A method, device, medium and equipment for mining community hot topics

Abstract

The present invention provides a method, device, medium and equipment for mining community hot topics, including: determining the first heat value of each word in a community post within a preset time length; performing heat correction on the first heat value of each word to obtain a second heat value; obtaining the number of first corpora containing first target words and second target words, and the number of second corpora containing second target words; determining a reference topic based on the number of first corpora and the number of second corpora; determining the reference topic as a hot topic based on the second heat values ​​of the first reference words and the second reference words in the reference topic and the number of third corpora containing the first reference words and the second reference words; in this way, after determining the first heat value of each word, continuing to correct the first heat value to avoid the situation where a word is mistakenly regarded as a hot topic when the number of historical appearances and the current increase are both relatively small, thereby reducing mining errors and improving accuracy.

Description

Technical Field

[0001] The present invention belongs to the technical field of community hot spots of live broadcast platforms, and in particular, relates to a method, device, medium and equipment for mining community hot topics. Background Art

[0002] The community is a very important content form in the live broadcast platform. Users can post and comment in the community to discuss anchors and games. In order to better operate the community content and further improve the community activity, it is necessary to explore the hot topics currently discussed by community users.

[0003] In the related art, the commonly used hotspot mining method is to count the frequency of occurrence of words in posts and take some words with a large increase in frequency as hotspots. However, if a word has appeared very few times in the past, but the current increase in frequency is small, the heat value of the word will be very large, and it will be mistaken for a hotspot, which obviously makes it impossible to ensure the accuracy of mining hot topics. Summary of the invention

[0004] In view of the problems existing in the prior art, the embodiments of the present invention provide a method, device, medium and equipment for mining community hot topics, which are used to solve the technical problem in the prior art that the mining accuracy cannot be ensured when mining community hot topics.

[0005] A first aspect of the present invention provides a method for mining community hot topics, the method comprising:

[0006] Acquire multiple words in community posts, and determine the first popularity value of each of the words within a preset time period;

[0007] Based on a preset correction strategy, the first heat value of each of the words is corrected to obtain a second heat value of each of the words;

[0008] For a first target word, obtain the amount of a first corpus containing the first target word and a second target word, and obtain the amount of a second corpus containing the second target word; determine a reference topic based on the amount of the first corpus and the amount of the second corpus; the first target word is any word among all words, and the second target word is any word among the remaining words except the first target word;

[0009] For each reference topic, determine the first reference word and the second reference word in the reference topic, and determine that the reference topic is a hot topic based on the second heat value of the first reference word and the second reference word and the number of third corpora containing the first reference word and the second reference word.

[0010] In the above solution, determining the first heat value of each of the words within a preset time period includes:

[0011] According to the formula Determine the first heat value S(w i ); wherein said w i is the first target word, i is the word sequence number, and T n is the nth time period within the preset time length, where n is the total number of time periods included in the preset time length, and T j is the jth time period within the preset time length, where j is any time period, j≤n; N(w i ,T n ) is the first target word w i In the nth time period T n The total number of occurrences in the i ,T j ) is the first target word w i In the jth time period T j The total number of times it appears in .

[0012] In the above scheme, the first heat value of each of the words is corrected based on a preset correction strategy to obtain the second heat value of each of the words, including:

[0013] Based on the formula Determine each of the first target words w i The second heat value F(w i ); wherein said w i is the first target word, i is the word sequence number, m is the total number of words, and T n is the nth time period within the preset time length, where n is the total number of time periods included in the preset time length, and X n is the number of times the first target word appears in the nth time period, and the S(w i ) is the first heat value, and the N(w i ,T n ) is the first target word w i In the nth time period T n The total number of times it appears in .

[0014] In the above solution, the determining of the reference topic based on the amount of the first corpus and the amount of the second corpus includes:

[0015] According to the formula Determine the subject ability expression value H(w i );

[0016] If it is determined that the topic ability expression value is greater than a preset topic expression threshold, the topic formed by the first target word and the second target word is determined as the reference topic; wherein,

[0017] The w i is the first target word, the w h is the second target word, i and h are word numbers, and the values ​​of i and h are different; m is the total number of words, and C(w i , w h ) is the number of first corpus containing the first target word and the second target word, and C(w h ) is the number of second corpora containing the second target word, and the corpus is the text or comments in the community post.

