CN109101485B - Information processing method and device, electronic equipment and computer storage medium - Google Patents
Information processing method and device, electronic equipment and computer storage medium Download PDFInfo
- Publication number
- CN109101485B CN109101485B CN201810745000.2A CN201810745000A CN109101485B CN 109101485 B CN109101485 B CN 109101485B CN 201810745000 A CN201810745000 A CN 201810745000A CN 109101485 B CN109101485 B CN 109101485B
- Authority
- CN
- China
- Prior art keywords
- text
- synonym
- word
- synonym set
- information
- 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.)
- Active
Links
- 230000010365 information processing Effects 0.000 title claims abstract description 51
- 238000003672 processing method Methods 0.000 title claims abstract description 13
- 238000000034 method Methods 0.000 claims abstract description 26
- 239000013598 vector Substances 0.000 claims description 44
- 230000011218 segmentation Effects 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 8
- 238000010586 diagram Methods 0.000 description 4
- 230000001174 ascending effect Effects 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- 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
- G06F40/247—Thesauruses; Synonyms
-
- 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
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Probability & Statistics with Applications (AREA)
- Machine Translation (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention discloses an information processing method, an information processing device, electronic equipment and a computer storage medium, wherein the word frequency-inverse file frequency (TF-IDF) can be used for evaluating the importance degree of words to a certain file, and in the current method, each word is only used as an independent element, so that the accuracy of text classification and information retrieval by adopting the TF-IDF value obtained by the current method is lower. The embodiment of the invention obtains the synonym of each text word in the text message, obtains the first synonym set of the text word according to the text word and the synonym of the text word, further obtains the second synonym set of the text message based on the first synonym set, and finally obtains the TF-IDF value of the second synonym set through calculation. Due to the consideration of the synonym relation between the text words in the text information, the accuracy of text classification or information retrieval can be further improved based on the TF-IDF value.
Description
Technical Field
The present invention relates to the field of internet technologies, and in particular, to an information processing method and apparatus, an electronic device, and a computer storage medium.
Background
Term Frequency-Inverse Document Frequency (TF-IDF) is a weighting technique used for text classification and information retrieval, and TF-IDF can be used to evaluate the importance of words to a Document set or a Document in a corpus. The importance of a word increases in proportion to the number of times the word appears in the document, but at the same time decreases in inverse proportion to the frequency with which the word appears in the corpus.
In the current practice, each word is only taken as an independent element and the TF-IDF value is calculated, so that the accuracy of text classification and information retrieval by adopting the TF-IDF value obtained by the current practice is low.
Disclosure of Invention
The embodiment of the invention discloses an information processing method, an information processing device, electronic equipment and a computer storage medium, which can obtain TF-IDF values of a synonym set included in text information and are further favorable for improving the accuracy of text classification and information retrieval.
In a first aspect, an embodiment of the present invention discloses an information processing method, which may include: receiving an information processing request, wherein the information processing request comprises a plurality of text messages, and each text message comprises at least one text word; obtaining a first synonym set related to the text words according to the text words included in the text information, wherein the first synonym set includes the text words and at least one synonym of the text words; for each piece of text information, determining a first coefficient of the text information, wherein the first coefficient corresponds to a second synonym set containing text words in the text information, the first synonym set comprises the second synonym set, and the first coefficient is used for establishing a linear representation relationship between the second synonym set and the text information; and obtaining the word frequency-inverse file frequency of the second synonym set according to the first coefficient of the text information.
In one implementation, the information processing request further includes a target number of a target synonym set, and after obtaining the word frequency-inverse file frequency of the second synonym set according to the first coefficient of the text information, the method may further include: and determining a target synonym set which meets the target quantity and has a higher word frequency-inverse file frequency from the second synonym set.
In one implementation, the specific implementation manner of determining the first coefficient of the text information may be: acquiring the word frequency of each text word in the text information, wherein the word frequency of each text word is used for establishing a linear representation relationship between the text word and the text information; acquiring a second synonym set containing each text word; and aiming at each second synonym set, obtaining a first coefficient of the second synonym set according to a second coefficient of the second synonym set aiming at each text word and the word frequency of the text word.
In one implementation, before obtaining the first coefficient of the second synonym set according to the second coefficient of the second synonym set for each text word and the word frequency of the text word, the method may further include: determining a first vector of the text word for each text word in the text information; obtaining a second vector of a third synonym set containing the text word according to the first vector of the text word, wherein the second synonym set comprises the third synonym set; according to the first vector of the text word and the second vector of the third synonym set, cosine similarity between the text word and the third synonym set is obtained; and obtaining a second coefficient of the third synonym set for the text word according to the cosine similarity.
In an implementation manner, the information processing request further includes the number of all text messages, and the specific implementation manner of obtaining the word frequency-inverse file frequency of the second synonym set according to the first coefficient of the text message may be: summing all first coefficients of the text information to obtain a first numerical value; dividing a first coefficient corresponding to the second synonym set by the first numerical value to obtain a second numerical value; summing the first coefficients of the second synonym set for the text messages to obtain a third numerical value; performing logarithm operation on the result of dividing the number of all text messages included in the information processing request by the third numerical value to obtain a fourth numerical value; and multiplying the second numerical value and the fourth numerical value to obtain the word frequency-inverse file frequency of the second synonym set.
In an implementation manner, the specific implementation manner of obtaining the first synonym set related to the text word according to the text word included in the plurality of text messages may be: performing word segmentation processing on the text information to obtain a text word set, wherein the text word set comprises at least one text word; searching synonyms of the text words in a preset synonym database to obtain a fourth synonym set related to the text words, wherein the fourth synonym set comprises the text words and the found synonyms of the text words; and obtaining the first synonym set according to the fourth synonym set.
In an implementation manner, a specific implementation manner of obtaining the first synonym set according to the fourth synonym set may be: determining a target fourth synonym set in which a text word and all synonyms of the text word exist in other fourth synonym sets, wherein the other fourth synonym sets are fourth synonym sets except the target fourth synonym set in the fourth synonym set related to each text word; determining the other fourth set of synonyms as the first set of synonyms.
