Method, device, electronic device and storage medium for determining associated words

Abstract

The present disclosure relates to a method, device, electronic device and storage medium for determining associated words, and belongs to the field of Internet technology. The method includes: based on multiple search processes for target businesses, obtaining multiple search statements, the search statements include keywords and at least one word of the target business; based on the positions of the keywords and words in the search statements to which they belong, determining the target association between any keyword and any word; among the words in the multiple search statements, determining the words whose target association with the keywords meets the target conditions as associated words of the target business. Since the target association can reflect the degree of association between the words and the keywords, and the degree of association between the words and the keywords can reflect the degree of association between the words and the target business, the words whose target association with the keywords meets the target conditions are determined as associated words of the target business, thereby improving the accuracy of the determined associated words.

Description

Technical Field

[0001] The present disclosure relates to the field of Internet technology, and in particular to a method, device, electronic device and storage medium for determining associated words. Background Art

[0002] With the rapid development of Internet technology and the gradual expansion of the network scale, all walks of life will promote their own business on the Internet. When the business party promotes its business, it usually needs to use words related to the business.

[0003] In the related art, a manual screening method is used to determine the associated words related to a certain business of the business party. However, since the manual screening method only relies on human subjective feelings, the accuracy of the determined associated words is low. Summary of the invention

[0004] The present disclosure provides a method, device, electronic device and storage medium for determining associated words, which can improve the accuracy of determined associated words.

[0005] According to one aspect of an embodiment of the present disclosure, a method for determining an associated word is provided, the method comprising:

[0006] Based on multiple search processes for the target business, multiple search statements are obtained, wherein the search statements include a keyword of the target business and at least one word;

[0007] Determining a target association degree between any of the keywords and any of the words based on the positions of the keywords and the words in the search sentences to which they belong, wherein the target association degree indicates the degree of association between the words;

[0008] Among the words in the plurality of search sentences, words whose target relevance with the keyword satisfies a target condition are determined as associated words of the target business.

[0009] In the disclosed embodiment, when determining the associated words of the target business, the search sentences in the search process for the target business are taken into consideration, and the target association between the keywords and words of the target business is determined based on the positions of the keywords and other words of the target business in the search sentences. Since the target association can reflect the degree of association between the words and the keywords, and the degree of association between the words and the keywords can reflect the degree of association between the words and the target business, the words whose target association with the keywords meets the target conditions are determined as the associated words of the target business, thereby improving the accuracy of the determined associated words.

[0010] Optionally, determining the target association between any of the keywords and any of the words based on the positions of the keywords and the words in the search statements to which they belong includes:

[0011] Determining a first correlation between any of the keywords and any of the words in the same search statement;

[0012] Determining a second degree of association between any of the keywords and any of the words in different search statements;

[0013] Based on the first degree of association and the second degree of association, a target degree of association between any of the keywords and any of the words is determined.

[0014] In the disclosed embodiment, when mining associated words of the target business, it is taken into account that there is a close connection between words in the same search statement, and there is also a close connection between words in different search statements of the same business. Therefore, the first correlation between the keywords and words in the same search statement and the second correlation between the keywords and words in different search statements are determined. Subsequently, it is determined whether to use a certain word as an associated word of the target business based on the first correlation and the second correlation. This is conducive to mining associated words with a strong correlation with the target business, thereby improving the accuracy of the determined associated words.

[0015] Optionally, determining the second association between any of the keywords and any of the words in different search statements includes:

[0016] Based on a plurality of search sentences searched within a target time period, a second degree of association between any of the keywords and any of the words in different search sentences is determined.

[0017] In the embodiment of the present disclosure, since the degree of correlation between words in different search statements searched within the target time period is higher, the second degree of correlation between the keywords and other words is determined in the different search statements searched within the target time period, taking into account the impact of the search time period on the degree of correlation between words in different search statements. This is conducive to mining associated words that are more closely related to the target business, thereby improving the accuracy of the determined associated words.

[0018] Optionally, determining the second association between any of the keywords and any of the words in different search statements includes:

[0019] Determining a second degree of association between any of the keywords and any of the words in the different search statements based on a search time interval between the different search statements;

[0020] The second correlation degree is negatively correlated with a search time interval, and the search time interval refers to an interval between search time points of different search statements.

[0021] In the disclosed embodiment, the shorter the search time interval between different search statements, the higher the correlation between the words in the two search statements, and the longer the search time interval between different search statements, the lower the correlation between the words in the two search statements. Therefore, the second correlation between the keywords and words in different search statements is set to be negatively correlated with the search time interval between the search statements. When determining the second correlation, the influence of the search time interval between the search statements is taken into account, which is conducive to improving the accuracy of the second correlation.

[0022] Optionally, the method further comprises:

[0023] Determine a third degree of association between any of the keywords in the search statement and any of the corresponding words in the search results, each of the search statements corresponding to at least one search result;

[0024] The determining of the target association between any of the keywords and any of the words based on the positions of the keywords and the words in the corresponding search sentences includes:

[0025] Determining a fourth degree of association between any of the keywords and any of the words based on positions of the keywords and the words in the search sentence to which they belong;

[0026] Based on the third degree of association and the fourth degree of association, a target degree of association between any of the keywords and any of the words is determined.

[0027] In the disclosed embodiment, when mining associated words of the target business, considering that there is a close connection between the words in the search statement and the words in the search results, the third degree of association between the keywords in the search statement and the corresponding words in the search results is determined, and then the third degree of association and the fourth degree of association are combined to determine whether to use the word as an associated word of the target business. This is conducive to mining associated words that are more strongly associated with the target business, thereby improving the accuracy of the determined associated words.

[0028] Optionally, determining a third degree of association between any of the keywords in the search statement and any term in the corresponding search result includes:

[0029] Obtaining a search correlation between the search statement and the corresponding search result, wherein the search correlation indicates a correlation degree between the search result and the corresponding search statement;

[0030] Based on the search relevance, a third relevance between any of the keywords in the search statement and any term in the corresponding search result is determined, and the third relevance is positively correlated with the search relevance.

[0031] In the disclosed embodiment, since the higher the correlation between the search statement and the search results, the higher the correlation between the words in the search statement and the words in the search results, and the lower the correlation between the search statement and the search results, the lower the correlation between the words in the search statement and the words in the search results, the third correlation between the keywords in the search statement and the corresponding words in the search results is set to be positively correlated with the corresponding search correlation, and the influence of the correlation between the search statement and the search results is taken into account when determining the third correlation, which is conducive to improving the accuracy of the third correlation.

[0032] Optionally, determining, among the words in the multiple search sentences, words whose target relevance with the keyword meets a target condition as associated words of the target business includes:

[0033] Among the words in the multiple search sentences, the first target number of words whose target relevance to the keyword is greater than that of other words are determined as associated words of the target business; or,

[0034] Among the words in the plurality of search sentences, words whose target relevance with the keyword reaches a target threshold are determined as associated words of the target business.