[0018] In the above solution, the step of determining the reference topic as a hot topic based on the second heat value of the first reference word, the second reference word, and the number of third corpora containing the first reference word and the second reference word includes:

[0019] Determine the heat value of the reference topic based on the second heat value of the first reference word, the second heat value of the second reference word, and the amount of third corpus containing the first reference word and the second reference word;

[0020] If it is determined that the heat value is greater than a preset heat threshold, the reference topic is determined to be a hot topic.

[0021] In the above solution, the determining the heat value of the reference topic based on the second heat value of the first reference word, the second heat value of the second reference word, and the number of third corpora containing the first reference word and the second reference word includes:

[0022] According to the formula T(p(w j , w k ))=C(w j , w k )max(F(w j ), F(w k )) Determine the heat value T(p(w j , w k )); wherein, the p(w j , w k ) is the first reference word w j and the second reference word w k The reference subject formed, j and k are word numbers, and the values ​​of j and k are different; C(w j , w k) is the number of third corpora containing the first reference words and the second reference words, and the F(w j ) is the second heat value of the first reference word, and the F(w k ) is the second heat value of the second reference word.

[0023] A second aspect of the present invention provides a device for mining community hot topics, the device comprising:

[0024] A first determination unit, configured to obtain a plurality of words in a community post and determine a first heat value of each of the words within a preset time period;

[0025] A correction unit, configured to correct the first heat value of each of the words based on a preset correction strategy to obtain a second heat value of each of the words;

[0026] The second determination unit obtains, for a first target word, a first corpus quantity including the first target word and a second target word, and obtains a second corpus quantity including the second target word; determines a reference topic based on the first corpus quantity and the second corpus quantity; the first target word is any word among all words, and the second target word is any word among the remaining words except the first target word;

[0027] The third determination unit is used to determine, for each reference topic, a first reference word and a second reference word in the reference topic, and determine that the reference topic is a hot topic based on the second heat values ​​of the first reference word and the second reference word and the number of third corpora containing the first reference word and the second reference word.

[0028] In the above solution, the first determining unit is specifically used for:

[0029] According to the formula Determine the first heat value S(w i ); wherein said w i is the first target word, i is the word sequence number, and T n is the nth time period within the preset time length, where n is the total number of time periods included in the preset time length, and T j is the jth time period within the preset time length, where j is any time period, j≤n; N(w i ,T n ) is the first target word w i In the nth time period T n The total number of occurrences in the i ,T j ) is the first target word w iIn the jth time period T j The total number of times it appears in .

[0030] According to a third aspect of the present invention, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the method described in any one of the first aspects is implemented.

[0031] According to a fourth aspect of the present invention, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method described in any one of the first aspects is implemented.

[0032] The present invention provides a method, device, medium and equipment for mining community hot topics. The method includes: obtaining multiple words in community posts, determining the first heat value of each word within a preset time length; performing heat correction on the first heat value of each word based on a preset correction strategy to obtain the second heat value of each word; for a first target word, obtaining the number of first corpora containing the first target word and the second target word, and obtaining the number of second corpora containing the second target word; determining a reference topic based on the number of the first corpora and the number of the second corpora; the first target word is any word among all the words, and the second target word is any word except the first target word. any word among the remaining words other than "", "", "", "" and "", for each reference topic, determine the first reference word and the second reference word in the reference topic, and determine that the reference topic is a hot topic based on the second heat values ​​of the first reference word and the second reference word and the number of third corpora containing the first reference word and the second reference word; in this way, after determining the first heat value of each word, continue to correct the first heat value to avoid the situation where a word is mistakenly considered to be a hot topic when the number of historical appearances and the current growth are both relatively small; then, when the present application mines hot topics through the combination of words and the second heat value of each word, it can also reduce mining errors and improve the accuracy of hot topics. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0034] Figure 1 A schematic diagram of a method for mining community hot topics provided by an embodiment of the present invention;

[0035] Figure 2A schematic diagram of the structure of a device for mining community hot topics provided by an embodiment of the present invention;

[0036] Figure 3 A schematic diagram of the computer device structure provided by an embodiment of the present invention;

[0037] Figure 4 A schematic diagram of the structure of a computer-readable storage medium provided for an embodiment of the present invention. DETAILED DESCRIPTION

[0038] In order to solve the technical problem in the prior art that the mining accuracy cannot be ensured when mining community hot spots, the present invention provides a method, device, medium and equipment for mining community hot topics.