In a second aspect, an embodiment of the present invention discloses an information processing apparatus, which includes means for performing the method of the first aspect.
In a third aspect, an embodiment of the present invention discloses an electronic device, which includes a memory and a processor, where the memory is used for storing a computer program, the computer program includes program instructions, and the processor is configured to call the program instructions to execute the method according to the first aspect.
In a fourth aspect, an embodiment of the present invention discloses a computer storage medium storing a computer program, the computer program comprising program instructions that, when executed by a processor, cause the processor to perform the method of the first aspect.
By implementing the embodiment of the invention, the second synonym set and the first coefficient corresponding to each text message can be obtained, and the TF-IDF value of the second synonym set corresponding to the text message can be obtained based on the first coefficient.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of an information processing method according to an embodiment of the present invention;
FIG. 2 is a flow chart of another information processing method provided by the embodiment of the invention;
FIG. 3 is a schematic structural diagram of an information processing apparatus according to an embodiment of the present invention;
Fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. 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 invention.
The main principle of the technical scheme of the application can include: the method comprises the steps of obtaining synonyms of each text word in text information in the text information, obtaining a first synonym set of the text word according to the text word and the synonyms of the text word, further obtaining a second synonym set corresponding to the text information based on the first synonym set, and finally calculating TF-IDF values of the second synonym set.
Referring to fig. 1, fig. 1 is a schematic flowchart illustrating an information processing method according to an embodiment of the present invention. Specifically, as shown in fig. 1, the information processing method according to the embodiment of the present invention may include, but is not limited to, the following steps:
s101, the electronic equipment receives an information processing request, wherein the information processing request comprises a plurality of text messages.
Specifically, the electronic device may extract a plurality of text information included in the information processing request in a case where the information processing request is received. In one implementation, the signal processing request may be sent by the terminal device, or may be automatically generated by the electronic device upon detection of an information processing event. The information handling event may be triggered by a user clicking a confirmation handling button in an information handling interface displayed by the electronic device. The electronic device may be a terminal device or a server. The terminal device may be a smart phone, a tablet Computer, a Personal Computer (PC), a smart television, a smart watch, a vehicle-mounted device, a wearable device, a terminal device in the 5th Generation (5G) network, and the like.
The text information may be a sentence or a combination of sentences, or a paragraph or a chapter, which is not limited in the embodiments of the present invention. Each text message comprises at least one text word, and the text word can be an independent word in a word segmentation result obtained by calling a word segmentation algorithm to perform word segmentation on the text message. For example, when the text message is "happy and happy are synonyms", the text message includes one text word that may be any one of "happy", "and", "happy", "being", "synonyms". In one implementation, the text word may also be an individual word in a target word segmentation result obtained by calling a word segmentation algorithm to perform word segmentation processing on the text information and removing a stop word in the word segmentation result. For example, when the text message is "happy and happy are synonyms", one text word included in the text message may be any one of "happy", and "synonyms". The word segmentation algorithm may include, but is not limited to, a word segmentation algorithm based on string matching (such as a forward maximum matching method, a reverse maximum matching method, a minimum segmentation method, a bidirectional maximum matching method, and the like), a word segmentation algorithm based on understanding, and a word segmentation algorithm based on statistics, which is not limited in the embodiments of the present invention. Stop words refer to certain words or phrases that are automatically filtered out before or after processing natural language data (or text) in order to save storage space and improve search efficiency in information retrieval. In general, stop words can be divided into two categories: the first category is words which are widely used and even frequently used, such as the words "I", "just", etc. in the text; the second category is words with high frequency but low practical meaning in the text, including words such as "help", "adverb", "preposition", conjunctive words, etc.
S102, the electronic equipment obtains a first synonym set related to the text words according to the text words included in the text information.
Wherein the first set of synonyms includes the text word and at least one synonym of the text word. That is, the text word and all synonyms of the text word in the associated text message are present in the first set of synonyms. For example, when the text information is "happy and happy are synonyms", the text information includes a text word of "happy", the synonym of the text word "happy" in the text information is "happy", and the first synonym set about the text word "happy" may include { "happy", "happy" }.
In one implementation, the plurality of text messages may correspond to a plurality of first synonym sets, and each text word in the text messages corresponds to one first synonym set.
In one implementation, the first synonym sets corresponding to different text words in the same text information may be the same or different. In one implementation, the first synonym sets corresponding to the same text word in different text messages are the same, and the first synonym sets corresponding to different text words in different text messages may be the same or different. For example, when the number of text messages is 2, and the text message 1 and the text message 2 are: when "happy and happy are synonyms" and "happy and happy are synonyms", the two text messages may correspond to 2 first synonym sets, and the 2 first synonym sets are: { "happy", "happy" }, { "synonyms" }, at this time, the first synonym set corresponding to the text word "happy", "happy" in the text information 1 and the text word "happy" and "happy" in the text information 2 is { "happy", "happy" }.
In one implementation, the first set of synonyms for the text word may include the text word and all synonyms of the text word in the associated text information, and may also include text words in other text information. For example, the aforementioned first synonym set { "happy", "happy" } includes text words in the text information 1 and the text information 2. In one implementation, all words included in the first set of synonyms for the text word may be present in the text information to which the text word belongs. For example, when the number of text messages is 2, and the text message 1 and the text message 2 are: when "happy and happy are synonyms" and "today is monday", the two text messages may correspond to 4 first synonym sets, and the 4 first synonym sets are: { "happy", "happy" }, { "synonym" }, { "today" }, { "monday" }, at this time, the first synonym set of the text word "happy" in the text information 1 is: { "happy", "happy" }, and all words in the first synonym word set exist in the text information 1 to which the text word "happy" belongs.
In one implementation, the plurality of text messages may correspond to a first set of synonyms. For example, the first synonym set corresponding to the text information 1 and the text information 2 may be: { "happy", "synonym", "today", "monday" }.