[0035] In the embodiment of the present disclosure, by selecting the first target number of words whose target relevance is greater than that of other words, or by selecting words whose target relevance is not less than the target threshold, words with higher target relevance can be selected, and associated words with a higher degree of relevance to the target business can be determined, thereby improving the accuracy of determining associated words.

[0036] Optionally, after determining, among the words in the multiple search sentences, words whose target relevance with the keyword meets the target condition as associated words of the target business, the method further includes:

[0037] Determine an object that has an association relationship with the associated word of the target business as a delivery object corresponding to the target business;

[0038] Deliver content resources under the target business to the delivery object.

[0039] In the disclosed embodiment, considering that an object that has an association relationship with the associated words of the target business is more likely to be interested in the target business, the object is determined as the delivery object for targeted delivery of the target business, thereby realizing a delivery method based on associated words, which effectively improves the accuracy of targeted delivery.

[0040] According to another aspect of the embodiments of the present disclosure, a device for determining a related word is provided, the device comprising:

[0041] A statement acquisition unit, configured to execute multiple search processes based on the target business, and acquire multiple search statements, wherein the search statements include a keyword and at least one word of the target business;

[0042] a relevance determination unit configured to determine a target relevance between any of the keywords and any of the words based on positions of the keywords and the words in the search sentences to which they belong, wherein the target relevance indicates a degree of relevance between the words;

[0043] The associated word determination unit is configured to determine, among the words in the multiple search sentences, words whose target association with the keyword satisfies a target condition as associated words of the target business.

[0044] Optionally, the association degree determination unit includes:

[0045] A relevance determination subunit is configured to determine a first relevance between any of the keywords and any term in the same search statement;

[0046] The association degree determination subunit is further configured to determine a second association degree between any of the keywords and any of the words in different search sentences;

[0047] The relevance fusion subunit is configured to determine a target relevance between any of the keywords and any of the words based on the first relevance and the second relevance.

[0048] Optionally, the relevance determination subunit is configured to determine the second relevance between any of the keywords and any of the words in different search statements based on a plurality of search statements searched within a target time period.

[0049] Optionally, the association degree determination subunit is configured to execute:

[0050] Determining a second degree of association between any of the keywords and any of the words in the different search statements based on a search time interval between the different search statements;

[0051] The second correlation degree is negatively correlated with a search time interval, and the search time interval refers to an interval between search time points of different search statements.

[0052] Optionally, the relevance determination unit is further configured to determine a third relevance between any of the keywords in the search statement and any term in the corresponding search result, each of the search statements corresponding to at least one search result;

[0053] The association degree determination unit includes:

[0054] a relevance determination subunit, configured to determine a fourth relevance between any of the keywords and any of the words based on positions of the keywords and the words in the search sentence to which they belong;

[0055] The relevance fusion subunit is configured to determine a target relevance between any of the keywords and any of the words based on the third relevance and the fourth relevance.

[0056] Optionally, the association degree determination unit includes:

[0057] The relevance determination subunit is further configured to execute the acquisition of a search relevance between the search statement and the corresponding search result, wherein the search relevance indicates a degree of relevance between the search result and the corresponding search statement;

[0058] The relevance determination subunit is configured to determine a third relevance between any of the keywords in the search statement and any term in the corresponding search result based on the search relevance, wherein the third relevance is positively correlated with the search relevance.

[0059] Optionally, the associated word determination unit includes:

[0060] The first determining subunit is configured to determine, among the words in the multiple search sentences, the first target number of words whose target relevance to the keyword is greater than that of other words as associated words of the target business; or

[0061] The second determining subunit is configured to determine, among the words in the multiple search sentences, words whose target relevance with the keyword reaches a target threshold as associated words of the target business.

[0062] Optionally, the device further comprises:

[0063] An object determination unit is configured to determine an object that has an association relationship with an associated word of the target business as a delivery object corresponding to the target business;

[0064] The delivery unit is configured to deliver the content resources under the target business to the delivery object.

[0065] According to another aspect of the embodiments of the present disclosure, an electronic device is provided, the electronic device comprising:

[0066] processor;

[0067] a memory for storing instructions executable by the processor;

[0068] The processor is configured to execute the instructions to implement the method for determining associated words as described in the above aspects.

[0069] According to another aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided. When instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device can execute the method for determining associated words as described in the above aspects.

[0070] According to another aspect of the embodiments of the present disclosure, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the method for determining associated words as described in the above aspects is implemented.

[0071] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0073] Figure 1 It is a schematic diagram showing an implementation environment according to an exemplary embodiment.

[0074] Figure 2 The figure is a flow chart showing a method for determining associated words according to an exemplary embodiment.

[0075] Figure 3 The figure is a flow chart showing another method for determining associated words according to an exemplary embodiment.

[0076] Figure 4 The flowchart of another method for determining associated words according to an exemplary embodiment is shown.

[0077] Figure 5 The invention is a block diagram showing a device for determining an associated word according to an exemplary embodiment.

[0078] Figure 6 It is a block diagram of another device for determining associated words according to an exemplary embodiment.

[0079] Figure 7 It is a block diagram of a terminal according to an exemplary embodiment.

[0080] Figure 8 It is a block diagram of a server according to an exemplary embodiment. DETAILED DESCRIPTION

[0081] In order to enable ordinary persons in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings.

[0082] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned figure descriptions are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0083] It should be noted that the user information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.) and signals involved in this disclosure are all authorized by the user or fully authorized by all parties. For example, the search statements involved in this disclosure are all obtained with full authorization.

[0084] The disclosed embodiment provides a method for determining associated words, and the execution subject is an electronic device. Exemplarily, the electronic device is a terminal, and the terminal is a computer, a mobile phone, a tablet computer or other terminals. Exemplarily, the electronic device is a server, and the server is a background server or a cloud server that provides cloud computing and cloud storage services. Among them, the electronic device obtains multiple search statements based on multiple search processes for the target business, and the search statement includes keywords and at least one word of the target business, and then determines the target association between any keyword and any word based on the position of the keyword and the word in the search statement to which it belongs, and determines the words whose target association with the keyword meets the target condition as the associated words of the target business, thereby improving the accuracy of determining the associated words.

[0085] Figure 1 is a schematic diagram of an implementation environment provided by an embodiment of the present disclosure. Figure 1 , the implementation environment includes a server 101. The server 101 is used to determine the associated words of the target business based on the search sentence corresponding to the target business. In some embodiments, the associated word determination method provided by the embodiment of the present disclosure is periodically executed by the server 101, for example, the server 101 executes the process performed by the above-mentioned associated word determination method once every target time interval (such as 1 hour).

[0086] In some embodiments, the implementation environment further includes a terminal 102, and the server 101 and the terminal 102 are connected via a wireless or wired network. In the disclosed embodiment, the server 101 can provide the associated words of the target business to the terminal 102. For example, in response to a trigger operation for obtaining the associated words, the terminal 102 sends a request for obtaining the associated words to the server 101 to request the server 101 to return the associated words of the target business.

