CN113886585A - Item recommendation method, computer device and computer-readable storage medium - Google Patents
Item recommendation method, computer device and computer-readable storage medium Download PDFInfo
- Publication number
- CN113886585A CN113886585A CN202111165808.1A CN202111165808A CN113886585A CN 113886585 A CN113886585 A CN 113886585A CN 202111165808 A CN202111165808 A CN 202111165808A CN 113886585 A CN113886585 A CN 113886585A
- Authority
- CN
- China
- Prior art keywords
- evaluation
- text
- emotion
- word
- preset
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3346—Query execution using probabilistic model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/237—Lexical tools
- G06F40/242—Dictionaries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
Abstract
An item recommendation method, a computer device and a computer-readable storage medium, the method comprising: acquiring a plurality of evaluation texts; performing word segmentation processing on each evaluation text to obtain a sentence set corresponding to each evaluation text; extracting emotion evaluation words of each evaluation text by using a preset emotion dictionary to obtain an emotion evaluation word set corresponding to the emotion evaluation words; obtaining an emotion evaluation unit set corresponding to the preset evaluation object dictionary and the preset adverb dictionary based on the statement set and emotion evaluation word set of each evaluation text; calculating the evaluation score of the item recorded by the evaluation text based on the emotion evaluation unit set of the evaluation text, and summarizing the evaluation score of each item to obtain the evaluation value of each item; and selecting at least one item from the items according to the evaluation value of each item, and recommending the selected item to the target user. The emotion evaluation unit is constructed on the basis of the evaluation text, and then the evaluation text is obtained according to the emotion evaluation unit to recommend the article to the evaluation score of the article, so that the article recommendation effect is better.
Description
Technical Field
The present application relates to the field of data processing technologies, and in particular, to an item recommendation method, a computer device, and a computer-readable storage medium.
Background
The recommendation system is used as an information screening tool, exists on the basis of mass data, and can effectively solve the problem of information overload. The recommendation system can dig out items (such as information, services, articles and the like) which are interested by the user from the mass data through a recommendation algorithm, and recommend the result to the user so as to meet the requirements of the user.
Although the conventional collaborative filtering algorithm can slow down the influence of data sparsity and cold start on a recommendation result, the evaluation value of mass data on articles commented on the collaborative filtering algorithm is not considered, so that the recommendation effect is poor, and the use experience of a user is influenced.
Disclosure of Invention
In view of the above, it is desirable to provide an item recommendation method, a computer device and a computer-readable storage medium for solving the technical problem that the accuracy of item recommendation is not high.
An embodiment of the present application provides an article recommendation method, including: obtaining a plurality of evaluation texts, wherein the plurality of evaluation texts relate to a plurality of articles; performing word segmentation processing on each evaluation text in the plurality of evaluation texts to obtain a sentence set corresponding to each evaluation text; extracting emotion evaluation words of each evaluation text by using a preset emotion dictionary to obtain an emotion evaluation word set corresponding to each evaluation text; obtaining an emotion evaluation unit set corresponding to each evaluation text based on a preset evaluation object dictionary, a preset adverb dictionary and a sentence set and an emotion evaluation word set corresponding to each evaluation text, wherein the emotion evaluation unit set comprises at least one emotion evaluation unit; calculating to obtain the evaluation score of each evaluation text for the recorded article based on the emotion evaluation unit set of each evaluation text, and summarizing the evaluation score of each article to obtain the evaluation value of each article; and selecting at least one item from the plurality of items according to the evaluation value of each item, and recommending the selected at least one item to the target user.
In some embodiments, the preset emotion dictionary includes a basic emotion dictionary, a network word emotion dictionary and an expression picture emotion dictionary, the basic emotion dictionary includes a plurality of positive emotion words, a plurality of negative emotion words, a plurality of positive evaluation words and a plurality of negative evaluation words, the network word emotion dictionary includes a plurality of positive network words and a plurality of negative network words, the expression picture emotion dictionary includes a plurality of expression pictures and emotion polarity words corresponding to the expression pictures, the preset evaluation object dictionary includes a plurality of item names and a plurality of item component names, the preset adverb dictionary includes a plurality of adverbs for representing emotion polarity or emotion degree, and the item recommendation method further includes: and performing stop word removing processing and part-of-speech tagging processing on each evaluation text.
In some embodiments, extracting an emotion evaluation word of each evaluation text by using a preset emotion dictionary to obtain an emotion evaluation word set corresponding to each evaluation text, including: extracting emotion evaluation words of the evaluation text by using a preset emotion dictionary; screening emotion evaluation words with the frequency of occurrence of the evaluation text larger than the preset frequency from the extracted emotion evaluation words; and constructing an emotion evaluation word set corresponding to the evaluation text based on the emotion evaluation words obtained by screening.