S103, the electronic equipment determines a first coefficient of each text message, wherein the first coefficient corresponds to a second synonym set containing the text words in the text messages.
Wherein the first coefficient may be used to establish a linear representation relationship between the second set of synonyms and the text information, and the first set of synonyms may include the second set of synonyms.
In one implementation, each text word in each text message may correspond to one second synonym set, and the second synonym sets corresponding to different text words in each text message may be the same or different. For example, when the number of text messages is 2, and the text message 1 and the text message 2 are: when "happy and happy are synonyms" and "today is monday", the two text messages may correspond to 1 first set of synonyms, the first set of synonyms being: { "happy", "synonym", "today", "monday" }. The second synonym set corresponding to the text word "happy" and the text word "happy" in the text information 1 may be the same and is { "happy", "happy" }, and the second synonym set corresponding to the text word "synonym" in the text information 1 is { "synonym" }.
In one implementation, the textual information may be represented by a second set of synonyms. For example, the text information 1 may be represented by a second synonym set { "happy", "happy" }, { "synonym" }. Specifically, the second synonym set for representing the text message corresponds to a first coefficient, and a linear representation relationship between the second synonym set and the text message can be established through the first coefficient. For example, when the first coefficients corresponding to the second synonym set { "happy", "happy" }, { "synonym" } are s1 and s2, respectively, the linear representation relationship between the second synonym set and the text message may be: text information 1 ═ s1 { "happy", "happy" } + s2 { "synonym" }. In one implementation, the number of the second synonym sets corresponding to the text information is the same as the number of the first coefficients corresponding to the text information, so that a linear representation relationship between the second synonym sets and the text information is established through the first coefficients. In one implementation, each set of second synonyms for each text message may correspond to a first coefficient.
S104, the electronic equipment obtains the word frequency-inverse file frequency of the second synonym set according to the first coefficient of the text information.
Specifically, the electronic device may obtain the word frequency and the inverse text frequency index of the second synonym set according to the first coefficient of the text information, and further obtain the word frequency-inverse file frequency of the second synonym set based on the word frequency and the inverse text frequency index.
The word frequency of the second synonym set can be obtained according to all first coefficients corresponding to text information (the text information corresponds to the second synonym set). For example, the linear representation relationship between the second synonym set and the text message 1 is: the text information 1 ═ s1 { "happy", "happy" } + s2 { "synonym" }, the word frequency of the second synonym set can be obtained from s1 and s 2.
In one implementation, the second set of synonyms can correspond to one or more textual messages, that is, the second set of synonyms can be used to linearly represent one or more textual messages corresponding to the second set of synonyms. If the second synonym set corresponds to a plurality of text messages, the inverse text frequency index of the second synonym set can be obtained according to the corresponding first coefficient of the second synonym set in each corresponding text message. For example, if the second synonym set { "happy", "happy" } corresponds to text information 1 ("happy and happy are synonyms") and text information 2 ("happy and happy are synonyms"), and the linear representation relationship between the second synonym set and text information 1 is: the linear expression relationship between the text information 1 ═ s1 { "happy", "happy" } + s2 { "synonym" }, the second synonym set, and the text information 2 is: the text information 2 ═ s1 ' { "happy", "happy" } + s2 ' { "synonym" }, the inverse text frequency index of the second synonym set can be obtained from s1 and s1 '.
By implementing the embodiment of the invention, the second synonym set and the first coefficient corresponding to each text message can be obtained, and the TF-IDF value of the second synonym set corresponding to the text message can be obtained based on the first coefficient.
Referring to fig. 2, fig. 2 is a schematic flowchart illustrating another information processing method according to an embodiment of the present invention. Specifically, as shown in fig. 2, another information processing method according to an embodiment of the present invention may include, but is not limited to, the following steps:
s201, the electronic equipment receives an information processing request, and the information processing request comprises a plurality of text messages.
It should be noted that, the execution process of step S201 may refer to the specific description in step S101 in fig. 1, and is not described herein again.
S202, the electronic equipment performs word segmentation processing on the text information to obtain a text word set, wherein the text word set comprises at least one text word.
Specifically, the electronic device may perform word segmentation processing on a plurality of text messages to obtain a text word set. Wherein the text word in each text message is present in the text word set.
In an implementation manner, the electronic device may perform word segmentation processing on each piece of text information in parallel, and merge the obtained multiple word segmentation results to obtain the text word set.
S203, the electronic equipment searches synonyms of all the text words in a preset synonym database to obtain a fourth synonym set related to all the text words. Wherein the fourth synonym set includes the text word and the synonyms of the searched text word.
In one implementation, the electronic device may search for synonyms of each text word in a preset synonym database to obtain a fifth set of synonyms for each text word, where the fifth set of synonyms does not include the text word. Further, the electronic device may determine an intersection of the fifth synonym set and the foregoing text word set as a sixth synonym set, and then add the text word to the sixth synonym set to obtain a fourth synonym set. And all words in the fourth synonym set exist in the text information corresponding to the text word. For example, when the number of text messages is 2, and the text message 1 and the text message 2 are: when "happy and happy are synonyms" and "today is monday", the text word set corresponding to the two text messages may be: { "happy", "synonym", "today", "monday" }, if the synonym of the text word "happy" in the text information 1 found in the preset synonym database is: "happy" and "happy", the fifth set of synonyms for the text word "happy" is: { "happy", "happy" }, the sixth synonym set obtained by taking the intersection of the fifth synonym set and the text word set is: { "happy" }, adding the text word "happy" into a sixth synonym set, and obtaining a fourth synonym set as follows: { "happy", "happy" }.
In one implementation, the preset synonym database may be stored in the electronic device or on the cloud. In an implementation manner, the preset synonym database may also be stored in another electronic device, and the another electronic device may establish a connection with the electronic device in a wired or wireless manner, so that the electronic device may query the preset synonym database stored in the another electronic device.