[0039] In order to better understand the above technical scheme, the technical scheme of the embodiments of this specification is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of this specification and the specific features in the embodiments are detailed descriptions of the technical scheme of the embodiments of this specification, rather than limitations on the technical scheme of this specification. In the absence of conflict, the embodiments of this specification and the technical features in the embodiments can be combined with each other.

[0040] This embodiment provides a method for mining community hot topics, such as Figure 1 As shown, the method comprises the following steps:

[0041] S110, obtaining multiple words in a community post, and determining a first popularity value of each of the words within a preset time period;

[0042] For each community post in the live platform community, multiple words of the community post are obtained, and the first heat value of each word within a preset time period is determined. Here, for the convenience of subsequent description, each initial word segmented out can be regarded as the first target word, that is, the first target word is any word among the words.

[0043] This embodiment can use any segmentation method to segment community posts, and there is no limitation here. The preset duration can be set according to actual conditions, such as one week, half a month or one month, etc. The preset duration includes multiple time periods, and the duration of each time period is the same, such as 1 day.

[0044] In an optional embodiment, determining the first heat value of each word within a preset time period includes:

[0045] According to the formula Determine the first heat value S(w i ), where w i is the first target word, i is the word number, T nis the nth time period within the preset duration, n is the total number of time periods included in the preset duration, T j is the jth time period within the preset time length, j is any time period, j≤n; N(w i ,T n ) is the first target word w i In the nth time period T n The total number of occurrences in i ,T j ) is the first target word w i In the jth time period T j The total number of times it appears in . The nth time period is the time period closest to the current time, and n is a constant, which is generally 30.

[0046] The above formula means that the popularity value of a word depends on the increase in the number of times the word appears in the current time period compared to the number of times it appears in the past. In order to measure this increase, the total number of times the word appears in time period n (w i ,T n ) divided by the sum of the number of occurrences of the word in several historical time periods It indicates the historical proportion of the number of times a word appears in the most recent period of time. Obviously, the larger the proportion is, the greater the increase in the number of words in the most recent period of time, so the heat value of the word is higher.

[0047] For example, suppose there are 4 time periods, for word w i , and the number of occurrences in the four time periods are 5, 10, 20 and 100 respectively.

[0048] So

[0049] This step preliminarily determines the hot words by first determining the first heat value of each word, laying a foundation for the subsequent determination of hot topics.

[0050] S111, performing heat correction on the first heat value of each of the words based on a preset correction strategy to obtain a second heat value of each of the words;

[0051] In practical applications, this situation may also exist: if a word has appeared very few times in history and also appears less often in the current time period, then the first heat value of the word finally determined may also be very large.

[0052] Therefore, this embodiment also needs to perform heat correction on the first heat value of each word based on a preset correction strategy to obtain the second heat value of each word to avoid a word being mistakenly regarded as a hot word.

[0053] In an optional embodiment, the first heat value of each word is corrected based on a preset correction strategy to obtain the second heat value of each word, including:

[0054] Based on the formula Determine each first target word w i The second heat value F(w i );in,

[0055] w i is the first target word, i is the word number, m is the total number of words, T n is the nth time period within the preset duration, n is the total number of time periods included in the preset duration, X n is the number of times the first target word appears in the nth time period, S(w i ) is the first heat value of the first target word, N(w i ,T n ) is the first target word w i In the nth time period T n The total number of times it appears in .

[0056] The principle of the above formula is: It represents the average heat value of all words. It represents the average number of occurrences of all words in the current time period n. The first heat value is corrected mainly because if N(w i ,T n ) is very large (much larger than ), then the value of this term will tend to 1, so F(w i ) will tend to S(w i ), then the average The influence of N(w i ,T n ) is small, then the uncertainty in calculating the first heat value is very large, and the average value needs to be used. To correct the first heat value, S(w i ) will be smoothed (towards the average heat value ).