In some embodiments, the obtaining of the emotion evaluation unit set corresponding to each evaluation text based on the preset evaluation object dictionary, the preset adverb dictionary, and the sentence set and emotion evaluation word set corresponding to each evaluation text includes: traversing sentences in a sentence set corresponding to the first evaluation text, and judging whether the sentences contain words in a preset evaluation object dictionary and words in an emotion evaluation word set corresponding to the first evaluation text; when the sentence contains a first word in a preset evaluation object dictionary and a second word in the emotion evaluation word set, constructing a binary evaluation unit based on the first word and the second word, and adding the binary evaluation unit to the emotion evaluation unit set corresponding to the first evaluation text; judging whether the sentence contains words in a preset adverb dictionary; and when the sentence comprises a third word in the preset adverb dictionary and the word positions of the first word and the third word in the sentence meet the preset requirement, constructing a ternary evaluation unit based on the first word, the second word and the third word, and replacing the binary evaluation unit in the emotion evaluation unit set with the ternary evaluation unit.
In some embodiments, the item recommendation method further comprises: and when the frequency of the binary evaluation units appearing in the emotion evaluation unit set is less than the preset frequency, deleting the binary evaluation units from the emotion evaluation unit set.
In some embodiments, calculating a rating score of the item described by each rating text based on the emotion rating unit set of each rating text comprises: calculating to obtain comment scores of the evaluation text according to the number of the ternary evaluation units in the emotion evaluation unit set corresponding to the evaluation text; and calculating the evaluation score of the evaluation text for the recorded article based on the influence index and the comment score of the evaluation text, wherein the influence index of the evaluation text is obtained based on the fan number of the user who issues the evaluation text, the forwarding number of the evaluation text and the comment number.
In some embodiments, the evaluation value of each article is calculated by the following equation:
Rm＝J×K×P，
Em＝αX+βY+γZ，
wherein D isuIs the evaluation value of the item u, N is the total number of evaluation texts, RmFor the mth evaluation text, EmThe comment score of the mth evaluation text, J is the fan number of the user who issues the mth evaluation text, and K is the forwarding of the mth evaluation textThe number of the comments is M, P is the number of the comments of the mth evaluation text, X is the comment score of the ternary evaluation unit contained in the mth evaluation text, Y is the comment score of the ternary evaluation unit contained in the forward text for forwarding the mth evaluation text, Z is the comment score of the ternary evaluation unit contained in the evaluation text for reviewing the mth evaluation text, and H is1The number of ternary evaluation units contained in the mth evaluation text, H2The number of ternary evaluation units, H, contained in the forwarded text for forwarding the mth evaluation text3The number of ternary evaluation units contained in the evaluation text for commenting the mth evaluation text, XiIs the comment score of the ith ternary evaluation unit contained in the mth evaluation text, YiThe comment score Z of the ith ternary evaluation unit contained in the forwarded text for forwarding the mth evaluation textiAlpha, beta and gamma are preset constants for the comment score of the ith ternary evaluation unit contained in the evaluation text for commenting the mth evaluation text.
In some embodiments, selecting at least one item from the plurality of items to recommend to the target user based on the rating value of each item includes: obtaining the evaluation grade of each article according to the evaluation value of each article; recommending the articles at the preset evaluation level to the target user.
An embodiment of the present application provides a computer device, which includes a processor and a memory, where the memory stores a plurality of computer programs, and the processor is configured to implement the steps of the item recommendation method when executing the computer programs stored in the memory.
An embodiment of the present application further provides a computer-readable storage medium, which stores a plurality of instructions, where the plurality of instructions are executable by one or more processors to implement the steps of the item recommendation method.
Compared with the prior art, the article recommendation method, the computer device and the computer readable storage medium construct the emotion evaluation unit based on the plurality of evaluation texts associated with the articles, obtain the evaluation scores of the articles recorded by the evaluation texts according to the emotion evaluation unit, classify the evaluation values of the articles according to the evaluation of the articles, and select the articles falling into the classification with better evaluation values to recommend to the user, so that the article recommendation effect is better.
Drawings
Fig. 1 is an application environment diagram of an item recommendation method according to an embodiment of the present application.
Fig. 2 is a flowchart of an item recommendation method according to an embodiment of the present application.
Fig. 3 is a functional block diagram of an article recommendation device according to an embodiment of the present application.
Fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Description of the main elements
The following detailed description will further illustrate the present application in conjunction with the above-described figures.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It is further noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
In the present application, "at least one" means one or more, "and" a plurality "means two or more. "and/or" describes an association relationship of associated objects, meaning that three relationships may exist, e.g., A and/or B may represent: a exists alone, A and B exist simultaneously, and B exists alone, wherein A and B can be singular or plural. The terms "first," "second," "third," "fourth," and the like in the description and in the claims and drawings of the present application, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order.
Fig. 1 is an application environment diagram of an item recommendation method according to an embodiment of the present application. Referring to fig. 1, an item recommendation method is applied to an item recommendation system. The item recommendation system may include a terminal 11 and a server 12, and the terminal 11 may be an electronic device used by a target user. The terminal 11 and the server 12 are connected through a wired network or a wireless network. The terminal 11 may specifically be a desktop terminal or a mobile terminal, and the mobile terminal may specifically be at least one of a mobile phone, a tablet computer, a notebook computer, and the like. The server 12 may be implemented as a stand-alone server or as a server cluster of multiple servers.
The item recommendation system is a tool for associating users and items based on mass data mining, and can help the users to screen information in which the users are interested in the information overload environment, and personalized decision support and information service are provided for the users. The item recommendation system can refer to recommendation of commodities (such as foods, living goods, electronic products, clothes and the like), recommendation of audio and video contents, recommendation of articles and the like for a user. This is not a limitation of the present application.
Fig. 2 is a flowchart of an item recommendation method according to an embodiment of the present application. The present embodiment is exemplified by applying the method to the server 12 in fig. 1, and according to different requirements, the order of the steps in the flowchart may be changed, and some steps may be omitted.
Step S20, a plurality of evaluation texts are acquired.
In some embodiments, the plurality of rating texts may relate to a plurality of items. Each rating text may relate to a rating of an item. The evaluation text can be microblog text published by microblog users, friend circle text published by micro credit users, posts published by forum/community users, evaluation text published by evaluation website users and the like. Some applications or web sites may have a plurality of evaluation texts related to articles stored on a server, and the plurality of evaluation texts may be obtained from the server. In other embodiments, the plurality of rating texts may be obtained by a method such as web crawling.
And step 21, performing word segmentation processing on each evaluation text in the plurality of evaluation texts to obtain a sentence set corresponding to each evaluation text.
In some embodiments, when multiple evaluation texts are obtained, word segmentation processing may be performed on each evaluation text to obtain a sentence set corresponding to each evaluation text. The set of sentences may include at least one sentence. For example, an ICTCLAS chinese word segmentation system may be used to perform word segmentation on a chinese evaluation text to obtain a plurality of sentences.
In some embodiments, in the word segmentation process, stop word processing and part-of-speech tagging processing may be further performed on the evaluation text, and position information of a word with a preset part-of-speech in the sentence is recorded. For example, position information of a name, an adjective, and an adverb in a sentence is recorded.
And step 22, extracting the emotion evaluation words of each evaluation text by using a preset emotion dictionary to obtain an emotion evaluation word set corresponding to each evaluation text.
In some embodiments, the preset emotion dictionary may include a base emotion dictionary, a network expression emotion dictionary, and an emoticon emotion dictionary. The base emotion dictionary may include a plurality of positive emotion words, a plurality of negative emotion words, a plurality of positive evaluation words, and a plurality of negative evaluation words, for example, the base emotion dictionary may be a HoWNET (HOWNET). The network expression emotion dictionary can comprise a plurality of active network words and a plurality of passive network words, and can be constructed by collecting network expressions in a plurality of network expression websites and screening words with emotion polarity. The expression picture emotion dictionary may include a plurality of expression pictures and emotion polarity words corresponding to the plurality of expression pictures, and the expression pictures may be expression pictures included in a website or application corresponding to the evaluation text.
In some embodiments, when a plurality of emotion assessment words are extracted from the assessment text by using a preset emotion dictionary, the emotion assessment words may be sorted according to the occurrence frequency of the emotion assessment words, for example, sorted from the most to the least of the occurrence frequency or sorted from the least to the most of the occurrence frequency, and an emotion assessment word whose occurrence frequency is greater than a preset value or ranked at a preset position is selected from the selected emotion assessment words, and then an emotion assessment word set corresponding to the assessment text is constructed based on the selected emotion assessment words. The preset value or the preset position can be set according to actual requirements, and the method is not limited in the application.
And step 23, obtaining an emotion evaluation unit set corresponding to each evaluation text based on the preset evaluation object dictionary, the preset adverb dictionary and the sentence set and emotion evaluation word set corresponding to each evaluation text.