[0087] Exemplarily, the terminal 102 is installed with a target application provided by the server 101, and the terminal 102 can realize functions such as resource search and resource delivery through the target application. Of course, the target application can also have other functions, such as network social functions, video sharing functions, or chat functions. Exemplarily, the target application is a target application in the operating system of the terminal 102, or a target application provided by a third party. Exemplarily, the target application is a short video application, a game application, a social application, or other applications, which is not limited in the embodiments of the present disclosure.

[0088] The method for determining associated words provided by the embodiments of the present disclosure can be applied to resource delivery scenarios under target businesses.

[0089] For example, it is applied to the advertising delivery scenario under the target business. In the embodiment of the present disclosure, the associated words refer to the words related to the target business. The method provided in the embodiment of the present disclosure is used to determine the associated words of the target business according to the degree of association between the keywords of the target business and other words in multiple search statements. Furthermore, when the business party needs to promote the target business by delivering advertisements, the object that has an associated relationship with the associated words of the target business will be determined as the delivery object, and advertisements will be delivered to the delivery object, thereby improving the pertinence and accuracy of the advertising delivery.

[0090] Figure 2 is a flowchart of a method for determining a related word according to an exemplary embodiment. Figure 2 The method is performed by an electronic device and comprises the following steps:

[0091] In step 201, the electronic device obtains multiple search statements based on multiple search processes for target services.

[0092] Among them, the search statement is a statement entered by a certain object during the search process, and the search process for the target business refers to the search process related to the target business. The search statement obtained in the embodiment of the present disclosure includes the keyword of the target business and at least one word, and the at least one word refers to other words other than the keyword. The keyword of the target business is used to indicate the target business, for example, the keyword is the name of the target business, etc. The target business can be any business under any industry. For example, taking the clothing industry as an example, the target business can be a women's clothing business, a men's clothing business, or a children's clothing business, etc. For another example, taking the cosmetics industry as an example, the target business can be a lipstick business, an eye shadow business, or an eyebrow pencil business, etc.

[0093] In step 202, the electronic device determines the target association between any keyword and any word based on the positions of the keyword and the word in the corresponding search sentence.

[0094] For a certain keyword and a certain word, the electronic device determines the search sentence to which the keyword belongs and the search sentence to which the word belongs, and determines the target association between the keyword and the word based on the positions of the keyword and the word in the search sentence to which they belong. According to the method, the electronic device can determine the target association between any keyword and any word in the multiple search sentences.

[0095] The target correlation represents the correlation between words. Optionally, the target correlation is expressed in the form of a numerical value. For example, the target correlation is positively correlated with the correlation between words, that is, the larger the target correlation is, the higher the correlation between words is, and the smaller the target correlation is, the lower the correlation between words is.

[0096] In step 203, the electronic device determines, among the words in the multiple search sentences, words whose target relevance with the keyword meets the target condition as associated words of the target business.

[0097] In the disclosed embodiment, the degree of association represented by the target association that meets the target condition is higher than the degree of association represented by the target association that does not meet the target condition. Therefore, according to the target condition, words with a higher degree of association with the keywords of the target business are selected from the words of multiple search sentences as the associated words of the target business. The associated words determined by this method have a stronger correlation with the target business, thereby improving the accuracy of the determined associated words.

[0098] The method provided by the embodiment of the present disclosure takes into account the search sentences in the search process for the target business when determining the associated words of the target business, and determines the target association between the keywords and words of the target business according to the positions of the keywords and other words of the target business in the search sentences. Since the target association can reflect the degree of association between the words and the keywords, and the degree of association between the words and the keywords can reflect the degree of association between the words and the target business, the words whose target association with the keywords meets the target conditions are determined as the associated words of the target business, thereby improving the accuracy of the determined associated words.

[0099] Above Figure 2 What is shown is only the basic process of the present disclosure. The solution provided by the present disclosure will be further explained below based on a specific implementation method. Figure 3 is a flowchart of another method for determining a related word according to an exemplary embodiment, the method being executed by an electronic device. The disclosed embodiment describes a process for determining a target relatedness based on a first relatedness and a second relatedness, see Figure 3 , the method comprises the following steps:

[0100] In step 301, the electronic device obtains multiple search statements based on multiple search processes for target services.

[0101] The search statement includes a keyword of the target service and at least one word. The electronic device determines multiple search processes for the target service and obtains search statements input in the multiple search processes.

[0102] In some embodiments, the search process for the target business refers to the search process for content resources under the target business, and the content resources refer to multimedia resources containing relevant content of the target business. Understandably, the content resources are also multimedia resources used to promote the target business. For example, the content resources under the target business can be advertising videos, promotional videos, etc. of the target business.

[0103] In other embodiments, the search process for the target business refers to a search process in which keywords of the target business appear, for example, the search statement in the search process includes the keywords of the target business, or the search results in the search process include the keywords of the target business. The search results may be search results in the form of video, audio, or text.

[0104] In other embodiments, the electronic device obtains search statements within a preset time period based on multiple search processes for the target business. For example, the electronic device obtains search statements that have been searched within the previous 30 days.

[0105] In step 302, the electronic device determines a first degree of association between any keyword and any word in the same search sentence.

[0106] Since the words in the same search statement belong to the same search process, these words are closely related. Therefore, for the same search statement, for each of the multiple search statements obtained, the electronic device determines a first correlation between any keyword and any word in the search statement, and the first correlation represents the degree of correlation between the keyword and the word.

[0107] The method provided by the embodiment of the present disclosure, when mining associated words of the target business, takes into account the close connection between words in the same search sentence, and therefore determines the first degree of association between the keywords and words in the same search sentence, and then combines the first degree of association and the second degree of association to determine whether to use the word as an associated word of the target business, which is conducive to mining associated words with a strong correlation with the target business, thereby improving the accuracy of the determined associated words.

[0108] In some embodiments, taking a search statement as an example, the electronic device performs word segmentation on the search statement to obtain multiple words in the search statement, and the multiple words include keywords of the target business and other words. After the electronic device obtains the multiple words in the search statement, it determines a first correlation between the keyword in the search statement and any other words.

[0109] In some embodiments, the electronic device determines the first value as a first correlation between any keyword and any word in the same search sentence. Optionally, the first value is a value preset by the electronic device.

[0110] For example, the electronic device performs word segmentation on a search sentence to obtain word a1, word a2 and word a3. Taking word a1 as the keyword of the target business as an example, the combination relationship between the keyword and the other words is obtained (a1-a2, a1-a3). Taking the first numerical value s1 as an example, the first correlation between the keyword and the other words is obtained (a1-a2: s1, a1-a3: s1).

[0111] In step 303, the electronic device determines a second degree of association between any keyword and any word in different search sentences.

[0112] Since the words in different search statements for the target business are also related, the electronic device determines, among multiple search statements, a second degree of association between any keyword in one of the multiple search statements and any word in other search statements in the multiple search statements, wherein the second degree of association indicates the degree of association between the keyword and the word.