[0057] For example, continuing with the example in the above steps, assuming that the average heat value of all words is 0.25, and the average number of occurrences of all words in the nth time period is 30, then,

[0058]

[0059] This step corrects the first heat value of each word to avoid the situation where a word has appeared very few times in history and also appears less often in the current time period, and the first heat value of the word is likely to be very large. This avoids the phenomenon where a non-hot word is mistakenly identified as a hot word, ensuring the accuracy of mining.

[0060] S112, for a first target word, obtaining a first corpus quantity including the first target word and a second target word, and obtaining a second corpus quantity including the second target word; determining a reference topic based on the first corpus quantity and the second corpus quantity; the second target word is any word among the remaining words except the first target word;

[0061] In practical applications, generally speaking, the probability that a hot topic is a combination of words is relatively high. The more times two words appear together, the more credible the topic formed by the two words is. Different words have different abilities to generate topics. Therefore, this embodiment obtains the number of first corpora containing the first target word and the second target word, and obtains the number of second corpora containing the second target word for the first target word; determines the reference topic based on the number of first corpora and the number of second corpora; and the second target word is any word among the remaining words except the first target word.

[0062] It should be noted that the corpus is the text or comments in the community posts, and a piece of corpus can be understood as a piece of text or a comment.

[0063] In an optional embodiment, determining a reference topic based on the amount of the first corpus and the amount of the second corpus includes:

[0064] According to the formula Determine the subject ability expression value H(w i );

[0065] If it is determined that the topic ability expression value is greater than the preset topic expression threshold, the topic formed by the first target word and the second target word is determined as the reference topic; wherein,

[0066] The topic expression threshold can be set according to the actual situation and is not limited here; i is the first target word, w h is the second target word, i and h are word numbers, i and h have different values; m is the total number of words, C(w i , w h ) is the number of the first corpus containing the first target word and the second target word, that is, C(w i , w h) can also be understood as the number of first corpus corresponding to the first target word and the second target word that appear together in the first corpus in the statistics of all corpus; the C(w h ) is the number of the second corpus containing the second target word.

[0067] Among them, the factors affecting the topic expression threshold mainly include: the content operation quality required by the current operation community; if the platform requires high operation quality and the topic is more representative, then the threshold needs to be set larger; otherwise, it needs to be set smaller. The value range of the topic expression threshold can be 0.1 to 0.3.

[0068] The principle of the above formula is: if a word often appears with other words, it means that this word can generate more topic phrases and has a stronger ability to generate topics. In order to eliminate the difference in the frequency of other words, the co-occurrence ratio is used to represent the co-occurrence of the first target word. Therefore, the first target word w is counted i The average co-occurrence ratio with other words. The higher the average ratio, the higher the co-occurrence ratio. i The stronger the subject expression ability is, the more likely it is to form a reference subject.

[0069] For example: Assume that the first target word w i , the number of first corpora corresponding to the first target word and one of the second target words is 10, and the number of second corpora corresponding to the second target word is 100; the number of first corpora corresponding to the first target word and another second target word is 20, and the number of second corpora corresponding to the other second target word is 100. So:

[0070]

[0071] This step determines the reference topic by determining the co-occurrence ratio of the first target word and the second target word, which is equivalent to a preliminary screening of hot topics, laying a foundation for the subsequent determination of hot topics.

[0072] S113, for each reference topic, determine the first reference word and the second reference word in the reference topic, and determine that the reference topic is a hot topic based on the second heat value of the first reference word and the second reference word and the number of third corpora containing the first reference word and the second reference word.

[0073] After the reference topic is determined, not every reference topic is a hot topic. Therefore, this embodiment determines the first reference word and the second reference word in the reference topic for each reference topic, and determines the reference topic as a hot topic based on the second heat value of the first reference word and the second reference word and the number of third corpora containing the first reference word and the second reference word.

[0074] In an optional embodiment, the heat value of the reference topic is determined based on the second heat value of the first reference word, the second heat value of the second reference word, and the number of third corpora containing the first reference word and the second reference word;

[0075] If it is determined that the heat value is greater than a preset heat threshold, the reference topic is determined to be a hot topic.

[0076] Among them, the factors affecting the heat threshold mainly include: the amount of content required for the current operation of the community. If the demand for content is large, the heat threshold can be set smaller; if the demand for content is small, the heat threshold can be set larger; generally speaking, the value range of the heat threshold can be 2 to 5.

