TWI476611B - Search results generation method and information search system - Google Patents

Description

Search result generation method and information search system

The present application relates to the field of computer applications, and in particular, to a search result generation method and an information search system.

The information search system is a system that can provide users with information retrieval services. Taking the search engine commonly used in the Internet as an example, as a search system applied in the Internet domain, the search engine has become an essential auxiliary for users to access the Internet. One of the tools. From the user's point of view, the search engine generally provides a page containing a search box, the user enters a keyword or other search conditions in the search box, and after the browser submits to the search engine, the search engine returns the keyword entered by the user. Information that matches the content.

For the same user search request (such as the search keyword entered by the user during the search), the search engine can often retrieve multiple matching information, which may reach tens to tens of thousands. From the user's point of view, it is often only focused on the top-ranking information in the search results. In this way, when the search engine provides search results to the user, how to sort the information is particularly important, and whether the ranking of the search results is reasonable will directly affect the user experience.

When the search engine sorts the information, it will consider a variety of factors. The reference factors may include the information source, information credibility, user feedback, etc. User feedback is an important factor affecting the ranking of search results. For example, when the search keyword is "China Central Television", 80% of the users clicked on the official homepage of China Central Television, then, from the perspective of user feedback, the search engine has reason to use China Central Television. The official homepage ranks first in the search results for the keyword "China Central Television".

In order to achieve the above effects, in the prior art, the search engine collects the search result and provides the search result to the user according to the user feedback amount of the matching information corresponding to the search keyword, and according to the order of the user feedback. By studying the prior art, the inventors found that the existing search result generation method has the problem that for the newly released information, the initial value of the feedback amount is 0 (or very low), resulting in its ranking lower, due to the lower ranking. It's hard to be noticed by users, so it has been impossible to improve the ranking. On the other hand, individual users can quickly change the amount of feedback by means of some cheating (such as fraudulent clicks), so that the information they publish can rank higher in the search results and affect the normal interests of others. It can be seen that from the user's point of view, the ranking of search results generated by the prior art is unreasonable and has an impact on the user experience.

To solve the above technical problem, the present application provides a search result generation method and an information search system, which can display a more reasonable matching information ranking result to a user and improve the user experience. The technical solution is as follows: The present application provides a search result generation method. The information search system receives the search request, obtains each piece of matching information that matches the search request by searching, and queries the user feedback quantity of the pieces of matching information to further calculate the matching information. The total amount of user feedback of the category; sorting the pieces of matching information according to the size of the total amount of user feedback of the categories to which the matching information belongs, and generating a search result.

The application further provides an information search system, comprising: an information retrieval unit, configured to receive a search request, obtain a matching information matching the search request by searching, and a user feedback amount calculation unit, configured to match each item The user feedback amount of the information is queried, and the total amount of user feedback of the matching information of each category is further calculated; the result generating unit is configured to: according to the total amount of user feedback of the category of the matching information, Sort the matching information to generate search results.

Compared with the prior art, the technical solution provided by the embodiment of the present application is not based on the size of the user feedback of a single piece of information, but is based on the size of the total amount of user feedback of each category of information. In this way, even if the amount of feedback from users who newly post information is small, if the category to which they belong is more concerned by the user, then the piece of information also has the opportunity to be ranked relatively high. On the other hand, the increase in the amount of user feedback for a single piece of information does not directly increase the ranking of the piece of information, but rather increases the ranking of the category of the piece of information, so it can effectively reduce fraudulent means such as fraudulent clicks. The effect of sorting search results.

First, a method for generating a search result according to an embodiment of the present application is described. The method includes: the information search system receives a search request, obtains, by searching, matching pieces of matching information that match the search request; and user feedback of the pieces of matching information. The quantity is queried, and the total amount of user feedback of the category of the matching information is further calculated; and the matching information is sorted according to the size of the total amount of user feedback of the category of the matching information, and the search is generated. result.

In order to make those skilled in the art better understand the technical solutions in the present application, the technical solutions in the embodiments of the present application will be clearly and completely described in the following with reference to the drawings in the embodiments of the present application. The embodiments are only a part of the embodiments of the present application, and not all of them. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present application without departing from the inventive scope shall fall within the scope of the application.