[0113] Optionally, the different search statements are different search statements that have been used to search for objects of the same type, for example, the objects of the same type refer to objects of the same age group.

[0114] The method provided by the embodiment of the present disclosure, when mining associated words of the target business, takes into account the close connection between words in different search sentences of the same business, and therefore determines the second degree of association between keywords and words in different search sentences, and then combines the first degree of association and the second degree of association to determine whether to use the word as an associated word of the target business, which is conducive to mining associated words with a strong correlation with the target business, thereby improving the accuracy of the determined associated words.

[0115] In some embodiments, the electronic device determines the second degree of association between any keyword and any word in different search statements based on multiple search statements searched within the target time period. For example, if the target time period is 120 minutes, the electronic device obtains multiple search statements searched within 120 minutes from multiple search statements, and determines the second degree of association between any keyword and any word in the multiple search statements.

[0116] In the disclosed embodiment, since the degree of correlation between words in different search statements searched within the target time period is higher, the second degree of correlation between the keywords and other words is determined in the different search statements searched within the target time period, taking into account the impact of the search time period on the degree of correlation between words in different search statements. This is conducive to mining associated words that are more closely related to the target business, thereby improving the accuracy of the determined associated words.

[0117] In some embodiments, the electronic device determines a second degree of association between any keyword and any word in different search statements based on a search time interval between different search statements, wherein the second degree of association is negatively correlated with the search time interval, and the search time interval refers to the interval between search time points of different search statements.

[0118] Taking the first search statement and the second search statement as an example, the electronic device determines the search time interval between the search time point of the first search statement and the search time point of the second search statement, and determines the second association degree between the keyword in the first search statement and the word in the second search statement based on the search time interval. The association degree represented by the second association degree is negatively correlated with the search time interval, that is, the longer the search time interval between the first search statement and the second search statement, the smaller the association degree represented by the second association degree, and the shorter the search time interval between the first search statement and the second search statement, the greater the association degree represented by the second association degree.

[0119] In the disclosed embodiment, the shorter the search time interval between different search statements, the higher the correlation between the words in the two search statements, and the longer the search time interval between different search statements, the lower the correlation between the words in the two search statements. Therefore, the second correlation between the keywords and words in different search statements is set to be negatively correlated with the search time interval between the search statements. When determining the second correlation, the influence of the search time interval between the search statements is taken into account, which is conducive to improving the accuracy of the second correlation.

[0120] It should be noted that the above two determination methods can also be combined, that is, the electronic device determines multiple search statements searched within the target time period, and among the multiple search statements determined, based on the duration of the target time period and the search time interval between different search statements, determines the second correlation between any keyword and any word in different search statements. The second correlation is negatively correlated with the search time interval and positively correlated with the duration of the target time period.

[0121] Optionally, the electronic device determines the second degree of association between any keyword and any word in different search statements based on the second numerical value, the duration of the target time period, and the search time interval between different search statements. For example, the second numerical value is s2, and the multiple search statements searched within the target time period are search statement a, search statement b, and search statement c, wherein search statement a includes keyword a1, search statement b includes word b1 and word b2, and search statement c includes word c1 and word c2. Among them, the duration of the target time period is T, the search time point of search statement a is t0, the search time point of search statement b is t1, and the search time point of search statement c is t2. Then the electronic device can use the following formula to determine the second degree of association between keyword a1 and each word.

[0122]

[0123] Among them, L a1,b1represents the second correlation between keyword a1 and word b1, L a1,b2 represents the second correlation between keyword a1 and word b2, L a1,c1 represents the second correlation between keyword a1 and word c1, L a1,c2 Indicates the second degree of association between keyword a1 and word c2.

[0124] It should be noted that the embodiment of the present disclosure is only described by taking the example of first executing step 302 and then executing step 303. In another embodiment, the electronic device may also first execute step 303 and then execute step 302, or execute step 302 and step 303 at the same time. The embodiment of the present disclosure does not limit the execution order of step 302 and step 303.

[0125] In step 304, the electronic device determines a target association degree between any keyword and any word based on the first association degree and the second association degree.

[0126] After the electronic device acquires the first correlation and the second correlation between any keyword and any word, the electronic device determines the target correlation between any keyword and any word based on the second correlation and the second correlation.

[0127] It should be noted that, taking keyword a and word b as an example, if there is a search statement X that includes both keyword a and word b, and there is a search statement Y that is different from search statement X and includes word b but does not include keyword a, then there is a first correlation and a second correlation between keyword a and word b. In this case, the electronic device merges the first correlation and the second correlation to obtain a target correlation between keyword a and word b.

[0128] If there is a search sentence X that includes both keyword a and word b, but there is no search sentence different from the search sentence X that includes word b and does not include keyword a, then there is only a first degree of association and no second degree of association between keyword A and word B. In this case, the electronic device determines the first degree of association as the target degree of association between keyword a and word b.

[0129] If there is a search sentence X that includes only keyword a and does not include word b, but there is a search sentence Y that is different from the search sentence X and includes only word b and does not include keyword a, then there is only the second degree of association and no first degree of association between keyword A and word B. In this case, the electronic device determines the second degree of association as the target degree of association between keyword a and word b.

[0130] In step 305, the electronic device determines, among the words in the multiple search sentences, words whose target relevance with the keyword meets the target condition as associated words of the target business.

[0131] In the disclosed embodiment, the degree of association represented by the target association that meets the target condition is higher than the degree of association represented by the target association that does not meet the target condition. Therefore, based on the target condition, words with a higher degree of association with the keywords of the target business are selected from the words of multiple search statements as associated words of the target business.

[0132] In some embodiments, the electronic device determines the first target number of words whose target relevance with the keyword is greater than that of other words among the words in multiple search sentences as the associated words of the target business. For example, the electronic device sorts the words in order of target relevance from high to low, and uses the words corresponding to the target relevance that are in the first target number as the associated words of the target business. The target number is a pre-set number. For example, if the target number is 8, the words corresponding to the target relevance that are in the first 8 order are selected as the associated words of the target business.

[0133] In other embodiments, the electronic device determines, among the words in the multiple search sentences, words whose target relevance with the keyword reaches a target threshold as the associated words of the target business. The target threshold is a preset threshold, for example, if the target threshold is 90, then the words whose target relevance reaches 90 are selected as the associated words of the target business.

[0134] In the above embodiment, by selecting the first target number of words whose target relevance is greater than that of other words, or selecting words whose target relevance is not less than the target threshold, words with higher target relevance can be selected, and associated words with a higher degree of relevance to the target business can be determined, thereby improving the accuracy of determining associated words.

[0135] In step 306, the electronic device determines an object that has an association relationship with the associated word of the target business as a delivery object corresponding to the target business, and delivers content resources under the target business to the delivery object.

[0136] After the electronic device determines the associated words of the target business, it can deliver content resources of the target business based on the associated words of the target business. The content resources are multimedia resources used to promote the target business.