In one implementation, the electronic device may also search synonyms of each text word over a network to obtain a fourth set of synonyms for each text word.
S204, the electronic equipment obtains a first synonym set according to the fourth synonym set.
In an implementation manner, a specific implementation manner of obtaining, by the electronic device, the first synonym set according to the fourth synonym set may be: the electronic device determines that the text word and all synonyms of the text word exist in a target fourth synonym set of other fourth synonym sets, and determines the other fourth synonym sets as the first synonym set. And the other fourth synonym sets are fourth synonym sets except the target fourth synonym set in the fourth synonym set related to each text word. For example, when the number of text messages is 2, and the text message 1 and the text message 2 are: when "happy and happy are synonyms" and "i am happy," the fourth synonym set corresponding to text message 1 may include: { "happy", "happy" }, { "synonym" }, a fourth synonym set corresponding to the text message 2 may include: { "i" }, { "very" }, { "happy" }, all words in a fourth synonym set { "happy" } corresponding to the text word "happy" in the text information 2 all exist in the fourth synonym set { "happy" } corresponding to the text word "happy" in the text information 1, at this time, the fourth synonym set { "happy" } corresponding to the text word "happy" in the text information 2 is a target fourth synonym set, and the fourth synonym set { "happy", "happy" } corresponding to the text information 1 is other fourth synonym sets.
In an implementation manner, a specific implementation manner of obtaining, by the electronic device, the first synonym set according to the fourth synonym set may further be that: the electronic equipment sorts the fourth synonym set according to the number of words in the fourth synonym set; circularly compressing the sorted fourth synonym set to obtain a first synonym set; wherein the compression process comprises: and if all words included in the first set exist in the second set, deleting the first set, determining the second set as a first synonym set, wherein the first set and the second set are two different fourth synonym sets.
In an implementation manner, the specific implementation manner of the electronic device sorting the fourth synonym set may be: the electronic device performs descending sorting on the fourth synonym set, or the electronic device performs ascending sorting on the fourth synonym set, which is not limited in the embodiment of the present invention.
S205, the electronic equipment obtains the word frequency of each text word in the text information. Wherein the word frequency of the text word is used for establishing a linear representation relationship between the text word and the text information.
In one implementation, the word frequency of a text word may be the number of times the text word appears in the belonging text information. In one implementation, the word frequency of a text word may be a value obtained by dividing the number of times the text word appears in the associated text message by the sum of the number of times all text words in the text message appear in the text message. In one implementation, the word frequency of a text word may be a value obtained by dividing the number of times the text word appears in the text information to which the text word belongs by the number of times a first text word appears in the text information, where the first text word may be the text word appearing in the text information the most frequently.
In one implementation, the word frequency of the text word and the text word may be used to establish a linear representation relationship between the text word and the text information. For example, when the word frequency of a text word is the number of times the text word appears in the text information to which the text word belongs, and the text information 1 is "happy and happy are synonyms, i.e., i is happy", the word frequency of the text word "happy" is 2, the word frequency of the text word "happy" is 1, the word frequency of the text word "synonym" is 1, and the word frequency of the text word "very" is 1. At this time, the linear representation relationship between the text word and the text information 1 may be: the text information 1 ═ happy "×" 2+ "happy" + "synonym" + "very".
S206, the electronic equipment acquires a second synonym set containing each text word. Wherein the first synonym set may include the second synonym set.
In one implementation, the electronic device may store a second synonym set corresponding to each text message, and a union of all the second synonym sets corresponding to each text message includes all the text words in the text message. For example, text message 1 (including m text words) corresponds to 3 second synonym sets (e.g., set 1, set 2, and set 3), and the union of set 1, set 2, and set 3 includes the m text words.
In one implementation, after the electronic device obtains the second synonym set including each text word, steps s2061-s2064 may be further performed:
s 2061: for each text word in the text information, a first vector of the text word is determined.
Wherein the first vector may be used to uniquely identify the text word. In one implementation, the first vector may be a word vector, which is used to turn words in natural language into dense vectors that can be understood by a computer. In one implementation, the word vector may be a one-hot vector. For example, assuming that the number of different text words is N, each text word may correspond to a consecutive integer from 0 to N-1, and if the corresponding integer of a text word is represented as i, in order to obtain a one-hot vector of the text word, a vector of all 0 s and N may be created and the ith bit thereof is set to 1. For example, when N is 3, the word vector for a text word may be: [1,0,0]. In an implementation manner, the word vector may also be obtained through a word2vec model or other models, which is not limited in the embodiment of the present invention. For example, a word vector for a text word may be: [0.5,0.3,0.2].
s 2062: and obtaining a second vector of a third synonym set containing the text word according to the first vector of the text word. Wherein the second synonym set includes the third synonym set.
In one implementation, the text word may correspond to one or more third sets of synonyms. If the text word corresponds to multiple third synonym sets, the text word exists in each third synonym set.
Wherein the second vector of the third set of synonyms can be used to uniquely identify the third set of synonyms. In one implementation, the second vector of the third synonym set may be an arithmetic average of the first vectors of all text words in the third synonym set. For example, if the third set of synonyms is { "happy", "happy" }, and the first vector of the text word "happy" is [0.5, 0.3, 0.2], and the first vector of the text word "happy" is [0.4, 0.1, 0.2], then the second vector of the third set of synonyms is: ([0.5,0.3,0.2]+[0.4,0.1,0.2])/2.
s 2063: and according to the first vector of the text word and the second vector of the third synonym set, obtaining the cosine similarity between the text word and the third synonym set.
In one implementation, the electronic device may determine a dot product of a first vector of a text word and a second vector of the third set of synonyms as a cosine similarity between the text word and the third set of synonyms.
s 2064: and obtaining a second coefficient of the third synonym set for the text word according to the cosine similarity.