[0077] It can be understood that the scope of the first target term should include the first reference term, and the scope of the second target term should include the second reference term.

[0078] In an optional embodiment, determining the heat value of the reference topic based on the second heat value of the first reference word, the second heat value of the second reference word, and the number of third corpora containing the first reference word and the second reference word includes:

[0079] According to the formula T(p(w j , w k ))=C(w j , w k )max(F(w j ), F(w k )) Determine the heat value T(p(w j , w k )); wherein, the p(w j , w k ) is the first reference word w j and the second reference word w k The reference subject formed, j and k are word numbers, and the values ​​of j and k are different; C(w j , w k ) is the number of third corpora containing the first reference words and the second reference words, and the F(w i ) is the second heat value of the first reference word, and the F(w k ) is the second heat value of the second reference word.

[0080] The principle of the above formula is: the popularity value of a topic is affected by two factors. One is the popularity value of each word that makes up the topic word. Here we use w j and w k The second maximum value of the heat value max(F(w j ), F(wk ) is used to measure the popularity of the topic. The word with greater popularity can better represent the popularity of the topic. The other is the word w j and the word w k The number of co-occurrences in the entire corpus indicates that the more the topic is discussed, the greater the possibility that the topic is a hot topic.

[0081] For example: Assume that the first reference word w j and the second reference word w k The corresponding third corpus size is 50, the second heat value of the first reference word is 0.1, and the second heat value of the second reference word is 0.15, so:

[0082] T(p(w j , w k ))=50*max(0.15,0.1)=4.5

[0083] In this step, the heat value of the reference topic is determined and compared with the heat threshold, so that the hot topic can be accurately determined.

[0084] After determining the first heat value of each word, this embodiment continues to correct the first heat value to avoid the situation where a word is mistakenly considered to be a hot spot when the number of historical appearances and the current growth number are relatively small; then when the application mines hot topics through the combination of words and the second heat value of each word, it can also reduce mining errors and improve the accuracy of hot topics.

[0085] Based on the same inventive concept, this embodiment also provides a community hot topic mining device, such as Figure 2 As shown, the device comprises:

[0086] A first determination unit 21 is used to obtain multiple words in the community post and determine a first heat value of each of the words within a preset time period;

[0087] A correction unit 22, configured to correct the first heat value of each of the words based on a preset correction strategy to obtain a second heat value of each of the words;

[0088] The second determination unit 23 obtains, for a first target word, a first corpus quantity including the first target word and a second target word, and obtains a second corpus quantity including the second target word; determines a reference topic based on the first corpus quantity and the second corpus quantity; the first target word is any word among all words, and the second target word is any word among the remaining words except the first target word;

[0089] The third determination unit 24 is used to determine, for each reference topic, a first reference word and a second reference word in the reference topic, and determine that the reference topic is a hot topic based on the second heat value of the first reference word and the second reference word and the number of third corpora containing the first reference word and the second reference word.

[0090] The first determining unit 21 is specifically configured to:

[0091] According to the formula Determine the first heat value S(w i ); wherein said w i is the first target word, i is the word sequence number, and T n is the nth time period within the preset time length, where n is the total number of time periods included in the preset time length, and T j is the jth time period within the preset time length, where j is any time period, j≤n; N(w i ,T n ) is the first target word w i In the nth time period T n The total number of occurrences in the i ,T j ) is the first target word w i In the jth time period T j The total number of times it appears in .

[0092] The specific functions of the above units can be found in the corresponding descriptions in the above method embodiments, which will not be described in detail here. Since the device introduced in the embodiment of the present invention is a device used to implement the method of the embodiment of the present invention, based on the method introduced in the embodiment of the present invention, those skilled in the art can understand the specific structure and deformation of the device, so they will not be described in detail here. All devices used in the method of the embodiment of the present invention belong to the scope of protection of the present invention.