[0137] First, the electronic device determines the object that has an association relationship with the associated word of the target business. For example, if the associated word is "female", then the object that has an association relationship with the associated word also refers to female. For another example, if the associated word is "region A", then the object that has an association relationship with the associated word is also the object located in region A. For another example, if the associated word is "lipstick", then the object that has an association relationship with the associated word is also the object that is interested in lipstick. Then, the electronic device determines the object that has an association relationship with the associated word as the delivery object corresponding to the target business, and delivers the content resources under the target business to the delivery object, thereby realizing targeted delivery of the content resources under the target business.

[0138] It should be noted that step 306 is only explained by taking the determination of the delivery object based on the associated words of the target business as an example. In another embodiment, the electronic device may not execute step 306, but use the associated words of the target business in other ways. For example, when the search statement of an object includes the associated words of the target business, the content resources under the target business are determined as the search results corresponding to the search statement, and the search results are returned to the object. Alternatively, the associated words of the target business are added to the content resources under the target business. The disclosed embodiment does not limit the use of the associated words of the target business.

[0139] In the disclosed embodiment, considering that an object that has an association relationship with the associated words of the target business is more likely to be interested in the target business, the object is determined as the delivery object for targeted delivery of the target business, thereby realizing a delivery method based on associated words, which effectively improves the accuracy of targeted delivery.

[0140] In some embodiments, the terminal operated by the business party can display the associated words of the target business determined by the embodiments of the present disclosure. When determining the delivery object of the content resource, the business party can select from the multiple associated words displayed on the terminal. The terminal responds to the business party's selection operation on the multiple associated words, obtains the selected associated words, and sends a delivery request for the content resource to the electronic device based on the selected associated words. The delivery request carries the selected associated words. In response to receiving the delivery request for the content resource, the electronic device determines the object that has an associated relationship with the associated words based on the associated words carried in the delivery request, that is, determines the delivery object of the content resource, and then sends the content resource to the terminal corresponding to the determined delivery object.

[0141] In the disclosed embodiment, the search statement is obtained by the search process for a certain business, so the words contained in the search statement are more likely to be associated with the business. In order to further mine more accurate associated words, the keywords of the business are used as a reference, and the degree of association between the word and the keyword is determined according to the position of the word and the keyword in the search statement to which it belongs. The greater the degree of association between the word and the keyword of the business, the greater the degree of association between the word and the business, so the word can be determined as the associated word of the business. In addition, considering that when searching for a certain business, the search statement usually includes words used to describe the target group of the business, for example, the keyword of a certain business is "lipstick", and the search statement for the business is "what are the lipsticks suitable for young people", then the word "young people" in the search statement is the word describing the target group of the business. On this basis, it can be considered that the greater the degree of association between the words in the search statement and the words of the business, the greater the possibility that the word is used to describe the target group of the business, so the target group of the business can be determined based on the mined associated words, so that the content resources under the business are sent to the target group.

[0142] The method provided by the embodiment of the present disclosure takes into account the search sentences in the search process for the target business when determining the associated words of the target business, and determines the target association between the keywords and words of the target business according to the positions of the keywords and other words of the target business in the search sentences. Since the target association can reflect the degree of association between the words and the keywords, and the degree of association between the words and the keywords can reflect the degree of association between the words and the target business, the words whose target association with the keywords meets the target conditions are determined as the associated words of the target business, thereby improving the accuracy of the determined associated words.

[0143] It should be noted that the disclosed embodiment is only described by processing a search statement for a target business as an example. In another embodiment, the electronic device obtains multiple search statements, uses the method provided in the above embodiment to determine the target association between any two words in the multiple search statements, and then obtains the target association between any two words in the multiple words. The electronic device then obtains the target association between the keyword of the target business and any word from the target association between any two words, and determines the words whose target association with the keyword meets the target condition as the associated words of the target business.

[0144] Figure 4 is a flowchart of another method for determining an associated word according to an exemplary embodiment, the method being executed by an electronic device. The disclosed embodiment describes a process for determining a target association degree based on a third association degree and a fourth association degree, see Figure 4, the method comprises the following steps:

[0145] In step 401, the electronic device obtains multiple search statements based on multiple search processes for target services.

[0146] The step 401 is the same as the above step 301 and will not be described in detail here.

[0147] In step 402, the electronic device determines a fourth degree of association between any keyword and any word based on the positions of the keyword and the word in the corresponding search sentence.

[0148] The process of determining the fourth correlation between any keyword and any word in step 402 is the same as the process of determining the target correlation in step 202 or steps 302 to 304, and will not be described in detail here.

[0149] In step 403, the electronic device determines a third degree of association between any keyword in the search sentence and any word in the corresponding search result.

[0150] Each search statement corresponds to at least one search result, and the search result may be a search result in the form of video, text or audio. Since the words in the search statement and the words in the search result corresponding to the search statement are closely related, the electronic device obtains the search result corresponding to the search statement and determines the third degree of association between any keyword in the search statement and any word in the search result, and the third degree of association indicates the degree of association between the keyword and the word.

[0151] The method provided by the embodiment of the present disclosure, when mining associated words of the target business, takes into account the close connection between the words in the search sentence and the words in the search results, and therefore determines the third degree of association between the keywords in the search sentence and the corresponding words in the search results, and then combines the third degree of association and the fourth degree of association to determine whether to use the word as an associated word of the target business, which is conducive to mining associated words with a strong correlation with the target business, thereby improving the accuracy of the determined associated words.

[0152] In some embodiments, the electronic device obtains a search correlation between a search statement and a corresponding search result, and the search correlation indicates the degree of correlation between the search result and the corresponding search statement. Based on the search correlation, the electronic device determines a third correlation between any keyword in the search statement and any word in the corresponding search result, and the third correlation is positively correlated with the search correlation. That is, the higher the degree of correlation represented by the search correlation between the search statement and the search result, the higher the degree of correlation represented by the second correlation, and the lower the degree of correlation represented by the search correlation between the search statement and the search result, the lower the degree of correlation represented by the second correlation.

[0153] In the disclosed embodiment, since the higher the correlation between the search statement and the search results, the higher the correlation between the words in the search statement and the words in the search results, and the lower the correlation between the search statement and the search results, the lower the correlation between the words in the search statement and the words in the search results, the third correlation between the keywords in the search statement and the corresponding words in the search results is set to be positively correlated with the corresponding search correlation, and the influence of the correlation between the search statement and the search results is taken into account when determining the third correlation, which is conducive to improving the accuracy of the third correlation.

[0154] Optionally, the electronic device determines the third degree of association between any keyword in the search statement and any word in the corresponding search result based on the third value and the search correlation. For example, the third value is s3, the search statement a includes the keyword a1, the search statement a corresponds to the search result x and the search result y, the search statement x includes the word x1 and the word x2, and the search statement y includes the word y1 and the word y2. Among them, the search correlation between the search statement a and the search result x is related1, and the search correlation between the search statement a and the search result y is related2. Then the electronic device can use the following formula to determine the third degree of association between the keyword a1 and each word.