In some embodiments, the preset rating object dictionary may include a plurality of item names and a plurality of item part names, for example, the item name may be a manufacturer + product, such as a millet mobile phone, and the item part name associated with the item name may be a battery, a screen, a frame, or the like. The predetermined adverb dictionary may include a plurality of adverbs for characterizing emotional polarity or emotional degree, for example, an adverb for characterizing emotional polarity may include "none, not, so, never, none, neither, etc., and an adverb for characterizing emotional degree may include" very, out, very, special, excessive, slight, comparative, a little, abnormal, straight ", etc.
In some embodiments, the set of sentiment evaluation units may include at least one ternary sentiment evaluation unit. The following description will take as an example the processing of a first comment text of a plurality of comment texts: when a first sentence set and a first emotion evaluation word set corresponding to the first evaluation text are obtained, traversing sentences in the first sentence set, and judging whether the sentences contain words in a preset evaluation object dictionary and words in the first emotion evaluation word set; when the sentence contains a first word in a preset evaluation object dictionary and a second word in a first emotion evaluation word set, constructing a binary evaluation unit based on the first word and the second word, and adding the binary evaluation unit to the emotion evaluation unit set corresponding to the first evaluation text; judging whether the sentence contains words in a preset adverb dictionary; when the sentence contains a third word in the preset adverb dictionary and the word positions of the first word and the third word in the sentence meet the preset requirement (for example, the first word and the third word are separated by 4 words in the sentence, the preset requirement is considered to be met), a ternary evaluation unit is constructed based on the first word, the second word and the third word, and the binary evaluation unit in the emotion evaluation unit set is replaced by the ternary evaluation unit.
In some embodiments, when the number of occurrences of a binary evaluation unit in the emotion evaluation unit set is less than a preset number, the binary evaluation unit may be deleted from the emotion evaluation unit set, i.e., the binary evaluation unit is not subjected to ternary evaluation unit conversion processing. The preset number of times may be set according to actual requirements, for example, the preset number of times may be 2 times.
In some embodiments, the emotion assessment unit set for each assessment text can be obtained by constructing a model by the emotion assessment unit. The input of the emotion evaluation unit construction model can comprise the following steps: the emotion evaluation unit comprises a word set S of an evaluation text, an emotion evaluation word set F of the evaluation text, an evaluation object set L, an adverb set B, a preset number of times t and a range d, and the output of the emotion evaluation unit construction model can comprise an emotion evaluation unit set W. The emotion evaluation unit construction model can be constructed in the following way to obtain an emotion evaluation unit set of the evaluation text: a is1) Initializing parameters t, d, W; a is2) For each sentence S in the set of words S1If a statement s1In the presence of a word e1E.f and the presence of a word e2E.g. L, and the word e1And the word e2Performing Cartesian product operation to form a binary evaluation unit<e1,e2>And a binary evaluation unit<e1,e2>Adding an emotion evaluation unit set W; a is3) For each binary evaluation unit in the emotion evaluation unit set W, if the occurrence frequency of the binary evaluation unit is less than the preset frequency, removing the binary evaluation unit from the emotion evaluation unit set W; a is4) For each binary evaluation unit in emotion evaluation unit set W subjected to removal processing, for example, binary evaluation unit<e1,e2>Get the word e1In a sentence s1Position i in if statement s1In the presence of a word e3E is e and B3∈[i-d,i+d]Constructing a ternary evaluation unit<e1,e2,e3>A ternary evaluation unit<e1,e2,e3>Replacement of binary evaluation units in emotion evaluation unit set W<e1,e2>Otherwise, collecting the two-element evaluation units in the emotion evaluation unit set W<e1,e2>Replacement by ternary evaluation Unit<e1,e2,0>。
And 24, calculating the evaluation score of each item recorded by each evaluation text based on the emotion evaluation unit set of each evaluation text, and summarizing the evaluation score of each item to obtain the evaluation value of each item.
In some embodiments, the comment score of the evaluation text can be calculated according to the number of the ternary evaluation units in the emotion evaluation unit set corresponding to the evaluation text, and then the evaluation score of the evaluation text for the articles recorded by the evaluation text can be calculated based on the influence index and the comment score of the evaluation text, wherein the influence index of the evaluation text can be obtained based on the number of fans of the user who issues the evaluation text, the forwarding number of the evaluation text and the number of comments.
After the evaluation score of the item described in each evaluation text is calculated, the evaluation score of each item may be summarized to obtain the evaluation value of each item.
