CN105528430A - Method and device for determining weights of search terms - Google Patents

Abstract

The invention discloses a method and a device for determining the weight of a search item. The method includes: obtaining a collection of search data pairs; wherein the search data pairs include: search words and corresponding search result content; according to the search data pair collection, it is determined that each search item included in each search term is included in the search result content Probability of occurrence: Determine the weight of each search item according to the probability of each search item appearing in the search result content. Through the technical solution of the present invention, the importance of the content of each search item appearing in the search results can be fully considered, and the search data pair fragments and the probability of each search item included in the fragments appearing in the search results can be excavated on a large scale, and according to The mined probability determines the weight of each search term.

Description

A method and device for determining the weight of a search term

technical field

The present invention relates to the technical field of data processing, in particular to a method and device for determining the weight of a search item.

Background technique

With the development of computer network technology, it is more and more common to search for data through the Internet, and as the amount of network information becomes larger and larger, users can search for more and more data. To provide users with the most accurate information and improve search efficiency has become a problem to be solved by major search engines.

In the prior art, search results are given according to the weight of each search term (term) in the search word, so as to provide users with the most accurate search result information among massive data. However, how to calculate the weight of each search item in the search term to give accurate search results is an urgent problem to be solved.

Contents of the invention

In view of the above problems, the present invention is proposed to provide a method and device for determining weights of search terms that overcome the above problems or at least partly solve the above problems.

According to one aspect of the present invention, a method for determining the weight of a search term is provided, the method comprising:

Obtain a collection of search data pairs; wherein the search data pairs include: search terms and corresponding search result content;

According to the collection of search data pairs, determine the probability that each search item contained in each search term appears in the content of the search result;

The weight of each search item is determined according to the probability of each search item appearing in the search result content.

Optionally, according to the set of search data pairs, determining the probability that each search item contained in each search word appears in the search result content includes:

For each search data pair in the search data pair set, determine each continuous segment that can be obtained from the search term of each search data pair;

Use the fragment as the key, and use whether each search item contained in the fragment appears in the search result content corresponding to the search word where the fragment is located as the value, and output the key-value pair;

In the output key-value pair set, the probability of each search item in the key appearing in the search result content is obtained by counting the values in each key-value pair with the same key.

Optionally, said obtaining a collection of search data pairs includes:

Get search data pairs from search engine click logs to form a collection.

Optionally, taking as a value whether each search item included in the segment appears in the search result content corresponding to the search term where the segment is located includes:

Determine the number N of search items contained in the fragment, where N is a natural number;

An N-bit binary number is used as the value, and two possible values of each binary number indicate whether the corresponding search item appears in the corresponding search result content.

Optionally, obtaining the probability that each search item in the key appears in the search result content by counting the values in each key-value pair with the same key includes:

For each search item in the same key, count the number of times the search item appears in the search result content in the value of each key-value pair with the same key, and record it as the first value;

Counting the number of key-value pairs with the same key as the second value;

According to the ratio of the first numerical value to the second numerical value, the probability of the search item appearing in the search result content is determined.

Optionally, taking whether each search item included in the segment appears in the search result content corresponding to the search term where the segment is located as a value includes: determining the number N of search items contained in the segment, where N is a natural number; Use an N-bit binary number as the value, and when each binary number takes a value of 1, it means that the corresponding search item appears in the corresponding search result content, and when it takes a value of 0, it means that it does not appear;

Obtaining the probability of each search item in the key appearing in the search result content by counting the values in each key-value pair with the same key includes: for each search item in the same key, counting the search item in the search result The value of each key-value pair with the same key is 1 times, which is recorded as the first value;

Counting the number of key-value pairs with the same key as the second value;

According to the ratio of the first numerical value to the second numerical value, the probability of the search item appearing in the search result content is determined.

Optionally, the search result content is any of the following;

the title of the search results page;

A summary of the search results page;

The entire content of the search results page.

Optionally, the method further includes:

Save each search term and the corresponding weight in the weight database;

When a search term is received, the search term is divided into multiple search terms;

Acquiring the respective weights corresponding to the plurality of search items from the weight database;

The search process is performed according to the respective weights corresponding to the multiple search items.