[0093] Based on the same inventive concept, this embodiment provides a computer device 300, such as Figure 3 As shown, it includes a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and executable on the processor 320. When the processor 320 executes the computer program 311, the following steps are implemented:

[0094] Acquire multiple words in community posts, and determine the first popularity value of each of the words within a preset time period;

[0095] Based on a preset correction strategy, the first heat value of each of the words is corrected to obtain a second heat value of each of the words;

[0096] For a first target word, obtain the amount of a first corpus containing the first target word and a second target word, and obtain the amount of a second corpus containing the second target word; determine a reference topic based on the amount of the first corpus and the amount of the second corpus; the first target word is any word among all words, and the second target word is any word among the remaining words except the first target word;

[0097] For each reference topic, determine the first reference word and the second reference word in the reference topic, and determine that the reference topic is a hot topic based on the second heat value of the first reference word and the second reference word and the number of third corpora containing the first reference word and the second reference word.

[0098] In a specific implementation process, when the processor 420 executes the computer program 411, any implementation method in the embodiment can be implemented.

[0099] Since the computer device introduced in this embodiment is a device used to implement a method for a community hot topic in the embodiment of this application, based on the method introduced in the first embodiment of this application, a person skilled in the art can understand the specific implementation of the computer device in this embodiment and its various variations, so how the server implements the method in the embodiment of this application is not described in detail here. As long as the device used by a person skilled in the art to implement the method in the embodiment of this application is within the scope of protection of this application.

[0100] Based on the same inventive concept, this embodiment provides a computer-readable storage medium 400, such as Figure 4 As shown, a computer program 411 is stored thereon, and when the computer program 411 is executed by a processor, the following steps are implemented:

[0101] Acquire multiple words in community posts, and determine the first popularity value of each of the words within a preset time period;

[0102] Based on a preset correction strategy, the first heat value of each of the words is corrected to obtain a second heat value of each of the words;

[0103] For a first target word, obtain the amount of a first corpus containing the first target word and a second target word, and obtain the amount of a second corpus containing the second target word; determine a reference topic based on the amount of the first corpus and the amount of the second corpus; the first target word is any word among all words, and the second target word is any word among the remaining words except the first target word;

[0104] For each reference topic, determine the first reference word and the second reference word in the reference topic, and determine that the reference topic is a hot topic based on the second heat value of the first reference word and the second reference word and the number of third corpora containing the first reference word and the second reference word.

[0105] In the specific implementation process, when the computer program 411 is executed by a processor, any implementation method in the aforementioned embodiments can be implemented.

[0106] The method, device, medium and equipment for mining community hot topics provided by the present invention can bring at least the following beneficial effects:

[0107] The present invention provides a method, device, medium and equipment for mining community hot topics. The method includes: obtaining multiple words in community posts, determining the first heat value of each word within a preset time length; performing heat correction on the first heat value of each word based on a preset correction strategy to obtain the second heat value of each word; for a first target word, obtaining the number of first corpora containing the first target word and the second target word, and obtaining the number of second corpora containing the second target word; determining a reference topic based on the number of the first corpora and the number of the second corpora; the first target word is any word among all the words, and the second target word is any word except the first target word. any word among the remaining words except the first reference word; for each reference topic, determine the first reference word and the second reference word in the reference topic, and determine that the reference topic is a hot topic based on the second heat values ​​of the first reference word and the second reference word and the number of third corpora containing the first reference word and the second reference word; in this way, after determining the first heat value of each word, continue to correct the first heat value to avoid the situation where a word is mistakenly considered to be a hot topic when the number of historical appearances and the current increase are both relatively small; then, when the present application mines hot topics through the combination of words and the second heat value of each word, it can also reduce mining errors and improve the accuracy of hot topics. Moreover, using a combination of words to determine hot topics can, to a certain extent, expand the scope of mining hot topics and improve the mining coverage of hot topics compared to the method of using only a single word to determine.

[0108] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0109] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0110] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0111] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0112] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0113] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for mining community hot topics, characterized in that: The method comprises: Acquire multiple words in community posts, and determine the first popularity value of each of the words within a preset time period; Based on a preset correction strategy, the first heat value of each of the words is corrected to obtain a second heat value of each of the words; For a first target word, obtain the amount of a first corpus containing the first target word and a second target word, and obtain the amount of a second corpus containing the second target word; determine a reference topic based on the amount of the first corpus and the amount of the second corpus; the first target word is any word among all words, and the second target word is any word among the remaining words except the first target word; For each reference topic, determine the first reference word and the second reference word in the reference topic, and determine that the reference topic is a hot topic based on the second heat value of the first reference word and the second reference word and the number of third corpora containing the first reference word and the second reference word.