The following is a detailed description of the technical solution provided by the present application by using a network search application as an example. FIG. 1 is a flowchart of a search result generating method according to an embodiment of the present application, including the following steps:

S101. The search engine receives the search request, and obtains matching information that matches the search request by searching. When the user needs to search for information on the network, one or more search conditions are input, and the most commonly used search condition is generally used. The search keyword is a search keyword. Some search engines can support more types of search conditions, such as information release time, information attributes, and the like. In the embodiment of the present application, various search conditions are collectively referred to as search requests. . After the search engine receives the search request, it retrieves the information that matches the search request. The types of information retrieved are different for different search application scenarios. For example, in web search, the retrieved information is a web page; in e-commerce search, the retrieved information is a commodity; in the literature search, the retrieved information is retrieved. Information for journals or papers, etc. The method for retrieving the matching information according to the search request is the same as that of the prior art, and is not described in detail in this embodiment of the present application.

S102: querying the amount of user feedback of each piece of matching information, and further calculating the total amount of user feedback of each category of matching information; corresponding to a search request, the search engine can often retrieve multiple matching information, and search The engine needs to filter and sort the information according to certain principles to facilitate the user's reading.

Among them, user feedback is an important factor affecting the ranking of search results. The basic principle is to rank the information that users are most concerned about at the forefront of search results. In the embodiment of the present application, the user feedback amount is used as a parameter reflecting the user's attention to a certain piece of information. For example, the number of clicks on a webpage link, the number of times a link is bookmarked, etc., can directly reflect the user's attention to the webpage. Therefore, for a webpage, information such as the number of links clicked, the number of times the link is bookmarked, and the like can be used as the webpage. User feedback. In e-commerce, the amount of user feedback of a certain product may include: the volume of the commodity, the amount of the transaction of the commodity, the number of times the commodity is inquired, and the number of times the commodity information is collected. Those skilled in the art can understand that one type of information can be selected to represent the amount of user feedback, and a plurality of types of information can be comprehensively used to represent the amount of user feedback, for example:

User feedback = commodity volume × 0.3 + number of collections × 2

User feedback = product transaction amount × product information was counted + log (commodity volume),

and many more.

The user feedback amount is generally recorded in the user feedback log, and the search engine can obtain the user feedback amount corresponding to each piece of matching information by reading the user feedback log. It can be understood that the search engine can choose to read only the user feedback log for a certain period of time (for example, the last week, the most recent month, etc.) to adapt to the changing user interest points.

Suppose that for a certain search request, the search engine retrieves four matching information and reads the user feedback log, and the user feedback amount corresponding to each matching information is shown in Table 1:

It can be seen from Table 1 that the relationship between the magnitudes of the four feedbacks of the matching information is: matching information 1 > matching information 3 > matching information 2 > matching information 4. If the solution according to the prior art is used, the search results will also be generated in this order and finally presented to the user. In the technical solution of the present application, the user feedback amount corresponding to each piece of matching information needs to be further processed.

Many of the information in the Internet is published according to certain categories. For example, in the portal, the type of webpage may include news, sports, entertainment, finance, etc. In an e-commerce website, the product category includes home, Electrical appliances, clothing, food, etc. Then, for each matching information retrieved by the search engine, it will correspond to a category to which it belongs. In the embodiment of the present application, after obtaining the user feedback amount corresponding to each piece of matching information, first querying the category to which each piece of matching information belongs. For a webpage, the webpage belongs to the category to which the webpage belongs. For example, the webpage containing the "news" field in the webpage path is a news webpage, and the webpage containing the "sports" field in the webpage path is a sports webpage. And so on; for goods, directly query their product information to get the category to which the item belongs.

The total amount of user feedback for matching information for each category is further calculated. For example, in the example of Table 1, the matching information 1 and the matching information 4 belong to "type A", the matching information 2 and the matching information 3 belong to "type B", and the total amount of user feedback of "type A" is 100+. 5=105, the total user feedback of “Type B” is 30+40=70, as shown in Table 2:

S103. Sort each matching information according to the total amount of user feedback of each category in which the matching information belongs, and generate a search result.

As can be seen from Table 2, "Type A" is more concerned by users than "Type B". Therefore, if it is only from the perspective of the total amount of user feedback, the information belonging to "Type A" should be classified as "Type B". The front of the information.