[0155] L a1,x1 =s3*related1;L a1,x2 =s3*related1;

[0156] L a1,y1 =s3*related2;L a1,y2 =s3*related2;

[0157] Among them, L a1,x1 represents the third degree of association between keyword a1 and word x1, L a1,x2 represents the third degree of association between keyword a1 and word x2, L a1,y1represents the third degree of association between keyword a1 and word y1, L a1,y2 Indicates the third degree of association between keyword a1 and word y2.

[0158] In some embodiments, the search result is a video, the electronic device performs voice extraction on the video to obtain the voice in the video, converts the voice into text, and then segments the text to obtain multiple words, which are also the words in the video.

[0159] In step 404, the electronic device determines a target association degree between any keyword and any word based on the third association degree and the fourth association degree.

[0160] After the electronic device acquires the third and fourth associations between any keyword and any word, the electronic device determines a target association between any keyword and any word based on the third and fourth associations.

[0161] It should be noted that, taking keyword a and word b as an example, if there is a third degree of association and a fourth degree of association between keyword a and word b, the electronic device merges the third degree of association and the fourth degree of association to obtain the target degree of association between keyword a and word b. If there is only the third degree of association between keyword a and word b, and there is no fourth degree of association, the electronic device determines the third degree of association as the target degree of association between keyword a and word b. If there is only the fourth degree of association between keyword a and word b, and there is no third degree of association, the electronic device determines the fourth degree of association as the target degree of association between keyword a and word b.

[0162] In step 405, the electronic device determines, among the words in the multiple search sentences, words whose target relevance with the keyword meets the target condition as associated words of the target business.

[0163] In step 406, the electronic device determines an object that has an association relationship with the associated word of the target business as a delivery object corresponding to the target business, and delivers content resources under the target business to the delivery object.

[0164] The process of step 405-step 406 is the same as the process of step 305-step 306 above, and will not be described in detail here.

[0165] The method provided by the embodiment of the present disclosure takes into account the search sentences in the search process for the target business when determining the associated words of the target business, and determines the target association between the keywords and words of the target business according to the positions of the keywords and other words of the target business in the search sentences. Since the target association can reflect the degree of association between the words and the keywords, and the degree of association between the words and the keywords can reflect the degree of association between the words and the target business, the words whose target association with the keywords meets the target conditions are determined as the associated words of the target business, thereby improving the accuracy of the determined associated words.

[0166] Above Figure 3 Examples and Figure 4 The embodiments of the present invention respectively illustrate the process of determining the target relevance in different ways, and in another embodiment, the above Figure 3 Examples and Figure 4 The embodiments can also be combined, and the method for determining the target association degree includes the following steps:

[0167] (1) The electronic device determines a first degree of association between a keyword and a word. The first degree of association indicates the degree of association between any keyword and any word in the same search sentence, which can be referred to as a "first degree relationship" between the keyword and the word. For example, the first value is determined as the first degree of association between any keyword and any word in the same search sentence.

[0168] Taking keyword a and word b as an example, the first correlation between keyword a and word b is: Here, s1 represents the first value.

[0169] (2) The electronic device determines the second degree of association between the keyword and the word. The second degree of association indicates the degree of association between any keyword and any word in different search statements among the multiple search statements searched within the target time period, which can be called the "second degree relationship" between the keyword and the word. For example, the electronic device determines the second degree of association between any keyword and any word in different search statements based on the second value, the duration of the target time period, and the search time interval between the search statements.

[0170] Taking keyword a and word b as an example, the second correlation between keyword a and word b is: Among them, s2 represents the second numerical value, T represents the length of the target time period, t1 represents the search time point of the search statement to which keyword a belongs, t0 represents the search time point of the search statement to which word b belongs, and t1-t0 represents the search time interval between the search statement to which keyword a belongs and the search statement to which word b belongs.

[0171] (3) The electronic device determines the third degree of association between the keyword and the word. The third degree of association indicates the degree of association between any keyword in the search statement and any word in the corresponding search result, which can be called the "third degree relationship" between the keyword and the word. For example, the electronic device determines the third degree of association between any keyword in the search statement and any word in the corresponding search result based on the third value and the search degree of association between the search statement and the search result.

[0172] Taking keyword a and word b as an example, the third correlation between keyword a and word b is: Among them, s3 represents the third value, and r represents the search correlation between the search statement to which keyword a belongs and the search result to which word b belongs.

[0173] (4) The electronic device combines the first correlation, the second correlation and the third correlation to obtain a target correlation between the keyword and the word.

[0174] Taking keyword a and word b as an example, the electronic device adds the first, second and third associations between keyword a and word b to obtain the target association between keyword a and word b. Subsequently, the associated words of the target business are determined based on the target association.

[0175] In the embodiment of the present disclosure, the first value, the second value and the third value are pre-set. For example, considering that the degree of association between words in the same search statement is greater than the degree of association between words in different search statements, and the degree of association between words in different search statements is greater than the degree of association between words in the search statement and the corresponding search results, the first value is set to be greater than the second value, and the second value is set to be greater than the third value, so as to reflect the degree of association in different situations.

[0176] Among them, the above-mentioned "first-degree relationship" reflects the relationship between words in the same search statement, the above-mentioned "second-degree relationship" reflects the relationship between words in different search statements in the same time period, and the above-mentioned "third-degree relationship" reflects the relationship between words in the search statement and the words in the search results. Based on these three relationships, the target correlation between keywords and words is determined, and the associated words of the target business are determined. The influence of various situations is taken into consideration, so that the confidence of the associated words can be improved, which provides data support for determining the target of resource allocation in the subsequent resource allocation, and automates the process of mining associated words, reducing the cost of manpower investment.

[0177] Figure 5 is a block diagram of a device for determining a related word according to an exemplary embodiment. Figure 6The device includes a sentence acquisition unit 501, a relevance determination unit 502 and a related word determination unit 503.

[0178] The sentence acquisition unit 501 is configured to execute multiple search processes based on the target business and acquire multiple search sentences, where the search sentences include a keyword of the target business and at least one word;

[0179] The relevance determination unit 502 is configured to determine a target relevance between any keyword and any word based on the positions of the keyword and the word in the search sentence to which they belong, wherein the target relevance indicates the degree of relevance between the words;

[0180] The associated word determination unit 503 is configured to determine, among the words in the multiple search sentences, words whose target association with the keywords meets the target condition as associated words of the target business.

[0181] The device provided by the embodiment of the present disclosure takes into account the search sentence in the search process for the target business when determining the associated words of the target business, and determines the target association between the keywords and words of the target business according to the positions of the keywords and other words of the target business in the search sentence. Since the target association can reflect the degree of association between the word and the keyword, and the degree of association between the word and the keyword can reflect the degree of association between the word and the target business, the words whose target association with the keywords meets the target condition are determined as the associated words of the target business, thereby improving the accuracy of the determined associated words.