In one implementation, the electronic device may determine a sum of cosine similarities between all third synonym sets corresponding to the text word and the text word, and divide the cosine similarities between the text word and the third synonym sets by the sum to obtain a second coefficient of the third synonym set for the text word. It should be noted that, when the text word corresponds to a plurality of third synonym sets, the sum of the second coefficients of all the third synonym sets for the text word is 1.
In one implementation, a linear representation relationship between the third set of synonyms and the text word may be established by the second coefficient and the third set of synonyms. For example, if the text word "happy" corresponds to two third synonym sets, where the third synonym set 1 is { "happy", "happy" }, the third synonym set 2 is { "happy", "happy" }, and the second coefficient of the third synonym set 1 for the text word is 0.4, and the second coefficient of the third synonym set 2 for the text word is 0.6, then the linear representation relationship between the third synonym set and the text word may be: the text word "happy" { "happy", "happy" } +0.6 { "happy", "happy" }.
S207, aiming at each second synonym set, the electronic equipment obtains a first coefficient of the second synonym set according to a second coefficient of the second synonym set aiming at each text word and the word frequency of the text word.
It is mentioned in step S205 that a linear representation relationship between a text word and the text message can be established by using the word frequency of the text word and the text word, and it is mentioned in step S2064 that a linear representation relationship between a third synonym set and the text word can be established by using the second coefficient and the third synonym set, it is understood that a linear representation relationship between the third synonym set and the text message can be established based on steps S205 and S2064, and further, a linear representation relationship between the second synonym set and the text message can be established.
For example, when the text information is "happy and happy are synonyms", and the third synonym set of the text word "happy" is { "happy", "happy" }, the third synonym set of the text word "synonym" is { "synonym" }, the text word "happy" may be represented by the third synonym set { "happy", "happy" } ", the text word" synonym "may be represented by the third synonym set {" happy "," happy "}", and since the text information may be represented by the text words "happy", the text information may be represented by the third synonym set { "happy" } "," }, at this time, { "happy", "happy" } and { "synonyms" } are determined as the second synonym set corresponding to the text information.
In one implementation, when the text words in the text information 1 are a text word 1 and a text word 2, the set of third synonyms corresponding to the text word 1 is set a (the second coefficient for the text word 1 is 0.4) and set b (the second coefficient for the text word 1 is 0.6), the set of third synonyms corresponding to the text word 2 is set b (the second coefficient for the text word 2 is 1), the word frequency of the text word 1 is 2, and the word frequency of the text word 2 is 1, the linear representation relationship between the text word and the text information 1 is: text information 1 ═ 2 text word 1+ text word 2. Substituting the linear expression relationship between the third synonym set and each text word into the above formula to obtain the linear expression relationship between the third synonym set and the text message 1 as follows: text message 1 ═ 2 × (0.4 × set a +0.6 × set b) + set b ═ 0.8 × set a +2.2 × set b. The set a is a third synonym set corresponding to the text word 1, and meanwhile, the set a is also a second synonym set aiming at the text message 1, and the set b is the same. Therefore, the first coefficient for the second synonym set (set a) of the text information 1 is 0.8, and the first coefficient for the second synonym set (set b) of the text information 1 is 2.2.
S208, the electronic equipment obtains the word frequency-inverse file frequency of the second synonym set according to the first coefficient of the text information.
In an implementation manner, when the electronic device performs the step of obtaining the word frequency-inverse document frequency of the second synonym set according to the first coefficient of the text information, steps s2081 to s2085 are specifically performed:
s 2081: and summing all the first coefficients of the text information to obtain a first numerical value.
Specifically, the electronic device may sum all first coefficients to obtain a first numerical value after obtaining first coefficients of all second synonym sets corresponding to the text information. For example, if the linear representation relationship between the second synonym set (set a and set b) and the text message 1 is: the text message 1 is 0.8 set a +2.2 set b, and the first value is 0.8+2.2 set 3.
s 2082: and dividing the first coefficient corresponding to the second synonym set by the first numerical value to obtain a second numerical value. Specifically, the number of the second numerical values corresponding to the text information is the same as the number of the second synonym sets corresponding to the text information, and the electronic device may calculate each of the second numerical values in parallel. For example, if the linear representation relationship between the second synonym set (set a and set b) and the text message 1 is: and if the text message 1 is 0.8 set a +2.2 set b, one second numerical value corresponding to the text message 1 is 0.8/3, and the other second numerical value corresponding to the text message 1 is 2.2/3.
s 2083: and summing the first coefficients of the second synonym set aiming at the text information to obtain a third numerical value. In an implementation manner, the same second synonym set may correspond to a plurality of pieces of text information, each piece of text information may be represented by the second synonym set in a linear manner, the second synonym set corresponds to each piece of text information, and the electronic device may sum the first coefficients of the second synonym set for each piece of text information to obtain a third numerical value. For example, the second synonym set (set a) corresponds to text message 1 and text message 2, and the linear representation relationship between text message 1 and the corresponding second synonym set (set a and set b) is: the linear representation relationship between the text message 1 and the corresponding second synonym set (set a and set c) is: text message 2 is 0.6 set a +1.3 set c, then the first coefficient for text message 1 in the second synonym set (set a) is 0.8, and the first coefficient for text message 2 in the second synonym set (set a) is 0.6, i.e. the third value is 0.8+0.6 is 1.4.
s 2084: and carrying out logarithm operation on the result of dividing the number of all text messages included in the information processing request by the third numerical value to obtain a fourth numerical value.
In one implementation, the information processing request may further include the number of all text messages. For example, if the number of all text messages is 2, and the third value is 1.4, the fourth value is lg (21.4).
s 2085: and multiplying the second numerical value and the fourth numerical value to obtain the word frequency-inverse file frequency of the second synonym set.