For the matching information 4, the amount of user feedback is small. If the prior art scheme is applied, it is difficult to obtain the ranking of the matching information 4 under normal circumstances. However, the technical solution of the present application is not based on the size of the user feedback of a single piece of information. Although the amount of user feedback of the matching information 4 is small, since it belongs to a type that is of interest, it is generated by the technical solution of the present application. In the search results, the matching information 4 will be ranked in front of the matching information 2 and the matching information 3 (or the matching information 4 will have more chances in front of the matching information 2 and the matching information 3). In this way, even the newly released information has more opportunities to obtain a higher ranking in the search results, and better adapt to the actual needs of users.

Based on Table 1, if someone newly publishes information 5 that matches the search request (assuming that the information 5 belongs to type C), and the user feedback amount reaches 50 in a short time by means of fraudulent clicks, etc. With the prior art solution, this matching information 5 will be ranked directly in the second place in the search results, thereby affecting the normal interests of other information publishers. However, applying the technical solution of the present application, since the total amount of user feedback of the type C belongs to be lower than that of the type A and the type B, even if the information is cheated, the matching information 5 cannot obtain the top ranking. It can be understood that the above examples are only used for illustrative explanation. In practical applications, the information is classified more, and the number of matching information retrieved is also larger. Although individual users can publish one or several pieces of information for themselves. Cheating is used to increase the amount of feedback, but it can't affect the total amount of user feedback in the category of information, which effectively reduces the impact of cheating on the ranking of search results.

It should be noted that, in the above embodiment, the matching information is ranked only from the perspective of the user feedback amount. In an actual application, the search engine can comprehensively consider various factors when generating the search result. . Generally, each factor is used as a weighting parameter, and according to the importance degree of these factors, a weighting coefficient is set for each weighting parameter, and a sorting score is obtained by weighted averaging processing of each weighting parameter, and the search engine finally According to the size of each matching information sorting score, the order of the matching information in the search results is determined.

If the prior art scheme is applied, the greater the amount of user feedback of a single matching information, the greater the weighting value obtained. With the technical solution of the present application, the greater the total amount of user feedback of a category of matching information, the greater the weighting value obtained. According to the results shown in Table 2, the weighting value of the matching information 1 and the matching information 4 in the user feedback amount is larger than the weighting value of the matching information 2 and the matching information 3. Matching information 1 will have a greater chance of achieving a higher ranking than the prior art.

Specifically, the weighting value of the matching information belonging to each category may be calculated according to the ratio of the total amount of user feedback of the matching information of each category. Taking Table 2 as an example, the total amount of user feedback of type A is 105, and the total amount of user feedback of type B is 70, and the ratio is 3:2. The ratio can be further normalized, for example, by dividing the total amount of user feedback for each category by the sum of the user feedbacks for all categories, and the resulting ratio is 0.6:0.4, then 0.6 and 0.4 are respectively The weighting value obtained by the matching information belonging to category A and category B on the parameter of the user feedback amount. It is also possible to divide the total amount of user feedback for each category by the maximum amount of single-class user feedback, and the resulting ratio is 1:0.67, then 1 and 0.67 are the matching information belonging to category A and category B, respectively. The weighted value obtained on this parameter.

The search engine can also sort the total amount of user feedback for each category of matching information, and according to the sorting result, obtain the weighting value of the matching information belonging to each category. as shown in Table 3:

It can be seen that the weighting value obtained by the final information of each category is only related to the order of the total amount of user feedback of this category, and is independent of the specific user feedback total value, that is, for the information belonging to the type E. Only when the total amount of user feedback of type E exceeds 500 will a larger weighting value be obtained to improve the ranking, thereby further reducing the effect of cheating on the ranking of search results.

The above describes two specific examples of calculating the weighting value. According to the principle that “the greater the total amount of user feedback of the category to which the matching information belongs is, the greater the weighting value obtained is,” the person skilled in the art can also The need to use other technical means to calculate the weighting values is also within the scope of this application.

In practical applications, for the comprehensive consideration of various factors, in addition to the weighted form, a hierarchical form can also be adopted. That is, after the matching information is first sorted according to one (or more) factors, the first sorting result is sorted a second time according to one or more other factors.