According to another aspect of the present invention, a device for determining the weight of a search term is provided, wherein the device includes:

The data acquisition unit is adapted to acquire a set of search data pairs; wherein the search data pairs include: search terms and corresponding search result content;

The probability determination unit is adapted to determine the probability that each search item included in each search term appears in the search result content according to the set of search data pairs;

The weight determination unit is adapted to determine the weight of each search item according to the probability of each search item appearing in the search result content.

Optionally, the probability determination unit further includes:

The key-value pair output unit is adapted to, for each search data pair in the search data pair set, determine each continuous segment that can be obtained from the search term of each search data pair; use the segment as a key, and use each search segment contained in the segment Whether the item appears in the search result content corresponding to the search word where the fragment is located is the value, and the key-value pair is output;

The statistical unit is adapted to obtain the probability of each search item in the key appearing in the search result content by counting the values in each key-value pair with the same key in the output key-value pair set.

Optionally, the data obtaining unit is adapted to obtain search data pairs from search engine click logs to form a set.

Optionally, the key-value pair output unit is adapted to determine the number N of search items contained in the segment, where N is a natural number; an N-bit binary number is used as the value, and two types of each binary number are used Possible values indicate whether the corresponding search item appears in the corresponding search result content.

Optionally, the statistical unit is adapted to, for each search item in the same key, count the number of times the search item appears in the search result content in the value of each key-value pair with the same key , recorded as the first value;

Counting the number of key-value pairs with the same key as the second value; determining the probability of the search item appearing in the search result content according to the ratio of the first value to the second value.

Optionally, the key-value pair output unit is adapted to determine the number N of search items contained in the segment, where N is a natural number; an N-bit binary number is used as the value, and each binary number takes a value of 1 When means that the corresponding search item appears in the corresponding search result content, when the value is 0, it means that it does not appear;

The statistical unit is adapted to, for each search item in the same key, count the number of times that the search item takes a value of 1 among the values of each key-value pair with the same key, and record it as the first value; The number of key-value pairs with the same key as the above is recorded as the second value; according to the ratio between the first value and the second value, the probability of the search item appearing in the search result content is determined.

Optionally, the search result content is any of the following;

the title of the search results page;

A summary of the search results page;

The entire content of the search results page.

Optionally,

The weight determination unit is further adapted to save each search item and the corresponding weight in a weight database;

The device further includes:

a storage unit adapted to store the weight database;

The search processing unit is adapted to divide the search term into multiple search items when receiving the search term; obtain the respective weights corresponding to the multiple search items from the weight database; weights for search processing.

According to the technical scheme of the present invention, a set of search data pairs is obtained, and according to the set of search data pairs, the probability of each search item contained in each search word appearing in the search result content is determined, and according to the probability of each search item appearing in the search result content Probability, which determines the weight of each search term. Through the technical solution of the present invention, the importance of the content of each search item appearing in the search results can be fully considered, and the fragments in the search data and the probability of each search item contained in the fragments appearing in the search results can be mined on a large scale, and according to the mining to determine the weight of each search term.

The above description is only an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention, it can be implemented according to the contents of the description, and in order to make the above and other purposes, features and advantages of the present invention more obvious and understandable , the specific embodiments of the present invention are enumerated below.

Description of drawings

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 drawings are only for the purpose of illustrating a preferred embodiment and are not to be considered as limiting the invention. Also throughout the drawings, the same reference numerals are used to designate the same components. In the attached picture:

FIG. 1 shows a flowchart of a method for determining the weight of a search item according to an embodiment of the present invention;

Fig. 2 shows a schematic diagram of a device for determining the weight of a search item according to an embodiment of the present invention;

Fig. 3 shows a schematic diagram of a probability determining unit of a device for determining the weight of a search item according to another embodiment of the present invention;

Fig. 4 shows a schematic diagram of an apparatus for determining the weight of a search item according to another embodiment of the present invention.

detailed description

Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

Fig. 1 shows a flow chart of a method for determining the weight of a search item according to an embodiment of the present invention. As shown in Figure 1, the method includes:

Step S110, obtaining a set of search data pairs; where the search data pairs include: search terms and corresponding search result content.

The obtained set of search data pairs includes one or more search data pairs.

Step S120, according to the set of search data pairs, determine the probability that each search term included in each search term appears in the content of the search result.

Step S130, determining the weight of each search item according to the probability of each search item appearing in the search result content.

The method shown in Figure 1 provides an accurate calculation method for the occurrence probability of each search item in the search word in the search result, and the weight of each search item can be further determined according to the probability obtained by this method, so that according to The weight of each search item gives the search results, which greatly improves the accuracy of the search engine.