In one implementation, each text message may correspond to one or more second synonym sets, and when the text message corresponds to multiple second synonym sets, the electronic device may calculate the word frequency-inverse file frequency of each second synonym set in parallel. For example, if the second synonym set corresponding to the text message 1 is: and the set a and the set b, and the set a corresponds to a second value of 0.8/3 and a fourth value of lg (21.4), the set b corresponds to a second value of 2.2/3 and a fourth value of lg (21.3), so that the term frequency-inverse file frequency of the second synonym set (set a) is (0.83) × lg (21.4), and the term frequency-inverse file frequency of the second synonym set (set b) is (2.23) × lg (21.3).
S209, the electronic equipment determines a target synonym set which meets the target quantity and has a large word frequency-inverse file frequency from the second synonym set.
In an implementation manner, the information processing request may further include a target number of the target synonym set, where if the second synonym set corresponds to the text information 1, the target synonym set is the second synonym set with the highest degree of association with the text information 1.
In one implementation manner, the electronic device may first determine, as the target synonym set, a second synonym set with the largest word frequency-inverse file frequency in a plurality of second synonym sets corresponding to the text information, and then determine, as the target synonym set, a second synonym set with the largest word frequency-inverse file frequency in a plurality of second synonym sets other than the target synonym set until the target synonym sets with the target number are obtained.
In one implementation, the electronic device may select a target number of second synonym sets from the plurality of second synonym sets as the target synonym set in order of the word frequency-inverse file frequency of the second synonym sets from large to small. For example, if the target number is 1, the second synonym set corresponding to the text message 1 is: and the set a and the set b, wherein the word frequency-inverse file frequency of the set a is 0.4, and the word frequency-inverse file frequency of the set b is 0.8, so that the target synonym set of the text information 1 is the set b. It should be noted that the numerical values in the above examples are only for illustration and do not limit the embodiments of the present invention.
In an implementation manner, the electronic device may further receive an information retrieval request from the terminal device, where the information retrieval request includes a retrieval word, the electronic device may obtain a synonym set of the retrieval word, obtain each second synonym set that is the same as a word included in the synonym set, obtain a word frequency-inverse file frequency of each second synonym set in corresponding text information, and then send the text information corresponding to the second synonym set with the maximum word frequency-inverse file frequency to the terminal device. Or, the electronic device may further send text information corresponding to a preset number of second synonym sets with a higher word frequency-inverse file frequency to the terminal device. The preset number may be set by the electronic device as a default, or may be sent to the electronic device by the terminal device, which is not limited in the embodiment of the present invention.
By implementing the embodiment of the invention, the second synonym set and the first coefficient corresponding to each text message can be obtained, and the TF-IDF value of the second synonym set corresponding to the text message can be obtained based on the first coefficient.
Referring to fig. 3, fig. 3 is a schematic structural diagram of an information processing apparatus according to an embodiment of the present invention, specifically, as shown in fig. 3, the information processing apparatus 30 may include:
a receiving unit 301, configured to receive an information processing request, where the information processing request includes a plurality of text messages, and each text message includes at least one text word.
The processing unit 302 is configured to obtain a first synonym set for a text word according to the text word included in the plurality of text messages, where the first synonym set includes the text word and at least one synonym of the text word.
The processing unit 302 is further configured to determine, for each piece of text information, a first coefficient of the piece of text information, where the first coefficient corresponds to a second synonym set including text words in the piece of text information, and the first coefficient is used to establish a linear representation relationship between the second synonym set and the piece of text information.
The processing unit 302 is further configured to obtain a word frequency-inverse file frequency of the second synonym set according to the first coefficient of the text message.
In an implementation, the information processing request may further include a target number of the target synonym sets, and the processing unit 302 may be further configured to determine, from the second synonym set, a target synonym set that satisfies the target number and has a higher word frequency-inverse file frequency.
In one implementation, the processing unit 302 is specifically configured to: acquiring the word frequency of each text word in the text information, wherein the word frequency of the text word is used for establishing a linear expression relation between the text word and the text information; acquiring a second synonym set containing each text word; and aiming at each second synonym set, obtaining a first coefficient of the second synonym set according to a second coefficient of the second synonym set aiming at each text word and the word frequency of the text word.
In one implementation, the processing unit 302 may be further configured to determine, for each text word in the text information, a first vector of the text word; obtaining a second vector of a third synonym set containing the text words according to the first vector of the text words, wherein the second synonym set comprises the third synonym set; according to the first vector of the text word and the second vector of the third synonym set, cosine similarity between the text word and the third synonym set is obtained; and obtaining a second coefficient of the third synonym set aiming at the text word according to the cosine similarity.
In an implementation manner, the information processing request may further include the number of all text messages, and the processing unit 302 is specifically configured to: summing all first coefficients of the text information to obtain a first numerical value; dividing a first coefficient corresponding to the second synonym set by the first numerical value to obtain a second numerical value; summing the first coefficients of the second synonym set aiming at all the text messages to obtain a third numerical value; performing logarithm operation on the result of dividing the number of all text messages included in the information processing request by the third numerical value to obtain a fourth numerical value; and multiplying the second numerical value and the fourth numerical value to obtain the word frequency-inverse file frequency of the second synonym set.
In one implementation, the processing unit 302 is specifically configured to: performing word segmentation processing on the plurality of text messages to obtain a text word set, wherein the text word set comprises at least one text word; searching synonyms of all the text words in a preset synonym database to obtain a fourth synonym set related to all the text words, wherein the fourth synonym set comprises the text words and the found synonyms of the text words; and obtaining a first synonym set according to the fourth synonym set.
In one implementation, the processing unit 302 is specifically configured to: determining a target fourth synonym set in which the text word and all synonyms of the text word exist in other fourth synonym sets, wherein the other fourth synonym sets are fourth synonym sets except the target fourth synonym set in the fourth synonym set related to each text word; the other fourth set of synonyms is determined as the first set of synonyms.
The embodiment of the present invention and the method embodiments shown in fig. 1 and fig. 2 are based on the same concept, and the technical effects thereof are also the same, and for the specific principle, reference is made to the description of the embodiments shown in fig. 1 and fig. 2, which is not repeated herein.