2. The method according to claim 1, characterized in that The determining of the first heat value of each of the words within a preset time period includes: According to the formula Determine the first heat value S(w i ); wherein said w i is the first target word, i is the word sequence number, and T n is the nth time period within the preset time length, where n is the total number of time periods included in the preset time length, and T j is the jth time period within the preset time length, where j is any time period, j≤n; N(w i ,T n ) is the first target word w i In the nth time period T n The total number of occurrences in the i ,T j ) is the first target word w i In the jth time period T j The total number of times it appears in .

3. The method according to claim 1, characterized in that The first heat value of each of the words is corrected based on a preset correction strategy to obtain a second heat value of each of the words, including: Based on the formula Determine each of the first target words w i The second heat value F(w i ); wherein said w i is the first target word, i is the word sequence number, m is the total number of words, and T n is the nth time period within the preset time length, where n is the total number of time periods included in the preset time length, and X n is the number of times the first target word appears in the nth time period, and the S(w i ) is the first heat value, and the N(w i ,T n ) is the first target word w i In the nth time period T n The total number of times it appears in .

4. The method according to claim 1, characterized in that The determining of a reference topic based on the first corpus quantity and the second corpus quantity includes: According to the formula Determine the subject ability expression value H(w i ); If it is determined that the topic ability expression value is greater than a preset topic expression threshold, the topic formed by the first target word and the second target word is determined as the reference topic; wherein, The w i is the first target word, the w h is the second target word, i and h are word numbers, and the values ​​of i and h are different; m is the total number of words, and C(w i , w h ) is the number of first corpus containing the first target word and the second target word, and C(w h ) is the number of second corpora containing the second target word, and the corpus is the text or comments in the community post.

5. The method according to claim 1, characterized in that The determining that the reference topic is a hot topic based on the first reference word, the second heat value of the second reference word, and the number of third corpora containing the first reference word and the second reference word includes: Determine the heat value of the reference topic based on the second heat value of the first reference word, the second heat value of the second reference word, and the amount of third corpus containing the first reference word and the second reference word; If it is determined that the heat value is greater than a preset heat threshold, the reference topic is determined to be a hot topic.

6. The method according to claim 5, characterized in that The determining the heat value of the reference topic based on the second heat value of the first reference word, the second heat value of the second reference word, and the number of third corpora containing the first reference word and the second reference word includes: According to the formula T(p(w j ,w k ))=C(w j ,w k )max(F(w j ), F(w k )) Determine the heat value T(p(w j ,w k )); wherein, the p(w j ,w k ) is the first reference word w j and the second reference word w k The reference subject formed, j and k are word numbers, and the values ​​of j and k are different; C(w j ,w k ) is the number of third corpora containing the first reference words and the second reference words, and the F(w j ) is the second heat value of the first reference word, and the F(w k ) is the second heat value of the second reference word.

7. A device for mining community hot topics, characterized in that: The device comprises: A first determination unit, configured to obtain a plurality of words in a community post and determine a first heat value of each of the words within a preset time period; A correction unit, configured to correct the first heat value of each of the words based on a preset correction strategy to obtain a second heat value of each of the words; The second determination unit obtains, for a first target word, a first corpus quantity including the first target word and a second target word, and obtains a second corpus quantity including the second target word; determines a reference topic based on the first corpus quantity and the second corpus quantity; the first target word is any word among all words, and the second target word is any word among the remaining words except the first target word; The third determination unit is used to determine, for each reference topic, a first reference word and a second reference word in the reference topic, and determine that the reference topic is a hot topic based on the second heat values ​​of the first reference word and the second reference word and the number of third corpora containing the first reference word and the second reference word.

8. The device according to claim 7, characterized in that The first determining unit is specifically configured to: According to the formula Determine the first heat value S(w i ); wherein said w i is the first target word, i is the word sequence number, and T n is the nth time period within the preset time length, where n is the total number of time periods included in the preset time length, and T j is the jth time period within the preset time length, where j is any time period, j≤n; N(w i ,T n ) is the first target word w i In the nth time period T n The total number of occurrences in the i ,T j ) is the first target word w i In the jth time period T j The total number of times it appears in .

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

10. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 6 is implemented.

Images