For the technical solutions proposed by the present application, those skilled in the art can easily think that after sorting each piece of matching information according to the total amount of user feedback of the categories to which the matching information belongs, the matching information may be further determined according to each piece. The amount of user feedback, sorting the matching information under each category.

Taking the data in Table 1 as an example, applying the application technical solution, it can be obtained that “the information belonging to type A should be ranked in front of the information belonging to type B”, that is, the matching information 1 and 4 should be ranked before the matching information 2 and 3. . Further, the matching information of each category is secondarily sorted according to the amount of user feedback of the single matching information, and it can be obtained that the matching information 1 should be ranked before the matching information 4, and the matching information 3 should be ranked before the matching information 2. The final sort result is:

Match information 4, match information 1, match information 3, match information 2.

It can be seen that the above solution ensures that the types of attention can be ranked first. On the other hand, under the premise of the same type, the matching information under each category is further sorted according to the size of the single user feedback. Of course, those skilled in the art can understand that after sorting each piece of matching information according to the total amount of user feedback of the categories to which the matching information belongs, it may also be based on other factors (but one or more). Sort the matching information under the category. And, if necessary, you can further do the third sorting and the fourth sorting according to other factors... This manual is not listed one by one.

The search result generation method of the present application will be described below in combination with several specific application examples.

For example, in the web search application, searching with the keyword "Red Cliff", the search engine will retrieve a number of web pages that match "Red Cliff", and these web pages belong to different categories. By reading the user feedback log for a certain period of time and calculating the total amount of user feedback for each category based on the page category, the results are shown in Table 4:

"Red Cliff" corresponds to a famous ancient battle. Naturally, many matching web pages belong to the "military" and "historical" categories. At the same time, "Red Cliff" often appears in the film or game plot, so there are many matching matches. Web pages belong to the category of "entertainment" and "games". In addition, "Red Cliff" is still a tourist attraction, so there are also some matching pages that belong to the "tourism" category.

Since the amount of user feedback is obtained by reading the user feedback log for a certain period of time, it can reflect the user's focus during this time. For example, "Red Cliff" as a movie has received a lot of attention. Therefore, in the period before and after the film is released, there will be more matching pages belonging to the category of "entertainment" than other categories, and there are high users. Click volume, as shown in Table 4. Applying the technical solution of the present application, if the user searches using the keyword "Red Cliff", the matching webpage belonging to the category of "entertainment" will obtain a higher weight value regardless of the amount of user clicks of the individual webpage. Therefore, it ranks in the top position in the search results, making it easy for users to click through.

The technical solution provided by the application is also applicable to the search application of e-commerce. For example, a user searches for a product with the keyword "notebook", and the search engine may retrieve a product that involves a laptop, a laptop battery, a notebook cooler, or even a conventional notebook. According to the classification of commodity categories by e-commerce websites, laptops may belong to the category of “laptops”, while laptop batteries and notebook coolers belong to the category of “notebook accessories”. As for notebooks in the traditional sense, they may belong to “culture”. "" supplies" or "office supplies" category. By counting the amount of feedback from users, it can be found that at this stage, most of the users who search by "notebook" as keywords are all notebooks, and then the application of the technical solution of the present application belongs to "notebook". This type of product will receive a higher weight value, so that it is ranked higher in the search results, which is convenient for users to click and browse, and for the newly released laptop product information, there are also Opportunities are ranked higher. For traditional notebooks belonging to the category of "cultural goods" or "office supplies", even by cheating (for example, the publisher himself raises the number of inquiry times and collects the product information multiple times), it is impossible to target "notebook". Keyword promotion ranking. Because traditional notebooks are not really concerned by most users who search for "notebooks" (users who really pay attention to traditional notebooks will further search in the scope of "cultural products" or "office supplies", regardless of the technical solution of this application, This is not explained in detail. It can be seen that the search results generated by applying the technical solution of the present application are more consistent with the requirements of most users, and the user experience is effectively improved.

The above two examples are only used for illustrative purposes. The actual Internet information may have a more complete classification level. For example, in the above example, “laptop battery” and “notebook cooler” refer to A single item of information under the "notebook accessories" category. In practical applications, "laptop battery" and "notebook cooler" may also be two sub-categories under the "notebook accessories" category. Then, applying the technical solution provided by the application, the two sub-categories respectively have the corresponding total amount of user feedback. If the user searches within the scope of “notebook accessories”, the products of the two sub-categories are also Different weighting values will be obtained separately. It can be understood that if the user searches within a minimum classification range, the obtained search result is based on the size of the user feedback amount of the single item information under the category.