In one embodiment of the present invention, the step S120 in the method shown in FIG. 1 determines the probability that each search term contained in each search word appears in the search result content according to the set of search data pairs, including:

Step S121, for each search data pair in the search data pair set, determine each continuous segment that can be obtained from the search word of each search data pair.

In step S122, a key-value pair is output using a segment as a key and whether each search term included in the segment appears in the search result corresponding to the search term where the segment is located as a value.

Step S123, in the output key-value pair set, by counting the values in each key-value pair with the same key, the probability of each search item in the key appearing in the search result content is obtained.

In one embodiment of the present invention, obtaining a set of search data pairs in step S110 of the method shown in FIG. 1 includes: obtaining a set of search data pairs from search engine click logs.

Obtaining search data pairs from search engine click logs to form a set can use a large amount of data, and data acquisition is easy, and because it takes into account the correlation between user requests and click results, it is more in line with user needs and has a high degree of relevance.

Here, in each pair of search data obtained from the search engine click log, the search word is the search query word entered by the user, and the content of the search result is a search result finally clicked by the user. It can be seen that the collection of search data pairs obtained from search engine click logs meets the user's expectations for search results.

In one embodiment of the present invention, in step S122, taking whether each search item included in the segment appears in the search result content corresponding to the search term where the segment is located as a value includes:

Step S1221, determine the number N of search items contained in the segment, where N is a natural number.

In step S1222, an N-bit binary number is used as the value, and two possible values of each binary number are used to indicate whether the corresponding search item appears in the corresponding search result content.

For example, if a segment contains three search items, a three-bit binary number is used as a value, and 1 indicates that the corresponding search item appears in the search result of the search data pair, and 0 indicates that it does not appear. A value of 110 indicates that the first search item and the second search item in the segment appear in the search results of the search data pair, and the third search item does not appear in the search results of the search data pair.

In one embodiment of the present invention, the probability of each search item in the key appearing in the search result content obtained by counting the values in each key-value pair with the same key as described in step S123 includes:

Step S1231, for each search item in the same key, count the number of times the search item appears in the search result content in the values of the key-value pairs with the same key, and record it as the first value.

Step S1232, count the number of key-value pairs with the same key, and record it as the second value.

Step S1233, according to the ratio of the first value to the second value, determine the probability of the search item appearing in the search result content.

Taking the segment "ABC" as an example, there are the following key-value pairs: [ABC, 111] [ABC, 100] [ABC, 011] [ABC, 101] [ABC, 110].

The probability that A search item appears in the search result = 4/5 = 0.8;

Probability of B search item appearing in the search result=3/5=0.6;

Probability of C search term appearing in the search result = 3/5 = 0.6.

In one embodiment of the present invention, in step S122, taking whether each search item included in the segment appears in the search result content corresponding to the search term where the segment is located as a value includes:

Step S1221', determine the number N of search items contained in the segment, where N is a natural number.

In step S1222', an N-bit binary number is used as the value, and when each binary number takes a value of 1, it indicates that the corresponding search item appears in the corresponding search result content, and when it takes a value of 0, it indicates that it does not appear.

Then described in step S123, obtain the probability that each search item in the key appears in the search result content by counting the values in each key-value pair with the same key as follows:

Step S1231', for each search item in the same key, count the number of times the search item takes a value of 1 in the values of each key-value pair with the same key, and record it as the first numerical value.

Step S1232', count the number of key-value pairs with the same key, and record it as the second value.

Step S1233', according to the ratio of the first value to the second value, determine the probability of the search item appearing in the search result content.

In one embodiment of the present invention, the search result content in the method shown in Figure 1 is any of the following: the title of the search result page clicked by the user; the summary of the search result page clicked by the user; the search result page clicked by the user all content.