In some embodiments, the item rating information referred to by each rating text may be present in the rating text itself, in a forwarding text forwarding the rating text, and in a comment text commenting on the rating text, i.e., the comment score of each rating text may consist of three parts: the comment scores of the text are evaluated, the comment scores of the forwarded text and the comment scores of the comment text are forwarded. The evaluation value of each article can be calculated by the following equation (i):
Rm＝J×K×P，
Em＝αX+βY+γZ，
wherein D isuIs the evaluation value of the item u, N is the total number of evaluation texts, RmFor the mth evaluation text, EmThe comment score is the comment score of the mth comment text, J is the fan number of the user who issues the mth comment text, K is the forwarding number of the mth comment text, P is the comment number of the mth comment text, X is the comment score average value of the ternary evaluation unit contained in the mth comment text, Y is the comment score average value of the ternary evaluation unit contained in the forwarding text which forwards the mth comment text, Z is the comment score average value of the ternary evaluation unit contained in the comment text which reviews the mth comment text, H is H1The number of ternary evaluation units contained in the mth evaluation text, H2The number of ternary evaluation units, H, contained in the forwarded text for forwarding the mth evaluation text3The number of ternary evaluation units contained in a comment text for commenting on the mth comment text, XiIs the comment score of the ith ternary evaluation unit contained in the mth evaluation text, YiThe comment score Z of the ith ternary evaluation unit contained in the forwarded text for forwarding the mth evaluation textiTo comment on the m < th > oneAnd alpha, beta and gamma are all preset constants of the comment scores of the ith ternary evaluation unit contained in the comment text of the evaluation text.
In some embodiments, the comment score of each ternary evaluation unit may be preset according to actual needs, or set based on the cartesian product of the ternary evaluation units.
And 25, selecting at least one item from the plurality of items according to the evaluation value of each item, and recommending the selected item to the target user.
In some embodiments, when the evaluation value of each article is calculated, the evaluation value of each article may be converted according to a preset rule to obtain an evaluation level of each article, and the article at the preset evaluation level may be recommended to the target user. For example, the rating scale may include four scales: the method comprises the steps of strong negative, positive and strong positive, recommending strong positive articles to a user, or sorting articles belonging to a positive interval or above from high to low evaluation values, and selecting the v-position articles with the top rank to recommend to a target user.
According to the article recommendation method, the emotion evaluation unit is constructed on the basis of the evaluation texts related to the articles, the evaluation scores of the articles recorded by the evaluation texts are obtained according to the emotion evaluation unit, the articles are classified according to the evaluation of the articles, the articles falling into the classification with a good evaluation value are selected and recommended to the user, and the article recommendation effect is better.
Based on the same idea as the item recommendation method in the above embodiment, the present application also provides an item recommendation apparatus, which may be used to execute the above item recommendation method. For convenience of explanation, only the parts related to the embodiments of the present application are shown in the schematic structural diagram of the embodiments of the article recommendation device, and those skilled in the art will understand that the illustrated structure does not constitute a limitation of the device, and may include more or less components than those illustrated, or combine some components, or arrange different components.
As shown in fig. 3, the item recommendation apparatus 100 includes an acquisition module 101, a processing module 102, an extraction module 103, a construction module 104, a calculation module 105, and a recommendation module 106. In some embodiments, the modules may be programmable software instructions stored in a memory and invoked for execution by a processor. It will be appreciated that in other embodiments, the modules may also be program instructions or firmware (firmware) that are resident in the processor.
The obtaining module 101 is configured to obtain a plurality of evaluation texts.
In some embodiments, the plurality of rating texts may relate to a plurality of items. Each rating text may relate to a rating of an item. The evaluation text can be microblog text published by microblog users, friend circle text published by micro credit users, posts published by forum/community users, evaluation text published by evaluation website users and the like.
The processing module 102 is configured to perform word segmentation on each evaluation text in the multiple evaluation texts to obtain a sentence set corresponding to each evaluation text.
In some embodiments, the processing module 102 may perform word segmentation on the chinese evaluation text by using an ICTCLAS chinese word segmentation system to obtain a plurality of sentences. The processing module 102 may also perform stop word processing and part-of-speech tagging processing on the evaluation text in the word segmentation processing process, and record position information of words with preset parts-of-speech in the sentence.
The extraction module 103 is configured to extract an emotion evaluation word of each evaluation text by using a preset emotion dictionary to obtain an emotion evaluation word set corresponding to each evaluation text.
In some embodiments, the preset emotion dictionary may include a basic emotion dictionary, a network phrase emotion dictionary, an emotion dictionary of emotion of network. When a plurality of emotion evaluation words are extracted from an evaluation text by using a preset emotion dictionary, sorting can be performed according to the occurrence frequency of the emotion evaluation words, for example, sorting is performed from more to less of the occurrence frequency or sorting is performed from less to more of the occurrence frequency, emotion evaluation words with occurrence frequency greater than a preset value or ranked at a preset position are screened from the emotion evaluation words, and an emotion evaluation word set corresponding to the evaluation text is constructed based on the screened emotion evaluation words. The preset value or the preset position can be set according to actual requirements, and the method is not limited in the application.