[0182] In some embodiments, see Figure 6 , the correlation determination unit 502 includes:

[0183] The association degree determination subunit 512 is configured to determine a first association degree between any keyword and any word in the same search sentence;

[0184] The relevance determination subunit 512 is further configured to determine a second relevance between any keyword and any word in different search sentences;

[0185] The relevance fusion subunit 522 is configured to determine a target relevance between any keyword and any word based on the first relevance and the second relevance.

[0186] In some embodiments, see Figure 6 The relevance determination subunit 512 is configured to determine a second relevance between any keyword and any word in different search sentences based on multiple search sentences searched within a target time period.

[0187] In some embodiments, see Figure 6 , the relevance determination subunit 512 is configured to execute:

[0188] Determining a second degree of association between any keyword and any word in different search sentences based on a search time interval between different search sentences;

[0189] The second correlation is negatively correlated with the search time interval, and the search time interval refers to the interval between search time points of different search statements.

[0190] In some embodiments, see Figure 6 The relevance determination unit 502 is further configured to determine a third relevance between any keyword in the search statement and any word in the corresponding search result, each search statement corresponding to at least one search result;

[0191] The correlation determination unit 502 includes:

[0192] The relevance determination subunit 512 is configured to determine a fourth relevance between any keyword and any word based on the positions of the keyword and the word in the corresponding search sentence;

[0193] The relevance fusion subunit 522 is configured to determine a target relevance between any keyword and any word based on the third relevance and the fourth relevance.

[0194] In some embodiments, see Figure 6 , the correlation determination unit 502 includes:

[0195] The relevance determination subunit 512 is further configured to execute the acquisition of a search relevance between the search statement and the corresponding search result, where the search relevance indicates the degree of relevance between the search result and the corresponding search statement;

[0196] The relevance determination subunit 512 is configured to determine a third relevance between any keyword in the search statement and any word in the corresponding search result based on the search relevance, where the third relevance is positively correlated with the search relevance.

[0197] In some embodiments, see Figure 6 , the associated word determination unit 503 includes:

[0198] The first determining subunit 513 is configured to determine, among the words in the multiple search sentences, the first target number of words whose target relevance to the keyword is greater than that of other words as associated words of the target business; or

[0199] The second determining subunit 523 is configured to determine, among the words in the multiple search sentences, words whose target relevance with the keyword reaches a target threshold as associated words of the target business.

[0200] In some embodiments, see Figure 6 , the device further comprises:

[0201] The object determination unit 504 is configured to determine the object associated with the associated word of the target business as the delivery object corresponding to the target business;

[0202] The delivery unit 505 is configured to deliver content resources under the target business to the delivery object.

[0203] Regarding the device in the above embodiment, the specific manner in which each unit performs the operation has been described in detail in the embodiment of the method, and will not be elaborated here.

[0204] The embodiment of the present disclosure provides an electronic device, which includes: a processor and a memory for storing instructions executable by the processor, wherein the processor is configured to execute the instructions to implement the above-mentioned method for determining associated words.

[0205] In some embodiments, the electronic device includes a terminal. Figure 7 1 is a block diagram of a terminal 700 according to an exemplary embodiment. The terminal 700 may be a portable mobile terminal, such as a smart phone, a tablet computer, an MP3 player (Moving Picture Experts Group Audio Layer III), an MP4 player (Moving Picture Experts Group Audio Layer IV), a laptop computer or a desktop computer. The terminal 700 may also be referred to as a user device, a portable terminal, a laptop terminal, a desktop terminal or other names.

[0206] The terminal 700 includes a processor 701 and a memory 702 .

[0207] The processor 701 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 701 may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 701 may also include a main processor and a coprocessor, the main processor is a processor for processing data in an awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in a standby state. The memory 702 may include one or more computer-readable storage media, which may be non-transitory. The memory 702 may also include a high-speed random access memory, and a non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory 702 is used to store at least one program code, which is used to be executed by the processor 701 to implement the method for determining the associated word provided in the method embodiment of the present disclosure.

[0208] In some embodiments, the terminal 700 may further include: a peripheral device interface 703 and at least one peripheral device. The processor 701, the memory 702 and the peripheral device interface 703 may be connected via a bus or a signal line. Each peripheral device may be connected to the peripheral device interface 703 via a bus, a signal line or a circuit board. Optionally, the peripheral device includes: a radio frequency circuit 704, a display screen 705 and a power supply 706.

[0209] The peripheral device interface 703 may be used to connect at least one peripheral device related to I / O (Input / Output) to the processor 701 and the memory 702. In some embodiments, the processor 701, the memory 702, and the peripheral device interface 703 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 701, the memory 702, and the peripheral device interface 703 may be implemented on a separate chip or circuit board, which is not limited in this embodiment.

[0210] The radio frequency circuit 704 is used to receive and transmit RF (Radio Frequency) signals, also known as electromagnetic signals. The radio frequency circuit 704 communicates with the communication network and other communication devices through electromagnetic signals. The radio frequency circuit 704 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals into electrical signals. Optionally, the radio frequency circuit 704 includes: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a user identity module card, etc. The radio frequency circuit 704 can communicate with other terminals through at least one wireless communication protocol. The wireless communication protocol includes but is not limited to: the World Wide Web, a metropolitan area network, an intranet, various generations of mobile communication networks (2G, 3G, 4G and 5G), a wireless local area network and / or a WiFi (Wireless Fidelity) network. In some embodiments, the radio frequency circuit 704 may also include circuits related to NFC (Near Field Communication), which is not limited in the present disclosure.

[0211] The display screen 705 is used to display a UI (User Interface). The UI may include graphics, text, icons, videos, and any combination thereof. When the display screen 705 is a touch display screen, the display screen 705 also has the ability to collect touch signals on the surface or above the surface of the display screen 705. The touch signal can be input to the processor 701 as a control signal for processing. At this time, the display screen 705 can also be used to provide virtual buttons and / or virtual keyboards, also known as soft buttons and / or soft keyboards. In some embodiments, the display screen 705 can be one, set on the front panel of the terminal 700; in other embodiments, the display screen 705 can be at least two, respectively set on different surfaces of the terminal 700 or in a folding design; in other embodiments, the display screen 705 can be a flexible display screen, set on a curved surface or a folding surface of the terminal 700. Even, the display screen 705 can also be set to a non-rectangular irregular shape, that is, a special-shaped screen. The display screen 705 can be made of materials such as LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode), etc.

[0212] The power supply 706 is used to power various components in the terminal 700. The power supply 707 can be an alternating current, a direct current, a disposable battery, or a rechargeable battery. When the power supply 706 includes a rechargeable battery, the rechargeable battery can be a wired rechargeable battery or a wireless rechargeable battery. A wired rechargeable battery is a battery charged through a wired line, and a wireless rechargeable battery is a battery charged through a wireless coil. The rechargeable battery can also be used to support fast charging technology.

