages are provided for disclosure of enablement only.

[0130] In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the application can be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been described in detail in order not to obscure the understanding of this description.

[0131] Similarly, it is to be understood that the mechanical details of the application sometimes are presented in terms of certain spatially-related or geometrical configurations and / or descriptions. It will be appreciated by those skilled in the art that the application can be practiced in an almost endless variety of geometrical configurations, and that the specific configuration(s) described herein are merely intended to be representative of the many in which the application can be practiced. It is therefore to be understood that no language in the specification should be interpreted as a specific limitation, but to the contrary, be understood to be illustrative only.

[0132] Those skilled in the art will appreciate that the modules in the apparatuses in the embodiments can be adapted and placed in one or more apparatuses other than the embodiments. The modules or units or components in the embodiments can be combined into one module or unit or component, and further can be divided into more sub-modules or sub-units or sub-components. Any combination of all the features disclosed in the specification (including the accompanying claims, abstract and drawings), and any method or apparatus so disclosed, can be made unless specifically stated otherwise. Each feature disclosed in the specification (including the accompanying claims, abstract and drawings) can be replaced by alternative features serving the same, equivalent or a similar purpose unless specifically stated otherwise.

[0133] Furthermore, those skilled in the art will recognize that, while certain embodiments described herein include certain features that are not included in other embodiments, combinations of features of the different embodiments are to be construed as being within the scope of the application and forming different embodiments. For example, in the following claims, any of the claimed embodiments can be used in any combination.

[0134] Embodiments of various components of the application can be implemented in hardware, software, or a combination thereof, and can be implemented with one or more processors in hardware, software, or a combination thereof under the control of one or more computer program products. The computer program product can be for example a computer readable medium storing the program code for execution by one or more processors. The computer readable medium can be a machine readable storage medium or a machine readable transmission medium. The machine readable storage medium can include, for example, floppy disks, optical disks, Compact Disc Read Only Memories (CD-ROMs), and Read Only Memories (ROMs), where appropriate. The machine readable transmission medium can include, for example, a modem, a wired

[0135] For example, Figure 3 A structural schematic of an electronic device according to an embodiment of the application is shown. The electronic device 300 conventionally comprises a processor 310 and a memory 320 arranged to store computer executable instructions (program code). The memory 320 can be an electronic memory such as a flash memory, an EEPROM (Electrically Erasable Programmable Read-Only Memory), an EPROM, a hard disk, or a ROM. The memory 320 has a storage space 330 for program code 340, which is shown. For example, the storage space 330 for program code can comprise individual program codes 340 for implementing the various steps in the above methods, respectively. These program codes can be read from or written to one or more computer program products. These computer program products include program code carriers such as a hard disk, a Compact Disc (CD), a memory card, or a floppy disk. Such computer program products are typically available as computer programs, for example, from a web site on the Internet. Figure 1 The storage space 330 for program code can comprise individual program codes 340 for implementing the various steps in the above methods, respectively. These program codes can be read from or written to one or more computer program products. These computer program products include program code carriers such as a hard disk, a Compact Disc (CD), a memory card, or a floppy disk. Such computer program products are typically available as computer programs, for example, from a web site on the Internet. Figure 4 The computer readable storage medium 400 is shown. The computer readable storage medium 400 can have a storage space 430 for program code 440, which is shown. For example, the storage space 430 for program code can comprise individual program codes 440 for implementing the various steps in the above methods, respectively. These program codes can be read from or written to one or more computer program products. These computer program products include program code carriers such as a hard disk, a Compact Disc (CD), a memory card, or a floppy disk. Such computer program products are typically available as computer programs, for example, from a web site on the Internet. Figure 3The memory 320 in the electronic device is similarly arranged as a storage segment, storage space, etc. The program code can be compressed, for example, in an appropriate form. Typically, the storage unit stores program code 410 for executing the steps of the method according to the present invention, that is, program code that can be read by a processor such as 310. When the program code is executed by the electronic device, it causes the electronic device to execute the various steps of the method described above.

[0136] It should be noted that the above embodiments illustrate rather than limit the invention, and that a person skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between brackets should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In a unit claim enumerating several means, several of these means may be embodied by the same item of hardware. The words first, second, and third etc. do not indicate any order. These words may be interpreted as names.