For example, a collection of search data pairs is obtained from search engine click logs, taking a pair of search data pairs whose search word is "ABCDE" and title content of the search result page is "FGACDHJ" as an example. Consecutive segments obtained from the search term "ABCDE" include:

1. Fragment containing 1 search term: A, B, C, D, E.

2. Fragment containing 2 search terms: AB, BC, CD, DE.

3. A fragment containing 3 search terms: ABC, BCD, CDE.

4. A fragment containing 4 search terms: ABCD, BCDE.

5. Fragment containing 5 search terms: ABCDE.

Using each segment as a key, and using whether each search item included in the segment appears in the search result content of the search data pair as a value, output a key-value pair about the search data pair. In this example, if the search items that appear in the search results are A, C, and D, it is determined that the values corresponding to A, C, and D are 1, and the values corresponding to the contents of other search items that do not appear are 0. To process the search term and the corresponding search result content, the following key-value pairs can be output:

1. Fragment containing 1 search term: A:1,B:0,C:1,D:1,E:0.

2. Fragment containing 2 search terms: AB:10, BC:01, CD:11, DE:10.

3. A fragment containing 3 search terms: ABC:101, BCD:011, CDE:110.

4. A fragment containing 4 search terms: ABCD:1011, BCDE:0110.

5. Fragment containing 5 search terms: ABCDE:10110.

The above processing is performed on each pair of search data pairs, and after processing all search words and corresponding search result contents in the search data pair set, a key-value pair set is obtained. In the key-value pair set, count the values in each key-value pair with the same key, and for each search item in the same key, count the value of the search item in the values of each key-value pair with the same key The number of times of 1 is recorded as the first value; the number of key-value pairs with the same key is counted as the second value; according to the ratio of the first value to the second value, determine the occurrence of the search item in the search result content probability. Taking A, B, and C as examples, assuming that in each key-value pair with the same key "ABC", the probability of each search item appearing in the search result content is counted, and data similar to the following can be obtained:

ABC: 0.7, 0.3, 0.9.

The data indicates the following meaning: among all the search data pairs containing the segment "ABC", the probability of including A in the clicked search result is 0.7, the probability of containing B is 0.3, and the probability of containing C is 0.9. Therefore, it can be considered that the importance of A and C is relatively high, while the importance of B is relatively low.

In one embodiment of the present invention, each search item and the corresponding weight are stored in the weight database, then on the basis of the above, the method further includes:

Step S140, when a search term is received, the search term is divided into multiple search items.

Step S150, acquiring the respective weights corresponding to the multiple search items from the weight database.

In step S160, search processing is performed according to the weights corresponding to the plurality of search items.

Use the obtained probability to calculate the weight of each search item in the segment. Because the probability calculation process takes into account the importance of each search item in the search result, the weight is more in line with user needs and has high accuracy. Save the obtained weight to the weight database In the online search process, using this weight for search processing can effectively improve the search quality of the search engine.

FIG. 2 shows a schematic diagram of an apparatus for determining the weight of a search item according to an embodiment of the present invention. As shown in FIG. 2 , the apparatus 200 for determining the weight of a search item includes:

The data acquiring unit 210 is adapted to acquire a set of search data pairs; wherein the search data pairs include: search terms and corresponding search result content.

The probability determination unit 220 is adapted to determine the probability that each search item included in each search term appears in the content of the search result according to the set of search data pairs.

The weight determining unit 230 is adapted to determine the weight of each search item according to the probability of each search item appearing in the search result content.

Fig. 3 shows a schematic diagram of a probability determination unit of an apparatus for determining the weight of a search item according to another embodiment of the present invention. As shown in Fig. 3, the probability determination unit 220 further includes:

A key-value pair output unit 221 and a statistics unit 222 .

The key-value pair output unit 221 is adapted to, for each search data pair in the search data pair set, determine each continuous segment that can be obtained from the search words of each search data pair; use the segment as a key, and use each segment contained in the segment Whether the search item appears in the search result content corresponding to the search word where the fragment is located is the value, and the key-value pair is output.

The statistical unit 222 is adapted to obtain the probability that each search item in the key appears in the search result content by counting the values in each key-value pair with the same key in the output key-value pair set.

In one embodiment of the present invention, the data acquisition unit 210 is adapted to acquire the search data set from the click log of the search engine.

In one embodiment of the present invention, the key-value pair output unit 221 is adapted to determine the number N of search items contained in the segment, where N is a natural number; an N-bit binary number is used as the value, and each bit of binary The two possible values of the number indicate whether the corresponding search item appears in the corresponding search result content.

In one embodiment of the present invention, the statistical unit 222 is adapted to, for each search item in the same key, count the search item in the value of each key-value pair with the same key as appearing in the content of the search result The number of times, recorded as the first value; counting the number of key-value pairs with the same key, recorded as the second value; according to the ratio of the first value and the second value, determine that the search item appears in the search result content The probability.