The construction module 104 is configured to obtain an emotion evaluation unit set corresponding to each evaluation text based on a preset evaluation object dictionary, a preset adverb dictionary, and a sentence set and an emotion evaluation word set corresponding to each evaluation text.
In some embodiments, the set of sentiment evaluation units may include at least one ternary sentiment evaluation unit. The following description takes as an example that the construction module 104 processes a first evaluation text in the plurality of evaluation texts: when a first sentence set and a first emotion evaluation word set corresponding to the first evaluation text are obtained, traversing sentences in the first sentence set, and judging whether the sentences contain words in a preset evaluation object dictionary and words in the first emotion evaluation word set; when the sentence contains a first word in a preset evaluation object dictionary and a second word in a first emotion evaluation word set, constructing a binary evaluation unit based on the first word and the second word, and adding the binary evaluation unit to the emotion evaluation unit set corresponding to the first evaluation text; judging whether the sentence contains words in a preset adverb dictionary; when the sentence contains a third word in a preset adverb dictionary and the word positions of the first word and the third word in the sentence meet preset requirements, a ternary evaluation unit is constructed based on the first word, the second word and the third word, and the binary evaluation unit in the emotion evaluation unit set is replaced by the ternary evaluation unit.
The calculating module 105 is used for calculating the evaluation score of the goods recorded by each evaluation text based on the emotion evaluation unit set of each evaluation text, and summarizing the evaluation score of each goods to obtain the evaluation value of each goods.
In some embodiments, the calculation module 105 may calculate a comment score of the evaluation text according to the number of ternary evaluation units in the emotion evaluation unit set corresponding to the evaluation text, and then calculate an evaluation score of the evaluation text for an article recorded by the evaluation text based on the influence index and the comment score of the evaluation text, where the influence index of the evaluation text may be obtained based on the fan count of the user who issued the evaluation text, the forwarding number of the evaluation text, and the comment number. After calculating the evaluation score of each article described in each evaluation text, the calculation module 105 may also sum the evaluation scores of each article to obtain the evaluation value of each article.
The recommending module 106 is configured to select at least one item from the multiple items according to the evaluation value of each item and recommend the selected at least one item to the target user.
In some embodiments, when the evaluation value of each item is calculated, the recommending module 106 may convert the evaluation value of each item according to a preset rule to obtain an evaluation level of each item, and recommend the item at the preset evaluation level to the target user. For example, the rating scale may include four scales: the method comprises the steps of strong negative, positive and strong positive, recommending strong positive articles to a user, or sorting articles belonging to a positive interval or above from high to low evaluation values, and selecting the v-position articles with the top rank to recommend to a target user.
Fig. 4 is a schematic diagram of a hardware structure of the electronic device 10 according to an embodiment of the present disclosure. As shown in fig. 4, the electronic device 10 may include a processor 1001, a memory 1002, and a communication bus 1003. The memory 1002 is used to store one or more computer programs 1004. One or more computer programs 1004 are configured to be executed by the processor 1001. The one or more computer programs 1004 include instructions that may be used to implement the method for item recommendation described in FIG. 2 for execution in the electronic device 10.
The Processor 1001 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the like.
The memory 1002 may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other non-volatile solid state storage device.
It is to be understood that the illustrated structure of the present embodiment does not constitute a specific limitation to the electronic device 10. In other embodiments, electronic device 10 may include more or fewer components than shown, or combine certain components, or split certain components, or a different arrangement of components.
The present embodiment also provides a computer storage medium, where computer instructions are stored in the computer storage medium, and when the computer instructions are run on an electronic device, the electronic device is caused to execute the above related method steps to implement the item recommendation method in the above embodiment.
The present embodiment also provides a computer program product, which when running on a computer, causes the computer to execute the relevant steps described above, so as to implement the item recommendation method in the above embodiments.
Through the above description of the embodiments, it is clear to those skilled in the art that, for convenience and simplicity of description, the foregoing division of the functional modules is merely used as an example, and in practical applications, the above function distribution may be completed by different functional modules according to needs, that is, the internal structure of the device may be divided into different functional modules to complete all or part of the above described functions.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described embodiments of the apparatus are illustrative, and for example, the division of the module or unit into one logical functional division may be implemented in another way, for example, a plurality of units or components may be combined or integrated into another apparatus, or some features may be omitted, or not implemented. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a readable storage medium. Based on such understanding, the technical solutions of the embodiments of the present application may be essentially or partially contributed to by the prior art, or all or part of the technical solutions may be embodied in the form of a software product, where the software product is stored in a storage medium and includes several instructions to enable a device (which may be a single chip, a chip, or the like) or a processor (processor) to execute all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above description is only an embodiment of the present application, but the scope of the present application is not limited thereto, and any changes or substitutions within the technical scope of the present disclosure should be covered by the scope of the present application.