Referring to fig. 4, fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present invention. The electronic device 40 may comprise a receiver 401, a memory 402 and a processor 403, the receiver 401, the memory 402 and the processor 403 being connected by one or more communication buses.
The receiver 401 may be used to receive data, for example, the receiver 401 may be used to receive an information processing request.
The Processor 403 may be a Central Processing Unit (CPU), and the Processor 403 may also be 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, and optionally, the processor 403 may be any conventional processor or the like. Wherein:
a memory 402 for storing program instructions.
A processor 403 for calling the program instructions stored in the memory 402 for:
receiving an information processing request, wherein the information processing request comprises a plurality of text messages, and each text message comprises at least one text word;
Obtaining a first synonym set related to a text word according to the text word included in a plurality of text messages, wherein the first synonym set includes the text word and at least one synonym of the text word;
aiming at each piece of text information, determining a first coefficient of the text information, wherein the first coefficient corresponds to a second synonym set containing text words in the text information, the first synonym set comprises the second synonym set, and the first coefficient is used for establishing a linear representation relation between the second synonym set and the text information;
and obtaining the word frequency-inverse file frequency of the second synonym set according to the first coefficient of the text information.
In one implementation, the information processing request may further include a target number of the target synonym sets, and the processor 403 may be further configured to determine, from the second synonym set, a target synonym set that satisfies the target number and has a higher word frequency-inverse file frequency.
In an implementation manner, the processor 403 is configured to, when determining the first coefficient of the text information, specifically, obtain a word frequency of each text word in the text information, where the word frequency of the text word is used to establish a linear representation relationship between the text word and the text information; acquiring a second synonym set containing each text word; and aiming at each second synonym set, obtaining a first coefficient of the second synonym set according to a second coefficient of the second synonym set aiming at each text word and the word frequency of the text word.
In one implementation, the processor 403 may be further configured to determine, for each text word in the text information, a first vector of text words; obtaining a second vector of a third synonym set containing the text words according to the first vector of the text words, wherein the second synonym set comprises the third synonym set; according to the first vector of the text word and the second vector of the third synonym set, cosine similarity between the text word and the third synonym set is obtained; and obtaining a second coefficient of the third synonym set aiming at the text word according to the cosine similarity.
In an implementation manner, the information processing request may further include the number of all text messages, and the processor 403 is configured to, when obtaining the word frequency-inverse file frequency of the second synonym set according to the first coefficient of the text message, specifically sum up all the first coefficients of the text message to obtain a first numerical value; dividing a first coefficient corresponding to the second synonym set by the first numerical value to obtain a second numerical value; summing the first coefficients of the second synonym set aiming at all the text messages to obtain a third numerical value; performing logarithm operation on the result of dividing the number of all text messages included in the information processing request by the third numerical value to obtain a fourth numerical value; and multiplying the second numerical value and the fourth numerical value to obtain the word frequency-inverse file frequency of the second synonym set.
In one implementation, the processor 403 is configured to, when obtaining a first synonym set related to a text word according to the text word included in the plurality of pieces of text information, specifically, perform word segmentation processing on the plurality of pieces of text information to obtain a text word set, where the text word set includes at least one text word; searching synonyms of all the text words in a preset synonym database to obtain a fourth synonym set related to all the text words, wherein the fourth synonym set comprises the text words and the found synonyms of the text words; and obtaining a first synonym set according to the fourth synonym set.
In an implementation manner, the processor 403 is configured to, when obtaining the first synonym set according to the fourth synonym set, specifically determine that the text word and all synonyms of the text word exist in a target fourth synonym set in other fourth synonym sets, where the other fourth synonym sets are fourth synonym sets other than the target fourth synonym set in the fourth synonym set for each text word; the other fourth set of synonyms is determined as the first set of synonyms.
It should be noted that, for details that are not mentioned in the embodiment corresponding to fig. 4 and the specific implementation manner of each step, reference may be made to the embodiments shown in fig. 1 to fig. 3 and the foregoing description, and details are not repeated here.
Embodiments of the present invention also provide a computer-readable storage medium, in which a computer program is stored, where the computer program includes program instructions, and the program instructions, when executed by a processor, cause the processor to execute the steps executed in the method embodiments shown in fig. 1-2.
While the invention has been described with reference to a number of embodiments, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (9)
1. An information processing method characterized by comprising:
receiving an information processing request, wherein the information processing request comprises a plurality of text messages, and each text message comprises at least one text word;
obtaining a first synonym set related to the text words according to the text words included in the text information, wherein the first synonym set includes the text words and at least one synonym of the text words;
for each piece of text information, determining a first coefficient of the text information, wherein the first coefficient corresponds to a second synonym set containing text words in the text information, the first synonym set comprises the second synonym set, and the first coefficient is used for establishing a linear representation relationship between the second synonym set and the text information;
Obtaining the word frequency-inverse file frequency of the second synonym set according to the first coefficient of the text information;
wherein the determining a first coefficient of the text information comprises:
acquiring the word frequency of each text word in the text information, wherein the word frequency of each text word is used for establishing a linear representation relationship between the text word and the text information;
acquiring a second synonym set containing each text word;
for each second synonym set, obtaining a first coefficient of the second synonym set according to a second coefficient of the second synonym set for each text word and the word frequency of the text word; wherein the second coefficient of one text word is used to establish a linear representation relationship between a third synonym set and the one text word, and the second synonym set includes the third synonym set.
2. The method of claim 1, wherein the information processing request further comprises a target number N of target synonym sets, and wherein after obtaining a word frequency-inverse file frequency of the second synonym set according to a first coefficient of the text information, the method further comprises:
And selecting the first N second synonym sets with the maximum word frequency-inverse file frequency from the second synonym sets as target synonym sets.
3. The method of claim 1, wherein before obtaining the first coefficients of the second set of synonyms based on the second coefficients of the second set of synonyms for each of the text words and the word frequency of the text word, the method further comprises:
determining a first vector of the text word for each text word in the text information;
obtaining a second vector of a third synonym set containing the text word according to the first vector of the text word;
according to the first vector of the text word and the second vector of the third synonym set, cosine similarity between the text word and the third synonym set is obtained;
and obtaining a second coefficient of the third synonym set for the text word according to the cosine similarity.