[0213] Those skilled in the art will understand that Figure 7 The structure shown in the figure does not constitute a limitation on the terminal 700, and the terminal 700 may include more or less components than those shown in the figure, or combine some components, or adopt a different component arrangement.

[0214] In some embodiments, the electronic device includes a server. Figure 8 This is a schematic diagram of the structure of a server according to an exemplary embodiment. The server 800 may have relatively large differences due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) 801 and one or more memories 802, wherein the memory 802 stores at least one computer program, and the at least one computer program is loaded and executed by the processor 801 to implement the methods provided by the above-mentioned various method embodiments. Of course, the server may also have components such as a wired or wireless network interface, a keyboard, and an input and output interface for input and output, and the server may also include other components for implementing device functions, which will not be described in detail here.

[0215] In an exemplary embodiment, a computer-readable storage medium is also provided, and when the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device can perform the steps in the above-mentioned method for determining associated words. For example, the computer-readable storage medium can be a ROM (Read Only Memory), a RAM (Random Access Memory), a CD-ROM (Compact Disc Read-Only Memory), a magnetic tape, a floppy disk, an optical data storage device, etc.

[0216] In an exemplary embodiment, a computer program product is also provided, including a computer program, and when the computer program is executed by a processor of an electronic device, the steps in the above-mentioned associated word determination method are implemented.

[0217] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the disclosure herein. The present disclosure is intended to cover any variations, uses or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are to be considered exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0218] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A method for determining a related word, characterized in that: The method comprises: Based on multiple search processes for the target business, multiple search statements are obtained, wherein the search statements include a keyword of the target business and at least one word; Determining a first correlation between any of the keywords and any of the words in the same search statement; Determining a second degree of association between any of the keywords and any of the words in different search sentences based on multiple search sentences searched within a target time period; Based on the first correlation and the second correlation, determining a target correlation between any of the keywords and any of the words, the target correlation indicating the degree of correlation between the words; Among the words in the plurality of search sentences, words whose target relevance with the keyword satisfies a target condition are determined as associated words of the target business.

2. The method for determining associated words according to claim 1, characterized in that: The determining of the second association between any of the keywords and any of the words in different search statements includes: Determining a second degree of association between any of the keywords and any of the words in the different search statements based on a search time interval between the different search statements; The second correlation degree is negatively correlated with a search time interval, and the search time interval refers to an interval between search time points of different search statements.

3. The method for determining associated words according to claim 1, characterized in that: The method further comprises: Determine a third degree of association between any of the keywords in the search statement and any of the corresponding words in the search results, each of the search statements corresponding to at least one search result; The determining, based on the first association degree and the second association degree, a target association degree between any of the keywords and any of the words comprises: Determining a fourth degree of association between any of the keywords and any of the words based on the first degree of association and the second degree of association; Based on the third degree of association and the fourth degree of association, a target degree of association between any of the keywords and any of the words is determined.

4. The method for determining associated words according to claim 3, characterized in that: The determining of a third degree of association between any of the keywords in the search statement and any of the corresponding words in the search results includes: Obtaining a search correlation between the search statement and the corresponding search result, wherein the search correlation indicates a correlation degree between the search result and the corresponding search statement; Based on the search relevance, a third relevance between any of the keywords in the search statement and any term in the corresponding search result is determined, and the third relevance is positively correlated with the search relevance.

5. The method for determining a related word according to any one of claims 1 to 4, characterized in that: The step of determining, among the words in the plurality of search sentences, words whose target relevance with the keyword satisfies a target condition as associated words of the target business includes: Among the words in the multiple search sentences, the first target number of words whose target relevance to the keyword is greater than that of other words are determined as associated words of the target business; or, Among the words in the plurality of search sentences, words whose target relevance with the keyword reaches a target threshold are determined as associated words of the target business.

6. The method for determining a related word according to any one of claims 1 to 4, characterized in that: After determining, among the words in the plurality of search sentences, words whose target relevance with the keyword satisfies the target condition as associated words of the target business, the method further includes: Determine an object that has an association relationship with the associated word of the target business as a delivery object corresponding to the target business; Deliver content resources under the target business to the delivery object.

7. A device for determining a related word, characterized in that: The device comprises: A statement acquisition unit, configured to execute multiple search processes based on the target business, and acquire multiple search statements, wherein the search statements include a keyword and at least one word of the target business; a correlation determination unit, configured to determine a first correlation between any of the keywords and any of the words in the same search sentence; The association degree determination unit is further configured to determine a second association degree between any of the keywords and any of the words in different search sentences based on a plurality of search sentences searched within a target time period; The association determination unit is further configured to determine a target association between any of the keywords and any of the words based on the first association and the second association, wherein the target association indicates a degree of association between the words; The associated word determination unit is configured to determine, among the words in the multiple search sentences, words whose target association with the keyword satisfies a target condition as associated words of the target business.

8. The device for determining related words according to claim 7, characterized in that: The association degree determination unit is configured to execute: Determining a second degree of association between any of the keywords and any of the words in the different search statements based on a search time interval between the different search statements; The second correlation degree is negatively correlated with a search time interval, and the search time interval refers to an interval between search time points of different search statements.

9. The device for determining related words according to claim 7, characterized in that: The association determination unit is further configured to determine a third association between any of the keywords in the search statement and any term in the corresponding search result, each of the search statements corresponding to at least one search result; The association degree determination unit includes: a relevance determination subunit, configured to determine a fourth relevance between any of the keywords and any of the words based on the first relevance and the second relevance; The relevance fusion subunit is configured to determine a target relevance between any of the keywords and any of the words based on the third relevance and the fourth relevance.

10. The device for determining related words according to claim 9, characterized in that: The association degree determination unit includes: The relevance determination subunit is further configured to execute the acquisition of a search relevance between the search statement and the corresponding search result, wherein the search relevance indicates a degree of relevance between the search result and the corresponding search statement; The relevance determination subunit is configured to determine a third relevance between any of the keywords in the search statement and any term in the corresponding search result based on the search relevance, wherein the third relevance is positively correlated with the search relevance.

11. The device for determining a related word according to any one of claims 7 to 10, characterized in that: The associated word determination unit includes: The first determining subunit is configured to determine, among the words in the multiple search sentences, the first target number of words whose target relevance to the keyword is greater than that of other words as associated words of the target business; or The second determining subunit is configured to determine, among the words in the multiple search sentences, words whose target relevance with the keyword reaches a target threshold as associated words of the target business.

12. The device for determining a related word according to any one of claims 7 to 10, characterized in that: The device also includes: An object determination unit is configured to determine an object that has an association relationship with an associated word of the target business as a delivery object corresponding to the target business; The delivery unit is configured to deliver the content resources under the target business to the delivery object.

13. An electronic device, characterized in that: The electronic device comprises: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the method for determining associated words as described in any one of claims 1 to 6.

14. A computer-readable storage medium, characterized in that: When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the method for determining associated words as described in any one of claims 1 to 6.

15. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method for determining associated words according to any one of claims 1 to 6 is implemented.

Images