[0137] The embodiment of the present invention discloses A1, a method for processing search results, wherein the method includes:

[0138] Obtain a search term and a first search result corresponding to the search term, which is pre-displayed on a search results page;

[0139] determining one or more keywords corresponding to the search term;

[0140] Get the search logs corresponding to each keyword;

[0141] Determining whether each first search result meets a preset user satisfaction level based on the acquired search log;

[0142] If not, a preset operation is performed on the first search result that does not meet the preset user satisfaction.

[0143] A2. The method according to A1, wherein the method further comprises:

[0144] Calculate the matching degree between each first search result and the search term;

[0145] For the first search results corresponding to the matching degree being greater than or equal to the preset threshold, executing the step of determining whether each first search result meets the preset user satisfaction level based on the obtained search log;

[0146] If the matching degree of the first search result is less than the first threshold, it is determined that the first search result does not reach the preset user satisfaction degree, and the step of performing a preset operation on the first search result that does not reach the preset user satisfaction degree is executed.

[0147] A3, the method of A2, wherein the calculating the matching degree of each first search result and the search term comprises:

[0148] obtaining the title and the abstract of each first search result;

[0149] performing a word segmentation processing on the obtained search term to obtain the word segmentation corresponding to the search term;

[0150] calculating the matching degree of each first search result and the search term according to the word segmentation corresponding to the search term and the title and the abstract of each first search result.

[0151] A4, the method of A1, wherein the judging whether each first search result reaches the preset user satisfaction degree according to the obtained search log comprises:

[0152] calculating a first user click ratio of the click amount of each first search result and the total click amount of all first search results according to the user click data in the obtained search log;

[0153] determining the second search result corresponding to each keyword, and when the first search result is included in the second search result corresponding to a keyword, calculating a second user click ratio of the click amount of the first search result and the total click amount of all second search results corresponding to the keyword according to the user click data in the obtained search log corresponding to the keyword;

[0154] judging whether each first search result reaches the preset user satisfaction degree according to the first user click ratio corresponding to each first search result and the second user click ratio corresponding to each first search result.

[0155] A5, the method of A4, wherein the judging whether each first search result reaches the preset user satisfaction degree according to the first user click ratio corresponding to each first search result and the second user click ratio corresponding to each first search result comprises:

[0156] comparing the first user click ratio corresponding to each first search result and the second user click ratio corresponding to the first search result respectively;

[0157] if the second user click ratio is less than the first user click ratio, it is determined that the first search result does not reach the preset user satisfaction degree.

[0158] A6, the method of A1, wherein the performing a preset operation on the first search result that does not reach the preset user satisfaction degree comprises:

[0159] deleting the first search result that does not reach the preset user satisfaction degree;

[0160] alternatively,

[0161] decreasing the display order of the first search result that does not reach the preset user satisfaction degree in the search result display page;

[0162] alternatively,

[0163] performing corresponding operations on the first search result that does not reach the preset user satisfaction degree according to the processing method configured by the user.

[0164] A7. The method of A6, wherein the decreasing the display order of the first search result that does not reach the preset user satisfaction degree in the search result display page comprises:

[0165] arranging the first search result that does not reach the preset user satisfaction degree after the search result that reaches the preset user satisfaction degree after random sorting.

[0166] Embodiments of the present application also disclose B8, a processing device for search results, wherein the device comprises:

[0167] a search term acquisition unit, adapted to acquire a search term and a first search result corresponding to the search term and pre-displayed in a search result page;

[0168] a determination unit, adapted to determine one or more keywords corresponding to the search term;

[0169] a search log acquisition unit, adapted to acquire search logs corresponding to each keyword respectively;

[0170] a judgment unit, adapted to judge whether each first search result reaches a preset user satisfaction degree according to the acquired search logs;

[0171] a processing unit, adapted to perform a preset operation on the first search result that does not reach the preset user satisfaction degree.

[0172] B9. The device of B8, wherein the device further comprises:

[0173] a calculation unit, adapted to calculate the matching degree of each first search result and the search term;

[0174] the judgment unit is adapted to perform the step of judging whether each first search result reaches a preset user satisfaction degree according to the acquired search logs on the first search result corresponding to the matching degree greater than or equal to a preset threshold;

[0175] The processing unit is adapted to directly determine the first search result as not reaching the preset user satisfaction degree if the matching degree is less than the first preset threshold, and execute the step of performing a preset operation on the first search result not reaching the preset user satisfaction degree.