The application of the technical solution of the present application in webpage search and e-commerce search is described above. It can be understood that this is only two embodiments of the technical solution of the present application. In fact, the technical solutions of the present application can be applied to each Class search requirements, such as book database search, literature database search, etc. And the scope of application is not limited to the Internet domain. Other technologies such as single-machine and local area network can apply the technical solutions provided by this application.

Corresponding to the above method embodiment, the present application further provides an information search system, as shown in FIG. 2, including: an information retrieval unit 210, configured to receive a search request, and obtain various items matching the search request by searching. The user feedback amount calculation unit 220 is configured to query the user feedback amount of each piece of matching information, and further calculate the total amount of user feedback of the matching information of each category; wherein the total amount of user feedback is: The sum of the user feedback amounts of the matching information of the category; the result generating unit 230 is configured to sort the matching information according to the total amount of the user feedback of the categories to which the matching information belongs, and generate a search result.

The user feedback amount calculation unit 220 can query the user feedback amount of each piece of matching information by reading the user feedback log of a specific time period.

As shown in FIG. 3, the result generating unit 230 may include: a sorting score calculation sub-unit 231, configured to calculate the matching items by using a size of a total amount of user feedback of each category of matching information as a weighting parameter. a sorting score of the information; wherein, if the total amount of user feedback of the category to which the first matching information belongs is greater than the total amount of user feedback of the category to which the second matching information belongs, the weighting value of the first matching information is greater than the second matching information The weighting value is generated; the result generating sub-unit 232 is configured to sort the size of the score according to each piece of matching information to generate a search result.

Referring to FIG. 4, the sorting score calculation sub-unit 231 may include: a first weighting value calculation module 2311, configured to obtain, according to the total amount of user feedback of each category of matching information, The weighting value of the matching information can be understood by those skilled in the art. The sorting score calculation sub-unit 231 can further include a second weighting value calculating module 2312, a third weighting value calculating module 2313, ... for The weighting values corresponding to other weighting parameters are calculated.

The weighted average module 2310 is configured to perform weighted averaging processing on the weighting values including the calculation result of the first weighting value calculation module to obtain a ranking score of each piece of matching information.

The first weighting value calculation module 2311 may be specifically configured to calculate a ratio of the total amount of user feedback of each category matching information, and obtain a weighting value of the matching information belonging to each category according to the ratio. It is also possible to sort the total amount of user feedback for each category matching information, and obtain weighting values of matching information belonging to each category according to the sorting result.

As shown in FIG. 5, the result generating unit 230 may further include the following components: a first sorting sub-unit 233, configured to determine, according to the size of the total amount of user feedback of the category to which each piece of matching information belongs. The pieces of matching information are sorted; the second sorting sub-unit 234 is configured to sort the matching information in each category according to the amount of user feedback of the pieces of matching information.

The information search system provided above may be a search engine applied to Internet search, or an information search system applied to search of a single machine or a regional network.

Of course, the amount of user feedback is not necessarily the only factor that ranks search results. Other factors, such as the degree to which the keyword entered by the user matches the information displayed on the web page, the Page Rank value of the web page, etc., can be used together with the user feedback amount as a factor for sorting the search results.

For the convenience of description, the above devices are described separately by function into various units. Of course, the functions of each unit can be implemented in the same software or software and/or hardware in the implementation of the present application.

As can be seen from the description of the above embodiments, those skilled in the art can clearly understand that the present application can be implemented by means of a software plus a necessary universal hardware platform. Based on such understanding, the technical solution of the present application can be embodied in the form of a software product in essence or in the form of a software product, which can be stored in a storage medium such as a ROM/RAM, a disk, A disc or the like includes instructions for causing a computer device (which may be a personal computer, server, or network device, etc.) to perform the methods described in various embodiments of the present application or portions of the embodiments.

The various embodiments in the specification are described in a progressive manner, and the same or similar parts between the various embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method embodiment. The system embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, ie may be located A place, or it can be distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the embodiment. Those of ordinary skill in the art can understand and implement without any creative effort.