Claims (10)
1. An item recommendation method, characterized in that the method comprises:
obtaining a plurality of rating texts, wherein the plurality of rating texts relate to a plurality of items;
performing word segmentation processing on each evaluation text in the plurality of evaluation texts to obtain a sentence set corresponding to each evaluation text;
extracting emotion evaluation words of each evaluation text by using a preset emotion dictionary to obtain an emotion evaluation word set corresponding to each evaluation text;
obtaining an emotion evaluation unit set corresponding to each evaluation text based on a preset evaluation object dictionary, a preset adverb dictionary and a sentence set and an emotion evaluation word set corresponding to each evaluation text, wherein the emotion evaluation unit set comprises at least one emotion evaluation unit;
calculating to obtain the evaluation score of the goods recorded by each evaluation text based on the emotion evaluation unit set of each evaluation text, and summarizing the evaluation score of each goods to obtain the evaluation value of each goods;
and selecting at least one item from the plurality of items according to the evaluation value of each item, and recommending the at least one item to a target user.
2. The item recommendation method according to claim 1, wherein the preset emotion dictionary comprises a basic emotion dictionary, a network word emotion dictionary and an expression picture emotion dictionary, the basic emotion dictionary comprises a plurality of positive emotion words, a plurality of negative emotion words, a plurality of positive evaluation words and a plurality of negative evaluation words, the network word emotion dictionary comprises a plurality of positive network words and a plurality of negative network words, the expression picture emotion dictionary comprises a plurality of expression pictures and emotion polarity words corresponding to the expression pictures, the preset evaluation object dictionary comprises a plurality of item names and a plurality of item part names, and the preset adverb dictionary comprises a plurality of adverbs for representing emotion polarity or emotion degree, the method further comprising:
and performing stop word elimination processing and part-of-speech tagging processing on each evaluation text.
3. The item recommendation method according to claim 1, wherein the extracting the emotion assessment words of each assessment text by using a preset emotion dictionary to obtain an emotion assessment word set corresponding to each assessment text comprises:
extracting emotion evaluation words of the evaluation text by using a preset emotion dictionary;
screening emotion evaluation words with the frequency of occurrence of the evaluation text larger than a preset frequency from the extracted emotion evaluation words;
and constructing an emotion evaluation word set corresponding to the evaluation text based on the emotion evaluation words obtained by screening.
4. The item recommendation method according to claim 1, wherein the plurality of rating texts comprise a first rating text, and the obtaining of the emotion evaluation unit set corresponding to each rating text based on a preset rating object dictionary, a preset adverb dictionary, and a sentence set and an emotion rating word set corresponding to each rating text comprises:
traversing sentences in a sentence set corresponding to the first evaluation text, and judging whether the sentences contain words in the preset evaluation object dictionary and words in an emotion evaluation word set corresponding to the first evaluation text;
when the sentence comprises a first word in the preset evaluation object dictionary and a second word in the emotion evaluation word set, constructing a binary evaluation unit based on the first word and the second word, and adding the binary evaluation unit to the emotion evaluation unit set corresponding to the first evaluation text;
judging whether the sentence contains words in the preset adverb dictionary;
when the sentence comprises a third word in the preset adverb dictionary and the word positions of the first word and the third word in the sentence meet preset requirements, constructing a ternary evaluation unit based on the first word, the second word and the third word, and replacing the binary evaluation unit in the emotion evaluation unit set with the ternary evaluation unit.
5. The item recommendation method of claim 4, further comprising:
and when the frequency of the binary evaluation units appearing in the emotion evaluation unit set is less than the preset frequency, deleting the binary evaluation units from the emotion evaluation unit set.
6. The item recommendation method according to claim 4, wherein the calculating of the evaluation score of the item described by each evaluation text based on the emotion evaluation unit set of each evaluation text comprises:
calculating the comment scores of the evaluation texts according to the number of the ternary evaluation units in the emotion evaluation unit set corresponding to the evaluation texts;
and calculating the evaluation score of the evaluation text for the recorded article based on the influence index and the comment score of the evaluation text, wherein the influence index of the evaluation text is obtained based on the number of fans of the user who issues the evaluation text, the forwarding number of the evaluation text and the number of comments.