[0176] B10. The apparatus of B9, wherein,

[0177] The computing unit is adapted to acquire the title and abstract of each first search result, perform word segmentation processing on the acquired search word to acquire segmented words corresponding to the search word, and calculate the matching degree of each first search result and the search word according to the segmented words corresponding to the search word and the title and abstract of each first search result.

[0178] B11. The apparatus of B8, wherein,

[0179] The judging unit is adapted to calculate a first user click ratio of the click volume of each first search result to the total click volume of all first search results according to the user click data in the acquired search log, determine the second search result corresponding to each keyword, calculate a second user click ratio of the click volume of the first search result to the total click volume of all second search results corresponding to the keyword according to the user click data in the search log corresponding to the keyword when the second search result corresponding to the keyword includes the first search result, and judge whether each first search result reaches the preset user satisfaction degree according to the first user click ratio corresponding to each first search result and the second user click ratio corresponding to each first search result.

[0180] B12. The apparatus of B11, wherein,

[0181] The judging unit is adapted to respectively compare the first user click ratio corresponding to each first search result and the second user click ratio corresponding to the first search result, and determine that the first search result does not reach the preset user satisfaction degree if the second user click ratio is less than the first user click ratio.

[0182] B13. The apparatus of B8, wherein,

[0183] The processing unit is adapted to delete the first search result not reaching the preset user satisfaction degree, or reduce the display order of the first search result not reaching the preset user satisfaction degree in a search result display page, or perform a corresponding operation on the first search result not reaching the preset user satisfaction degree according to a processing device configured by a user.

[0184] B14. The apparatus of B13, wherein,

[0185] The processing unit is adapted to arrange the first search results that do not reach the preset user satisfaction degree after being randomly sorted behind the search results that reach the preset user satisfaction degree.

[0186] Embodiments of the application also disclose C15, an electronic device, wherein the electronic device comprises:

[0187] a processor; and

[0188] a memory arranged to store computer-executable instructions that, when executed, cause the processor to perform the method according to any one of A1-A7.

[0189] Embodiments of the application also disclose D16, a computer-readable storage medium, wherein the computer-readable storage medium stores one or more programs, and the one or more programs, when executed by a processor, implement the method according to any one of A1-A7.

Claims

1. A method of processing search results, wherein, The method comprises: acquiring a search word and first search results corresponding to pre-showing of the search word on a search result page; determining one or more keywords corresponding to the search word; acquiring search logs corresponding to each keyword respectively; the search logs comprise user operation behaviors in a search process; judging whether each first search result reaches a preset user satisfaction degree according to the acquired search logs; if not, performing a preset operation on the first search result that does not reach the preset user satisfaction degree; the judging whether each first search result reaches a preset user satisfaction degree according to the acquired search logs comprises: calculating a first user click ratio of a click volume of each first search result to a total click volume of all first search results according to user click data in the acquired search logs; determining second search results corresponding to each keyword respectively, and when the second search results corresponding to a keyword include the first search result, calculating a second user click ratio of the click volume of the first search result to a total click volume of all second search results corresponding to the keyword according to user click data in the search logs corresponding to the keyword; judging whether each first search result reaches a preset user satisfaction degree according to the first user click ratio corresponding to each first search result and the second user click ratio corresponding to each first search result.

2. The method of claim 1, wherein, The method further comprises: calculating a matching degree of each first search result and the search word; for the first search result corresponding to a matching degree greater than or equal to a preset threshold, performing the step of judging whether each first search result reaches a preset user satisfaction degree according to the acquired search logs; for the first search result corresponding to a matching degree less than the preset threshold, directly determining that the first search result does not reach a preset user satisfaction degree, and performing the step of performing a preset operation on the first search result that does not reach the preset user satisfaction degree.

3. The method of claim 2, wherein, the calculating a matching degree of each first search result and the search word comprises: acquiring a title and an abstract of each first search result; performing a word segmentation processing on the acquired search word to acquire word segmentation corresponding to the search word; calculating a matching degree of each first search result and the search word according to the word segmentation corresponding to the search word and the title and the abstract of each first search result.