For example, the key-value pair output unit 221 is adapted to determine the number N of search items contained in the segment, and N is a natural number; the binary number of N bits is used as the value, and when each bit of the binary number takes a value of 1, it represents the corresponding The search item of appears in the corresponding search result content, and a value of 0 indicates that it does not appear.

Correspondingly, the statistical unit 222 is suitable for each search item in the same key, and counts the number of times the search item takes a value of 1 in the values of each key-value pair with the same key, and records it as the first numerical value; The number of key-value pairs with the same key is recorded as the second value; according to the ratio of the first value to the second value, the probability of the search item appearing in the search result content is determined.

In an embodiment of the present invention, the content of the search result is any of the following;

the title of the search results page;

A summary of the search results page;

The entire content of the search results page.

FIG. 4 shows a schematic diagram of an apparatus for determining the weight of a search item according to another embodiment of the present invention. As shown in FIG. 4 , the apparatus 300 for determining the weight of a search item includes: a data acquisition unit 310, a probability determination unit 320 , a weight determination unit 330 , a storage unit 340 and a search processing unit 350 .

Wherein, the data acquisition unit 310, the probability determination unit 320, and the weight determination unit 330 are correspondingly the same as the data acquisition unit 210, the probability determination unit 220, and the weight determination unit 230 described above, and will not be repeated here.

In this embodiment, the weight determining unit 330 is further adapted to save each search item and the corresponding weight in the weight database;

a storage unit 340, adapted to store the weight database;

The search processing unit 350 is adapted to divide the search term into multiple search terms when receiving the search term; obtain weights corresponding to the multiple search terms from the weight database; The corresponding weights are searched for.

It should be noted that the embodiments of the apparatus shown in FIG. 2 to FIG. 4 are correspondingly the same as the embodiments of the method shown in FIG. 1 above, which have been described in detail above and will not be repeated here.

To sum up, according to the technical solution of the present invention, a set of search data pairs is obtained, and according to the set of search data pairs, the probability of each search item included in each search term appearing in the search result content is determined, and according to the search term of each search item The probability of occurrence in the result content determines the weight of each search item and saves it in the weight database. The present invention obtains the set of search data pairs from the search engine click log, which can use a large amount of data and is easy to obtain data, and because it takes into account the correlation between user requests and click results, it is more in line with user needs and has a high degree of correlation. Through the technical solution of the present invention, the importance of the content of each search item appearing in the search results can be fully considered, and the search data pair fragments and the probability of each search item included in the fragments appearing in the search results can be excavated on a large scale. At the same time, Use the obtained probability to calculate the weight of each search item in the segment. The obtained weight is more in line with user needs and has high accuracy. The obtained weight is saved in the weight database. During the online search process, using this weight for search processing can effectively improve Search engine search quality.

It should be noted:

The algorithms and displays presented herein are not inherently related to any particular computer, virtual appliance, or other device. Various general purpose devices can also be used with the teachings based on this. The structure required to construct such an apparatus will be apparent from the foregoing description. Furthermore, the present invention is not specific to any particular programming language. It should be understood that various programming languages can be used to implement the contents of the present invention described herein, and the above description of specific languages is for disclosing the best mode of the present invention.

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

Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, in order to streamline this disclosure and to facilitate an understanding of one or more of the various inventive aspects, various features of the invention are sometimes grouped together in a single embodiment, figure, or its description. This method of disclosure, however, is not to be interpreted as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the Detailed Description are hereby expressly incorporated into this Detailed Description, with each claim standing on its own as a separate embodiment of this invention.

Those skilled in the art can understand that the modules in the device in the embodiment can be adaptively changed and arranged in one or more devices different from the embodiment. Modules or units or components in the embodiments may be combined into one module or unit or component, and furthermore may be divided into a plurality of sub-modules or sub-units or sub-assemblies. All features disclosed in this specification (including accompanying claims, abstract and drawings) and any method or method so disclosed may be used in any combination, except that at least some of such features and/or processes or units are mutually exclusive. All processes or units of equipment are combined. Each feature disclosed in this specification (including accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.

Furthermore, those skilled in the art will understand that although some embodiments described herein include some features included in other embodiments but not others, combinations of features from different embodiments are meant to be within the scope of the invention. and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.