4. The method according to any one of claims 1 to 3, wherein the information processing request further includes a quantity of all text messages, and the obtaining the word frequency-inverse file frequency of the second synonym set according to the first coefficient of the text messages comprises:
Summing all first coefficients of the text information to obtain a first numerical value;
dividing a first coefficient corresponding to the second synonym set by the first numerical value to obtain a second numerical value;
summing the first coefficients of the second synonym set for the text messages to obtain a third numerical value;
performing logarithm operation on the result of dividing the number of all text messages included in the information processing request by the third numerical value to obtain a fourth numerical value;
and multiplying the second numerical value and the fourth numerical value to obtain the word frequency-inverse file frequency of the second synonym set.
5. The method according to any one of claims 1 to 3, wherein the obtaining a first synonym set about a text word included in the plurality of text messages according to the text word comprises:
performing word segmentation processing on the text information to obtain a text word set, wherein the text word set comprises at least one text word;
searching synonyms of the text words in a preset synonym database to obtain a fourth synonym set related to the text words, wherein the fourth synonym set comprises the text words and the found synonyms of the text words;
And obtaining the first synonym set according to the fourth synonym set.
6. The method of claim 5, wherein obtaining the first set of synonyms from the fourth set of synonyms comprises:
determining a target fourth synonym set in which a text word and all synonyms of the text word exist in other fourth synonym sets, wherein the other fourth synonym sets are fourth synonym sets except the target fourth synonym set in the fourth synonym set related to each text word;
determining the other fourth set of synonyms as the first set of synonyms.
7. An information processing apparatus characterized in that the apparatus comprises means for performing the method according to any one of claims 1 to 6.
8. An electronic device comprising a memory for storing a computer program comprising program instructions and a processor configured to invoke the program instructions to perform the method of any of claims 1 to 6.
9. A computer storage medium, characterized in that the computer storage medium stores a computer program comprising program instructions that, when executed by a processor, cause the processor to perform the method according to any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810745000.2A CN109101485B (en) | 2018-07-09 | 2018-07-09 | Information processing method and device, electronic equipment and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810745000.2A CN109101485B (en) | 2018-07-09 | 2018-07-09 | Information processing method and device, electronic equipment and computer storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109101485A CN109101485A (en) | 2018-12-28 |
| CN109101485B true CN109101485B (en) | 2022-07-29 |
Family
ID=64845870
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810745000.2A Active CN109101485B (en) | 2018-07-09 | 2018-07-09 | Information processing method and device, electronic equipment and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109101485B (en) |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104298715B (en) * | 2014-09-16 | 2017-12-19 | 北京航空航天大学 | A kind of more indexed results ordering by merging methods based on TF IDF |
| CN104778276A (en) * | 2015-04-29 | 2015-07-15 | 北京航空航天大学 | Multi-index combining and sequencing algorithm based on improved TF-IDF (term frequency-inverse document frequency) |
| CN106502990A (en) * | 2016-10-27 | 2017-03-15 | 广东工业大学 | A kind of microblogging Attribute selection method and improvement TF IDF method for normalizing |
| CN108132930A (en) * | 2017-12-27 | 2018-06-08 | 曙光信息产业(北京)有限公司 | Feature Words extracting method and device |
-
2018
- 2018-07-09 CN CN201810745000.2A patent/CN109101485B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109101485A (en) | 2018-12-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111797210A (en) | Information recommendation method, device and equipment based on user portrait and storage medium | |
| CN107911448B (en) | Content pushing method and device | |
| CN107885717B (en) | Keyword extraction method and device | |
| CN109388743B (en) | Language model determining method and device | |
| CN112100396B (en) | Data processing method and device | |
| WO2019028990A1 (en) | Code element naming method, device, electronic equipment and medium | |
| CN110210038B (en) | Core entity determining method, system, server and computer readable medium thereof | |
| CN111209372B (en) | Keyword determination method and device, electronic equipment and storage medium | |
| WO2018058118A1 (en) | Method, apparatus and client of processing information recommendation | |
| CN110209781B (en) | Text processing method and device and related equipment | |
| CN112784063A (en) | Idiom knowledge graph construction method and device | |
| CN111435406A (en) | Method and device for correcting database statement spelling errors | |
| CN112732898A (en) | Document abstract generation method and device, computer equipment and storage medium | |
| CN108875050B (en) | Text-oriented digital evidence-obtaining analysis method and device and computer readable medium | |
| CN108628875B (en) | Text label extraction method and device and server | |
| CN113806660A (en) | Data evaluation method, training method, device, electronic device and storage medium | |
| CN110738048B (en) | Keyword extraction method and device and terminal equipment | |
| CN109101485B (en) | Information processing method and device, electronic equipment and computer storage medium | |
| CN111737571B (en) | Searching method and device and electronic equipment | |
| CN109033070B (en) | Data processing method, server and computer readable medium | |
| CN116610782B (en) | Text retrieval method, device, electronic equipment and medium | |
| CN112307312A (en) | Article recommendation method and device | |
| CN113377921B (en) | Method, device, electronic equipment and medium for matching information | |
| CN111930954B (en) | Intention recognition method and device, storage medium and electronic equipment | |
| CN113656393B (en) | Data processing method, device, 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20231213 Address after: 430070 Hubei Province, Wuhan city Hongshan District Luoyu Road No. 546 Patentee after: HUBEI CENTRAL CHINA TECHNOLOGY DEVELOPMENT OF ELECTRIC POWER Co.,Ltd. Address before: 400000 Floor 9, building 11, Internet Industrial Park, No. 106, west section of Jinkai Avenue, Yubei District, Chongqing Patentee before: CHONGQING XIEZHI TECHNOLOGY Co.,Ltd. |