4. The method of claim 1, wherein, the judging whether each first search result reaches a preset user satisfaction degree according to the first user click ratio corresponding to each first search result and the second user click ratio corresponding to each first search result comprises: comparing the first user click ratio corresponding to each first search result and the second user click ratio corresponding to the first search result respectively; if the second user click ratio is less than the first user click ratio, it is determined that the first search result does not reach a preset user satisfaction degree.

5. The method of claim 1, wherein, the performing a preset operation on the first search result that does not reach a preset user satisfaction degree comprises: deleting the first search result that does not reach a preset user satisfaction degree; or, reducing a display order of the first search result that does not reach a preset user satisfaction degree on a search result display page; or, performing a corresponding operation on the first search result that does not reach a preset user satisfaction degree according to a user configured processing method.

6. The method of claim 5, wherein, The display order of the first search results that do not reach the preset user satisfaction degree in the search result display page comprises: After the first search results that do not reach the preset user satisfaction degree are randomly sorted, the first search results are arranged behind the search results that reach the preset user satisfaction degree.

7. A processing apparatus of search results, wherein, The device comprises: A search word acquisition unit is adapted to acquire a search word and first search results corresponding to the search word and pre-displayed in a search result page; A determination unit is adapted to determine one or more keywords corresponding to the search word; A search log acquisition unit is adapted to acquire search logs corresponding to each keyword respectively; the search logs comprise user operation behaviors in a search process; A judgment unit is adapted to judge whether each first search result reaches a preset user satisfaction degree according to the acquired search logs; the judgment unit is adapted to calculate a first user click ratio of a click volume of each first search result to a total click volume of all first search results according to user click data in the acquired search logs; determine second search results corresponding to each keyword; when the second search results corresponding to a keyword include the first search result, calculate a second user click ratio of the click volume of the first search result to a total click volume of all second search results corresponding to the keyword according to user click data in the acquired search logs corresponding to the keyword; and judge whether each first search result reaches the preset user satisfaction degree according to the first user click ratio corresponding to each first search result and the second user click ratio corresponding to each first search result; A processing unit is adapted to perform a preset operation on the first search result that does not reach the preset user satisfaction degree if the first search result does not reach the preset user satisfaction degree.

8. The apparatus of claim 7, wherein, The device further comprises: A calculation unit is adapted to calculate a matching degree of each first search result and a search word; The judgment unit is adapted to perform the step of judging whether each first search result reaches the preset user satisfaction degree according to the acquired search logs on the first search result corresponding to a matching degree greater than or equal to a preset threshold; The processing unit is adapted to directly determine that the first search result does not reach the preset user satisfaction degree on the first search result corresponding to a matching degree less than the preset threshold, and perform the step of performing a preset operation on the first search result that does not reach the preset user satisfaction degree.

9. The device of claim 8, wherein The calculation unit is adapted to acquire a title and an abstract of each first search result; perform a word segmentation processing on the acquired search word to acquire segmented words corresponding to the search word; and calculate the matching degree of each first search result and the search word according to the segmented words corresponding to the search word and the title and the abstract of each first search result.

10. The device of claim 7, wherein The judgment unit is adapted to compare the first user click ratio corresponding to each first search result and the second user click ratio corresponding to the first search result respectively; If the second user click ratio is less than the first user click ratio, it is determined that the first search result does not reach the preset user satisfaction degree.

11. The device of claim 7, wherein The processing unit is adapted to delete the first search result that does not reach the preset user satisfaction degree; or, reduce the display order of the first search result that does not reach the preset user satisfaction degree in the search result display page. Or, according to the user-configured processing device, the first search result that does not reach the preset user satisfaction degree is subjected to corresponding operation.

12. The apparatus of claim 11, wherein, The processing unit is adapted to arrange the first search result that does not reach the preset user satisfaction degree after the search result that reaches the preset user satisfaction degree after being randomly sorted.

13. An electronic device, comprising: The electronic device includes: a processor; and a memory arranged to store computer-executable instructions that, when executed, cause the processor to perform the method of any one of claims 1-6.

14. A computer readable storage medium, wherein, The computer-readable storage medium stores one or more programs that, when executed by a processor, implement the method of any one of claims 1-6.

Images