This application can be used in a variety of general purpose or special purpose computing system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, small computers, large Computer, decentralized computing environment including any of the above systems or devices, and so on.

The application can be described in the general context of computer-executable instructions executed by a computer, such as a program module. Generally, a program module includes routines, programs, objects, components, data structures, and the like that perform particular tasks or implement particular abstract data types. The present application can also be practiced in a decentralized computing environment in which tasks are performed by remote processing devices that are connected by a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media, including storage devices.

The above description is only a specific embodiment of the present application, and it should be noted that those skilled in the art can also make several improvements and retouchings without departing from the principles of the present application. It should be considered as the scope of protection of this application.

210. . . Information retrieval unit

220. . . User feedback calculation unit

230. . . Result generation unit

231. . . Sort score calculation subunit

232. . . Result generating subunit

233. . . First sorting subunit

234. . . Second sorting subunit

2310. . . Weighted average module

2311. . . First weighting calculation module

2312. . . Second weighted value calculation module

2313. . . Third weighted value calculation module

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the embodiments or the prior art description will be briefly described below. Obviously, the drawings in the following description are only Some embodiments described in the application can also obtain other drawings according to these drawings without any creative labor for those skilled in the art.

1 is a flowchart of a method for generating a search result according to an embodiment of the present application;

2 is a schematic structural diagram of an information search system according to an embodiment of the present application;

3 is a schematic structural diagram of a result generating unit according to an embodiment of the present application;

4 is a schematic structural diagram of a sub-segment calculation sub-unit according to an embodiment of the present application;

FIG. 5 is another schematic structural diagram of a result generating unit according to an embodiment of the present application.

Claims (20)

A computer implementation method for generating search results, comprising: the information search system receiving a search request, obtaining each matching information that matches the search request by searching; and querying the user feedback amount of each piece of matching information Calculating the total amount of user feedback of the category to which the matching information belongs; calculating the first matching information by using the first user feedback corresponding to the first category to which the first matching information of the matching information belongs a first score; using a second user feedback corresponding to the second category to which the second matching information of the pieces of matching information belongs, calculating a second score of the second matching information, the calculation obtaining the The total amount of user feedback of each category of matching information includes querying a first total amount of user feedback of the first category in a predetermined time period and a second total amount of user feedback of the second category; and using the first a score, the second score, the first amount of feedback from the user of the first category, and the second amount of feedback from the user of the second category, Article information and matching the second match of information to sort, search results are generated. According to the computer implementation method of claim 1, wherein the total amount of feedback of the user is: the sum of user feedback amounts of matching information belonging to the category. According to the computer implementation method of claim 1 of the scope of the patent application, wherein The user feedback quantity of the matching information is queried by reading the user feedback log of the user feedback of each search result by reading the record of the predetermined time period, and querying the user feedback quantity of each piece of matching information. . According to the computer implementation method of claim 1, further comprising: sorting the pieces of matching information, wherein sorting the pieces of matching information comprises: using a total amount of user feedback of the category of the matching information a weighting parameter, the ranking score of the matching information is calculated; wherein, if the total amount of user feedback of the third category to which the third matching information belongs is greater than the total amount of user feedback of the fourth category to which the fourth matching information belongs, the first The weighting value of the three matching information is greater than the weighting value of the fourth matching information. According to the computer implementation method of claim 4, wherein the size of the total user feedback of the category of the matching information is used as a weighting parameter, and the specific implementation is: calculating the ratio of the total amount of user feedback of each category of matching information. And based on the ratio, the weighted values of the matching information belonging to each category are calculated. According to the computer implementation method of claim 4, wherein the total amount of user feedback of the category of the matching information is used as a weighting parameter, and the specific implementation is: the total amount of user feedback for each category matching information is performed. Sorting; and based on the sorting, calculating the matching information belonging to each category Weight. According to the computer implementation method of claim 1, the method further includes: matching the one or more matching information in each category according to at least part of one or more user feedback amounts corresponding to one or more pieces of matching information. Sort. The computer-implemented method of claim 1, wherein the search request comprises: a web search request, and/or an e-commerce search request. The computer implementation method of claim 1, wherein when the search request is a webpage search request, the user feedback amount includes: a webpage link click count, and/or a webpage link being bookmarked. The computer implementation method according to claim 1, wherein the search request includes an e-commerce search request, and the user feedback amount includes: a commodity volume, a commodity transaction amount, a product inquiry number, and/or a product information collection number . An information search system, comprising: one or more processors; a memory; an information retrieval unit stored in the memory and executable by the one or more processors, the information retrieval unit Receiving a search request, obtaining, by searching, matching pieces of matching information that match the search request; the user feedback amount calculating unit is stored in the memory and can be Executing by the processor or more, the user feedback amount calculation unit is configured to query the amount of user feedback corresponding to the pieces of matching information, and calculate the total amount of user feedback of the category to which the pieces of matching information belong, under the category The user feedback total includes a sum of user feedbacks corresponding to one or more pieces of matching information of the pieces of matching information belonging to the category; and a result generating unit stored in the memory and readable by the one or more Executing, the result generating unit is configured to: calculate a ranking score of each piece of matching information by using a size of the total amount of user feedback of the category of the matching information, and if the first matching information belongs to The total amount of user feedback of the first category is greater than the total amount of user feedback of the second category to which the second matching information belongs, and the weighting value of the first matching information is greater than the weighting value of the second matching information; a score, sorting the pieces of matching information; generating a search result according to the sorting score of the pieces of matching information. According to the information search system of claim 11, wherein the user feedback amount calculation unit calculates a matching information of the pieces of matching information by reading a user feedback log of the user feedback for a specific time period. User feedback. According to the information search system of claim 11, the method further includes: a first weighting value calculation module, configured to obtain one of the matching information according to the total amount of user feedback of the category of the matching information Weighted value of each category to which the information belongs; and a weighted average module for weighted averaging of the weighted values The sorting score to the matching information. According to the information search system of claim 13, wherein the first weighting value calculation module is configured to calculate a ratio of total user feedback of each category of matching information, and according to the ratio, obtain a matching belonging to each category. The weighted value of the information. According to the information search system of claim 13, wherein the first weighting value calculation module is configured to sort the total amount of user feedback of each category matching information, and according to the ranking, obtain a matching belonging to each category. The weighted value of the information. According to the information search system of claim 11, wherein the result generating unit comprises: a first sorting subunit, configured to match the strips according to the total amount of user feedback of the categories to which the respective matching information belongs The information is sorted; and the second sorting sub-unit is configured to: according to the corresponding one or more user feedback quantity of the one or more pieces of matching information in the pieces of matching information, the pieces of matching information in the category The one or more pieces of matching information in the ranking are sorted. A non-transitory storage medium, comprising computer executable instructions, when the computer device executes the instruction, the action performed by the instruction comprises: the information search system receives the search request, and obtains a matching match matching the search request by searching News; Querying the amount of user feedback of each piece of matching information; calculating the total amount of user feedback of the category of the matching information; using the first category corresponding to the first matching information of the pieces of matching information a user feedback, calculating a first score of the first piece of matching information; calculating the second piece by using a second user feedback corresponding to the second category of the second piece of matching information of the pieces of matching information Matching the second score of the information, the calculated total user feedback of the category to which the matching information belongs includes the first total amount of user feedback for the first category in the predetermined time period and the user feedback of the second category The second total amount is queried; and the first total value, the second score, the first total amount of user feedback of the first category, and the second total amount of user feedback of the second category are used, Sorting the first matching information and the second matching information to generate a search result. According to the non-transitory storage medium of claim 17, wherein the user feedback amount of each piece of matching information is queried by: reading the record of the predetermined time period corresponding to the user feedback of each search result The user feedback log queries the user feedback amount of each piece of matching information. According to the non-transitory storage medium of claim 17 of the patent application, the action further comprises sorting the pieces of matching information, wherein the sorting of the pieces of matching information comprises: Calculating a ranking score of each piece of matching information by using a total amount of user feedback of the category of the matching information as a weighting parameter; wherein, if the total amount of user feedback of the third category to which the third matching information belongs is greater than the fourth The weight of the third matching information is greater than the weighting value of the fourth matching information. According to the non-transitory storage medium of claim 17 of the patent application, the action further comprises: at least part of the one or more user feedback quantity according to one or more pieces of matching information, for the one or More matching information to sort.