The various component embodiments of the present invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art should understand that a microprocessor or a digital signal processor (DSP) can be used in practice to implement some or all functions of some or all of the components in the device for determining the weight of a search item according to an embodiment of the present invention . The present invention can also be implemented as an apparatus or an apparatus program (for example, a computer program and a computer program product) for performing a part or all of the methods described herein. Such a program for realizing the present invention may be stored on a computer-readable medium, or may be in the form of one or more signals. Such a signal may be downloaded from an Internet site, or provided on a carrier signal, or provided in any other form.

It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In a unit claim enumerating several means, several of these means can be embodied by one and the same item of hardware. The use of the words first, second, and third, etc. does not indicate any order. These words can be interpreted as names.

Claims (10)

1. A method of determining the weight of a search term, wherein the method comprises: Obtain a collection of search data pairs; wherein the search data pairs include: search terms and corresponding search result content; According to the collection of search data pairs, determine the probability that each search item contained in each search term appears in the content of the search result; The weight of each search item is determined according to the probability of each search item appearing in the search result content. 2. The method according to claim 1, wherein, according to the set of search data pairs, determining the probability that each search item included in each search word appears in the search result content comprises: For each search data pair in the search data pair set, determine each continuous segment that can be obtained from the search term of each search data pair; Use the fragment as the key, and use whether each search item contained in the fragment appears in the search result content corresponding to the search word where the fragment is located as the value, and output the key-value pair; In the output key-value pair set, the probability of each search item in the key appearing in the search result content is obtained by counting the values in each key-value pair with the same key. 3. The method according to claim 1 or 2, wherein said obtaining a collection of search data pairs comprises: Get search data pairs from search engine click logs to form a collection. 4. The method according to any one of claims 1-3, wherein said taking whether each search item included in the segment appears in the search result content corresponding to the search word where the segment is located as a value includes: Determine the number N of search items contained in the fragment, where N is a natural number; An N-bit binary number is used as the value, and two possible values of each binary number indicate whether the corresponding search item appears in the corresponding search result content. 5. The method according to any one of claims 1-4, wherein, the probability that each search item in the key appears in the search result content is obtained by counting the values in each key-value pair identical to the key include: For each search item in the same key, count the number of times the search item appears in the search result content in the value of each key-value pair with the same key, and record it as the first value; Counting the number of key-value pairs with the same key as the second value; According to the ratio of the first numerical value to the second numerical value, the probability of the search item appearing in the search result content is determined. 6. The method of any one of claims 1-5, wherein, Said taking whether each search item included in the segment appears in the search result content corresponding to the search word where the segment is located as a value includes: determining the number N of search items contained in the segment, N being a natural number; The binary number is used as the value, and when each binary number takes a value of 1, it means that the corresponding search item appears in the corresponding search result content, and when it takes a value of 0, it means that it does not appear; Obtaining the probability of each search item in the key appearing in the search result content by counting the values in each key-value pair with the same key includes: for each search item in the same key, counting the search item in the search result The value of each key-value pair with the same key is 1 times, which is recorded as the first value; Counting the number of key-value pairs with the same key as the second value; According to the ratio of the first numerical value to the second numerical value, the probability of the search item appearing in the search result content is determined. 7. The method according to any one of claims 1-6, wherein the search result content is any one of the following; the title of the search results page; A summary of the search results page; The entire content of the search results page. 8. The method of any one of claims 1-7, further comprising: Save each search term and the corresponding weight in the weight database; When a search term is received, the search term is divided into multiple search terms; Acquiring the respective weights corresponding to the plurality of search items from the weight database; The search process is performed according to the respective weights corresponding to the multiple search items. 9. An apparatus for determining the weight of a search term, wherein the apparatus comprises: The data acquisition unit is adapted to acquire a set of search data pairs; wherein the search data pairs include: search terms and corresponding search result content; The probability determination unit is adapted to determine the probability that each search item included in each search term appears in the search result content according to the set of search data pairs; The weight determination unit is adapted to determine the weight of each search item according to the probability of each search item appearing in the search result content. 10. The device according to claim 9, wherein the probability determination unit further comprises: The key-value pair output unit is adapted to, for each search data pair in the search data pair set, determine each continuous segment that can be obtained from the search term of each search data pair; use the segment as a key, and use each search segment contained in the segment Whether the item appears in the search result content corresponding to the search word where the fragment is located is the value, and the key-value pair is output; The statistical unit is adapted to obtain the probability of each search item in the key appearing in the search result content by counting the values in each key-value pair with the same key in the output key-value pair set.