7. The item recommendation method according to claim 6, wherein the evaluation value of each item is calculated by the following equation:
Rm＝J×K×P，
Em＝αX+βY+γZ，
wherein D isuIs the evaluation value of the item u, N is the total number of evaluation texts, RmFor the mth evaluation text, EmThe comment score of the mth evaluation text, J is the fan number of the user who issues the mth evaluation text, K is the forwarding number of the mth evaluation text, P is the comment number of the mth evaluation text, X is the comment score average value of the ternary evaluation unit contained in the mth evaluation text, and Y is the comment score average value of the ternary evaluation unit contained in the forwarding text which forwards the mth evaluation textThe value Z is the comment score average value of the ternary evaluation unit contained in the evaluation text of the mth comment text, H1The number of ternary evaluation units contained in the mth evaluation text, H2The number of ternary evaluation units, H, contained in the forwarded text for forwarding the mth evaluation text3The number of ternary evaluation units contained in the evaluation text for commenting the mth evaluation text, XiIs the comment score of the ith ternary evaluation unit contained in the mth evaluation text, YiThe comment score Z of the ith ternary evaluation unit contained in the forwarded text for forwarding the mth evaluation textiAlpha, beta and gamma are preset constants for the comment score of the ith ternary evaluation unit contained in the evaluation text for commenting the mth evaluation text.
8. The item recommendation method according to any one of claims 1 to 7, wherein said selecting at least one item from the plurality of items to recommend to a target user according to the evaluation value of each item comprises:
obtaining the evaluation grade of each article according to the evaluation value of each article;
recommending the articles at the preset evaluation level to the target user.
9. Computer arrangement comprising a processor and a memory, said memory having stored thereon a number of computer programs, characterized in that said processor is adapted to carry out the steps of the item recommendation method according to any one of claims 1-8 when executing the computer programs stored in the memory.
10. A computer-readable storage medium having stored thereon instructions executable by one or more processors to perform the steps of the item recommendation method of any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111165808.1A CN113886585A (en) | 2021-09-30 | 2021-09-30 | Item recommendation method, computer device and computer-readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111165808.1A CN113886585A (en) | 2021-09-30 | 2021-09-30 | Item recommendation method, computer device and computer-readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113886585A true CN113886585A (en) | 2022-01-04 |
Family
ID=79005216
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111165808.1A Pending CN113886585A (en) | 2021-09-30 | 2021-09-30 | Item recommendation method, computer device and computer-readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113886585A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114398911A (en) * | 2022-01-24 | 2022-04-26 | 平安科技（深圳）有限公司 | Emotion analysis method and device, computer equipment and storage medium |
-
2021
- 2021-09-30 CN CN202111165808.1A patent/CN113886585A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114398911A (en) * | 2022-01-24 | 2022-04-26 | 平安科技（深圳）有限公司 | Emotion analysis method and device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Alberto et al. | Tubespam: Comment spam filtering on youtube | |
| Jia et al. | Women are seen more than heard in online newspapers | |
| CN105224699B (en) | News recommendation method and device | |
| CN108885623B (en) | Semantic analysis system and method based on knowledge graph | |
| CN109145216A (en) | Network public-opinion monitoring method, device and storage medium | |
| US9015158B2 (en) | Contents creating device and contents creating method | |
| CN104573054A (en) | Information pushing method and equipment | |
| US20100306144A1 (en) | System and method for classifying information | |
| US20150324342A1 (en) | Method and apparatus for enriching social media to improve personalized user experience | |
| US9996529B2 (en) | Method and system for generating dynamic themes for social data | |
| CN105512300B (en) | information filtering method and system | |
| CN107104875B (en) | Information pushing method and device | |
| Cui et al. | Personalized microblog recommendation using sentimental features | |
| CN113886585A (en) | Item recommendation method, computer device and computer-readable storage medium | |
| US10339559B2 (en) | Associating social comments with individual assets used in a campaign | |
| Singh et al. | Mining the blogosphere from a socio-political perspective | |
| Saito et al. | Classifying user reviews at sentence and review levels utilizing Naïve Bayes | |
| KR101621735B1 (en) | Recommended search word providing method and system | |
| KR101568800B1 (en) | Real-time issue search word sorting method and system | |
| CN114223012A (en) | Push object determination method and device, terminal equipment and storage medium | |
| US20220292127A1 (en) | Information management system | |
| Rokade et al. | Business recommendation based on collaborative filtering and feature engineering–aproposed approach | |
| CN113821727A (en) | Item recommendation method, computer device and computer-readable storage medium | |
| CN114742573A (en) | Marketing analysis method and device, electronic equipment and storage medium | |
| CN110825847B (en) | Method and device for identifying intimacy between target people, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |