CN116383343A - Text mining method, device, equipment and storage medium - Google Patents
Text mining method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN116383343A CN116383343A CN202310416583.5A CN202310416583A CN116383343A CN 116383343 A CN116383343 A CN 116383343A CN 202310416583 A CN202310416583 A CN 202310416583A CN 116383343 A CN116383343 A CN 116383343A
- Authority
- CN
- China
- Prior art keywords
- vocabulary
- mining
- text
- search
- template
- 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
- 238000005065 mining Methods 0.000 title claims abstract description 231
- 238000000034 method Methods 0.000 title claims abstract description 43
- 230000001960 triggered effect Effects 0.000 claims abstract description 31
- 238000000605 extraction Methods 0.000 claims description 32
- 238000012545 processing Methods 0.000 claims description 28
- 238000009412 basement excavation Methods 0.000 claims description 13
- 238000012216 screening Methods 0.000 claims description 10
- 238000004458 analytical method Methods 0.000 claims description 8
- 238000004378 air conditioning Methods 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 abstract description 12
- 238000013473 artificial intelligence Methods 0.000 abstract description 8
- 230000006870 function Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 230000004044 response Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 238000001514 detection method Methods 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000699 topical effect Effects 0.000 description 1
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
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- 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
- G06F16/338—Presentation of query results
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to artificial intelligence and provides a text mining method, device, equipment and storage medium. When the method monitors that the mining template is successfully triggered in the operation interface, generating a target vocabulary according to the positive input vocabulary, identifying a mining relation according to the input position of the target vocabulary in the operation interface, generating a search sentence according to the template vocabulary, the negative input vocabulary, the mining relation and the inter-word distance of the target vocabulary, calling a search thread to execute the search sentence according to the text quantity of the template type in a preset micro-service architecture, and further generating a mining detail interface. In addition, the invention also relates to a blockchain technology, and the mining detail interface can be stored in the blockchain.
Description
Technical Field
The present invention relates to the field of artificial intelligence technologies, and in particular, to a text mining method, apparatus, device, and storage medium.
Background
In the current big data age, industries such as finance accumulate massive amounts of data, including structured text and unstructured text. As the ways in which businesses interact with customers increase, much of the valuable information is hidden in these vast amounts of interaction data, and thus, the need for text mining by businesses increases.
Related text mining schemes exist in the field of artificial intelligence, however, in these schemes, valuable text information cannot be efficiently and accurately mined from massive information due to the lack of structured tags (e.g., customer tags, agent portraits, business information, etc.) to assist in locking the mining scope.
Disclosure of Invention
In view of the foregoing, it is necessary to provide a text mining method, apparatus, device, and storage medium, which can solve the technical problem that valuable text information cannot be efficiently and accurately mined from mass information.
In one aspect, the present invention provides a text mining method, including:
when a text mining request is received, displaying a mining template in an operation interface according to the text mining request;
when the mining template is monitored to be successfully triggered in the operation interface, generating a target word according to a forward input word in the operation interface, wherein the target word comprises the forward input word and a key word in an associated word corresponding to the forward input word;
identifying an excavation relation according to the input position of the target vocabulary in the operation interface;
Generating search sentences according to template words in the mining template, negative input words in the operation interface, the mining relation and inter-word distances of the target words;
according to the text quantity of the template type corresponding to the mining template in a preset micro-service architecture, a search thread in a preset search engine is called to execute the search sentence, and a search text is obtained;
and generating a mining detail interface according to the text quantity and the search text.
According to a preferred embodiment of the present invention, before generating the target vocabulary according to the forward input vocabulary in the operation interface, the text mining method further includes:
identifying the initial display time of the excavation template on the operation interface;
acquiring an operation log of the operation interface based on the initial display time;
identifying a button position of an associated button associated with the mining template from the operation interface, and identifying a frame position of a text frame in the operation interface;
detecting whether the operation log includes the button position and the frame position;
and if the operation log comprises the button position and/or the frame position, determining that the mining template is successfully triggered in the operation interface.
According to a preferred embodiment of the present invention, the frame positions include a positive position and a negative position, and the generating the target vocabulary according to the positive input vocabulary in the operation interface includes:
acquiring the forward input vocabulary from the forward position;
generating an associated vocabulary corresponding to the forward input vocabulary based on a pre-trained paraphrasing prediction model;
detecting whether the associated vocabulary is successfully triggered;
determining the association vocabulary successfully triggered as the key vocabulary;
generating the frame position of the target vocabulary according to the positive input vocabulary and the key vocabulary comprises a positive position and a negative position, and generating the target vocabulary according to the positive input vocabulary in the operation interface comprises:
acquiring the forward input vocabulary from the forward position;
generating an associated vocabulary corresponding to the forward input vocabulary based on a pre-trained paraphrasing prediction model;
detecting whether the associated vocabulary is successfully triggered;
determining the association vocabulary successfully triggered as the key vocabulary;
and generating the target vocabulary according to the forward input vocabulary and the key vocabulary.
According to a preferred embodiment of the present invention, the paraphrasing prediction model includes a semantic analysis network and a prediction output network, the semantic analysis network includes a forward feature extraction network and a reverse feature extraction network, and generating the associated vocabulary corresponding to the forward input vocabulary based on the pre-trained paraphrasing prediction model includes:
Encoding the forward input vocabulary to obtain an input vector;
performing feature extraction on the input vector based on the forward feature extraction network to obtain a first feature;
performing feature extraction on the input vector based on the reverse feature extraction network to obtain a second feature;
generating a semantic vector of the forward input vocabulary according to the first feature and the second feature;
based on the semantic vector, corresponding vocabulary is obtained from the prediction output network to be used as the associated vocabulary.
According to a preferred embodiment of the present invention, the generating the search sentence according to the template vocabulary in the mining template, the negative input vocabulary in the operation interface, the mining relation, and the inter-word distance of the target vocabulary includes:
recognizing the vocabulary types of the template vocabularies in the mining template, and recognizing the vocabulary relations of the template vocabularies in the mining template;
generating a negative search vocabulary by using the template vocabulary with the vocabulary type of the negative type and the negative input vocabulary;
generating a forward search vocabulary by using the template vocabulary with the vocabulary type being the forward type and the target vocabulary;
And writing the vocabulary relation, the negative search vocabulary, the positive search vocabulary, the mining relation and the inter-word distance into a preset query sentence to obtain the search sentence.
According to a preferred embodiment of the present invention, the generating a mining detail interface according to the text quantity and the search text includes:
counting the searching quantity of the searching text;
generating a search ratio according to the ratio of the search quantity to the text quantity;
counting the occurrence frequency of each forward search word in the search text;
calculating the matching degree of the search text and the search sentence according to the frequency;
screening target texts from a plurality of search texts according to the matching degree;
and writing the text quantity, the search ratio, the frequency and the target text into a preset interface to obtain the mining detail interface.
According to a preferred embodiment of the present invention, the calling a search thread in a preset search engine to execute the search sentence according to the text quantity of the template type corresponding to the mining template in the preset micro service architecture, and obtaining the search text includes:
quantizing public opinion texts stored in the preset micro-service architecture based on the template type to obtain the text quantity;
Acquiring the processing rate of an idle thread from the preset search engine;
extracting mining duration requirements from the text mining request;
determining the processing rate with the minimum value as a target rate;
calculating the number of threads according to the number of texts, the mining duration requirement and the target rate;
screening the search thread from a plurality of idle threads according to the thread number and the processing rate;
and calling the search thread, comparing the search sentence with the public opinion text, and determining the public opinion text successfully matched with the search sentence as the search text.
On the other hand, the invention also provides a text mining device, which comprises:
the display unit is used for displaying the mining template in the operation interface according to the text mining request when the text mining request is received;
the generating unit is used for generating a target vocabulary according to forward input vocabulary in the operation interface when the mining template is monitored to be successfully triggered in the operation interface, wherein the target vocabulary comprises the forward input vocabulary and key vocabulary in associated vocabulary corresponding to the forward input vocabulary;
The identification unit is used for identifying the mining relation according to the input position of the target vocabulary in the operation interface;
the generating unit is further used for generating search sentences according to template words in the mining template, negative input words in the operation interface, the mining relation and inter-word distances of the target words;
the execution unit is used for calling a search thread in a preset search engine to execute the search sentence according to the text quantity of the template type corresponding to the mining template in the preset micro-service architecture to obtain a search text;
the generating unit is further used for generating a mining detail interface according to the text quantity and the search text.
In another aspect, the present invention also proposes an electronic device, including:
a memory storing computer readable instructions; a kind of electronic device with high-pressure air-conditioning system
And a processor executing computer readable instructions stored in the memory to implement the text mining method.
In another aspect, the present invention also proposes a computer readable storage medium having stored therein computer readable instructions that are executed by a processor in an electronic device to implement the text mining method.
According to the technical scheme, the mining template corresponding to the text mining request is identified, and the user does not need to repeatedly input template content in the mining template in the operation interface, so that the search sentence can be generated rapidly, the generation efficiency of the search text is improved, when the mining template is monitored to be triggered, the mining template is required to be further improved, further the associated vocabulary which is input by an auxiliary user can be generated through the positive input vocabulary, the generation efficiency of the target vocabulary is improved, meanwhile, the locking of the mining range can be assisted on the premise that the user lacks a structured label, and further search sentences can be generated accurately by combining the template vocabulary, the negative input vocabulary, the mining relation and the inter-word distance, so that the generation accuracy of the search text is improved, the search thread can be reasonably called to process the search sentence through the text quantity, and the rapid processing of the search text can be realized on the premise that other request processing is not influenced. In addition, the mining detail interface is generated through the text quantity and the search text, so that a user can be assisted to quickly know the response condition of the text mining request.
Drawings
FIG. 1 is a flow chart of a preferred embodiment of the text mining method of the present invention.
Fig. 2 is a model structure diagram of a paraphrasing predictive model in the text mining method of the present invention.
Fig. 3 is a functional block diagram of a preferred embodiment of the text-mining apparatus of the present invention.
Fig. 4 is a schematic structural diagram of an electronic device implementing a preferred embodiment of the text mining method of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in detail with reference to the accompanying drawings and specific embodiments.
As shown in FIG. 1, a flow chart of a preferred embodiment of the text mining method of the present invention is shown. The order of the steps in the flowchart may be changed and some steps may be omitted according to various needs.
The text mining method can acquire and process related data based on artificial intelligence technology. Among these, artificial intelligence (Artificial Intelligence, AI) is the theory, method, technique and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend and extend human intelligence, sense the environment, acquire knowledge and use knowledge to obtain optimal results.
Artificial intelligence infrastructure technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and other directions.
The text mining method is applied to one or more electronic devices, wherein the electronic devices are devices capable of automatically performing numerical calculation and/or information processing according to preset or stored computer readable instructions, and the hardware of the electronic devices comprises, but is not limited to, microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASICs), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital signal processors (Digital Signal Processor, DSP), embedded devices and the like.
The electronic device may be any electronic product that can interact with a user in a human-computer manner, such as a personal computer, tablet computer, smart phone, personal digital assistant (Personal Digital Assistant, PDA), game console, interactive internet protocol television (Internet Protocol Television, IPTV), smart wearable device, etc.
The electronic device may comprise a network device and/or a user device. Wherein the network device includes, but is not limited to, a single network electronic device, a group of electronic devices made up of multiple network electronic devices, or a Cloud based Cloud Computing (Cloud Computing) made up of a large number of hosts or network electronic devices.
The network in which the electronic device is located includes, but is not limited to: the internet, wide area networks, metropolitan area networks, local area networks, virtual private networks (Virtual Private Network, VPN), etc.
101, when a text mining request is received, displaying a mining template in an operation interface according to the text mining request.
In at least one embodiment of the present invention, the text-mining request is a request generated in response to a user triggering a mining requirements button on the operating interface.
The operation interface is an interface which can be operated by a user in the electronic equipment.
The mining template refers to a template matched with the scene type corresponding to the request scene.
In at least one embodiment of the present invention, the electronic device displaying the mining template in the operation interface according to the text mining request includes:
analyzing a request message of the text mining request to obtain data information carried by the request message;
extracting a request scene from the data information;
identifying a scene type corresponding to the request scene as a template type;
acquiring a template corresponding to the template type from a preset template library as the mining template;
Locating a triggering interface of the file mining request as the operation interface according to the generated log of the file mining request;
and displaying the excavation template based on the operation interface.
Wherein, the data information comprises the request scene, the mining duration requirement and the like. The request scenario includes, but is not limited to: complaints pursue, topical studies, etc.
And the preset template library stores mapping relations between a plurality of template types and templates.
And generating a log refers to triggering the log file generated by the text mining request.
The trigger interface is an interface where the excavation requirement button is located.
The request scene can be rapidly acquired through the request message, the mining template can be accurately acquired based on the request scene, and the operation interface can be accurately positioned through the generated log.
102, when the mining template is monitored to be successfully triggered in the operation interface, generating a target word according to a forward input word in the operation interface, wherein the target word comprises the forward input word and a key word in an associated word corresponding to the forward input word.
In at least one embodiment of the present invention, the forward input vocabulary refers to a vocabulary input by the user at a forward position in the operation interface. The forward input vocabulary refers to the vocabulary that must be included in the search text.
The associated vocabulary refers to the near meaning words of the forward input vocabulary.
The key words refer to associated words successfully triggered by the user.
In at least one embodiment of the present invention, before generating the target vocabulary according to the forward input vocabulary in the operation interface, the text mining method further includes:
identifying the initial display time of the excavation template on the operation interface;
acquiring an operation log of the operation interface based on the initial display time;
identifying a button position of an associated button associated with the mining template from the operation interface, and identifying a frame position of a text frame in the operation interface;
detecting whether the operation log includes the button position and the frame position;
and if the operation log comprises the button position and/or the frame position, determining that the mining template is successfully triggered in the operation interface.
The initial display time refers to the initial time of displaying the excavation template on the operation interface.
The operation log is a log corresponding to the operation interface, and the log generation time is greater than the day of the initial display time.
The association button may be: a push-to-apply button, etc.
The operation log can be accurately obtained through the initial display time and the operation interface, and whether the excavation template is successfully triggered in the operation interface can be accurately identified through identifying whether the operation log comprises the button position and the frame position.
In other embodiments, if the button location and the frame location are not included in the operation log, it is determined that the mining template was not successfully triggered in the operation interface.
In at least one embodiment of the present invention, the frame positions include a positive position and a negative position, and the generating, by the electronic device, the target vocabulary according to the positive input vocabulary in the operation interface includes:
acquiring the forward input vocabulary from the forward position;
generating an associated vocabulary corresponding to the forward input vocabulary based on a pre-trained paraphrasing prediction model;
detecting whether the associated vocabulary is successfully triggered;
Determining the association vocabulary successfully triggered as the key vocabulary;
and generating the target vocabulary according to the forward input vocabulary and the key vocabulary.
The positive position refers to the position of the vocabulary which is necessarily contained in the search text, and the negative position refers to the position of the vocabulary which is not necessarily contained in the search text.
FIG. 2 is a diagram showing the structure of a model of a paraphrasing predictive model in the text mining method of the present invention. In fig. 2, the paraphrasing predictive model includes a semantic analysis network and a predictive output network, the semantic analysis network including a forward feature extraction network and a reverse feature extraction network.
Through the paraphrasing prediction model, the associated vocabulary can be generated, so that a user is assisted in text mining, the convenience of mining is improved, and the situation that search text cannot be comprehensively obtained due to the loss of structural labels is avoided.
Specifically, the generating, by the electronic device, the associated vocabulary corresponding to the forward input vocabulary based on the pre-trained paraphrasing prediction model includes:
encoding the forward input vocabulary to obtain an input vector;
performing feature extraction on the input vector based on the forward feature extraction network to obtain a first feature;
Performing feature extraction on the input vector based on the reverse feature extraction network to obtain a second feature;
generating a semantic vector of the forward input vocabulary according to the first feature and the second feature;
based on the semantic vector, corresponding vocabulary is obtained from the prediction output network to be used as the associated vocabulary.
Wherein the forward feature extraction network and the backward feature extraction network each comprise a convolutional layer.
The forward feature extraction network refers to a network that analyzes vector elements of the input vector in a front-to-back order. The inverse feature extraction network refers to a network that analyzes vector elements of the input vector in order from back to front.
The semantic vector refers to an element average value of each feature element in the first feature and a corresponding feature element in the second feature.
The prediction output network comprises a full connection layer and a vector-vocabulary mapping table.
The input vector is analyzed by combining the forward feature extraction network and the reverse feature extraction network, so that the semantic vector can be accurately generated, the semantic vector can be accurately processed by the prediction output network, and the generation accuracy of the associated vocabulary is improved.
And 103, identifying the mining relation according to the input position of the target vocabulary in the operation interface.
In at least one embodiment of the invention, the input positions include a series position and a parallel position.
The mining relationship includes a series relationship (i.e., and) and a parallel relationship (i.e., or).
In at least one embodiment of the present invention, the electronic device identifying the mining relation according to the input position of the target vocabulary in the operation interface includes:
determining the mining relation corresponding to the target vocabulary at the serial position as a serial relation;
and determining the mining relation corresponding to the target vocabulary at the parallel position as a parallel relation.
The mining relation can be accurately identified through the input position.
104, generating a search sentence according to the template vocabulary in the mining template, the negative input vocabulary in the operation interface, the mining relation and the inter-word distance of the target vocabulary.
In at least one embodiment of the present invention, the template vocabulary refers to vocabulary information stored in the mining template, where the template vocabulary includes a template vocabulary with a negative vocabulary type and a template vocabulary with a positive vocabulary type.
The negative input vocabulary refers to the vocabulary input by the user at the negative position in the operation interface, and the negative input vocabulary refers to the vocabulary which is not necessarily contained in the search text.
The inter-word distance refers to the number of words between any target word and another target word, for example, from [ inter-word distance is 2 ], the search text may be: company [ havingzhi ].
In at least one embodiment of the present invention, the generating, by the electronic device, a search sentence according to a template vocabulary in the mining template, a negative input vocabulary in the operation interface, the mining relationship, and an inter-word distance of the target vocabulary includes:
recognizing the vocabulary types of the template vocabularies in the mining template, and recognizing the vocabulary relations of the template vocabularies in the mining template;
generating a negative search vocabulary by using the template vocabulary with the vocabulary type of the negative type and the negative input vocabulary;
generating a forward search vocabulary by using the template vocabulary with the vocabulary type being the forward type and the target vocabulary;
and writing the vocabulary relation, the negative search vocabulary, the positive search vocabulary, the mining relation and the inter-word distance into a preset query sentence to obtain the search sentence.
Wherein the vocabulary relation includes the series relation and the parallel relation.
The preset query statement may be a structured query statement.
Through recognizing the vocabulary types, the vocabulary with the vocabulary types of negative types can be screened out from the template vocabulary, the negative search vocabulary can be comprehensively generated by combining the negative input vocabulary, the vocabulary with the vocabulary types of positive types can be comprehensively generated by screening the template vocabulary, the positive search vocabulary can be comprehensively generated by combining the positive input vocabulary, and meanwhile, the search sentences can be rapidly generated by the preset query sentences, so that the text mining efficiency is improved.
And 105, calling a search thread in a preset search engine to execute the search sentence according to the text quantity of the template type corresponding to the mining template in the preset micro service architecture, and obtaining a search text.
In at least one embodiment of the present invention, the template types include, but are not limited to: not renewing, etc.
The preset micro-service architecture may be an architecture composed of a plurality of database servers.
And a plurality of search threads are stored in the preset search engine.
The search sentence is a public opinion text successfully matched with the search sentence in the preset micro-service architecture.
In at least one embodiment of the present invention, the electronic device invoking a search thread in a preset search engine to execute the search sentence according to the text quantity of the template type corresponding to the mining template in the preset micro service architecture, and obtaining the search text includes:
quantizing public opinion texts stored in the preset micro-service architecture based on the template type to obtain the text quantity;
acquiring the processing rate of an idle thread from the preset search engine;
extracting mining duration requirements from the text mining request;
determining the processing rate with the minimum value as a target rate;
calculating the number of threads according to the number of texts, the mining duration requirement and the target rate;
screening the search thread from a plurality of idle threads according to the thread number and the processing rate;
and calling the search thread, comparing the search sentence with the public opinion text, and determining the public opinion text successfully matched with the search sentence as the search text.
The idle threads refer to all execution threads in idle states in the preset search engine.
The mining duration requirement refers to a maximum period of time that can be tolerated in response to the text mining request.
The generation formula of the thread number is as follows:
wherein n is 1 Representing the number of threads, n 2 And representing the text quantity, v representing the target rate, and t representing the mining duration requirement.
The searching threads are threads screened from the plurality of idle threads according to the sequence of the processing speed from the big to the small, and the number of the searching threads is equal to the number of the threads.
In this embodiment, since the text-mining request is a further defined search on the mining template, the text quantity can be reasonably quantified according to the template type, and then the thread quantity can be determined as large as possible by selecting the processing rate with the smallest value as the target rate, so that the search thread can be screened out in combination with the processing rate of the thread order, and the text-mining request can be ensured to complete the response within the mining duration requirement.
In at least one embodiment of the present invention, when the negative search vocabulary is not included in the public opinion text, the positive search vocabulary is included, and the inter-word distance is satisfied, the electronic device determines the public opinion text as the search text.
And 106, generating a mining detail interface according to the text quantity and the search text.
It should be emphasized that, to further ensure the privacy and security of the mining detail interface, the mining detail interface may also be stored in a node of a blockchain.
In at least one embodiment of the present invention, the mining details interface includes the text quantity, the search quantity of the search text, and the like.
In at least one embodiment of the present invention, the generating, by the electronic device, a mining detail interface according to the text quantity and the search text includes:
counting the searching quantity of the searching text;
generating a search ratio according to the ratio of the search quantity to the text quantity;
counting the occurrence frequency of each forward search word in the search text;
calculating the matching degree of the search text and the search sentence according to the frequency;
screening target texts from a plurality of search texts according to the matching degree;
And writing the text quantity, the search ratio, the frequency and the target text into a preset interface to obtain the mining detail interface.
Wherein, the greater the frequency, the higher the matching degree.
The target text refers to N search texts with the largest matching degree, and N can be set according to the interface size of the preset interface.
The preset interface may be a blank interface, and the preset interface may also be an interface including the text number, the search ratio, the frequency and the tag information of the target text.
The matching degree can be accurately quantized through statistics of the frequency of each forward search word, the target text can be reasonably screened out through the matching degree, the target text is further displayed in the mining detail interface, and the intuitiveness of the target text is improved.
According to the technical scheme, the mining template corresponding to the text mining request is identified, and the user does not need to repeatedly input template content in the mining template in the operation interface, so that the search sentence can be generated rapidly, the generation efficiency of the search text is improved, when the mining template is monitored to be triggered, the mining template is required to be further improved, further the associated vocabulary which is input by an auxiliary user can be generated through the positive input vocabulary, the generation efficiency of the target vocabulary is improved, meanwhile, the locking of the mining range can be assisted on the premise that the user lacks a structured label, and further search sentences can be generated accurately by combining the template vocabulary, the negative input vocabulary, the mining relation and the inter-word distance, so that the generation accuracy of the search text is improved, the search thread can be reasonably called to process the search sentence through the text quantity, and the rapid processing of the search text can be realized on the premise that other request processing is not influenced. In addition, the mining detail interface is generated through the text quantity and the search text, so that a user can be assisted to quickly know the response condition of the text mining request.
Fig. 3 is a functional block diagram of a preferred embodiment of the text-mining apparatus of the present invention. The text mining device 11 includes a display unit 110, a generation unit 111, an identification unit 112, an execution unit 113, a determination unit 114, an acquisition unit 115, and a detection unit 116. The module/unit referred to herein is a series of computer readable instructions capable of being retrieved by the processor 13 and performing a fixed function and stored in the memory 12. In the present embodiment, the functions of the respective modules/units will be described in detail in the following embodiments.
A display unit 110 for displaying a mining template in an operation interface according to a text mining request when the text mining request is received;
a generating unit 111, configured to generate a target vocabulary according to a forward input vocabulary in the operation interface when it is monitored that the mining template is successfully triggered in the operation interface, where the target vocabulary includes the forward input vocabulary and a key vocabulary in an associated vocabulary corresponding to the forward input vocabulary;
an identifying unit 112, configured to identify an excavation relationship according to an input position of the target vocabulary in the operation interface;
The generating unit 111 is further configured to generate a search sentence according to a template vocabulary in the mining template, a negative input vocabulary in the operation interface, the mining relationship, and a distance between words of the target vocabulary;
an execution unit 113, configured to invoke a search thread in a preset search engine to execute the search sentence according to the number of texts in a preset micro service architecture, where the number of texts is in a preset micro service architecture, where the template type corresponds to the mining template, so as to obtain a search text;
the generating unit 111 is further configured to generate a mining details interface according to the text quantity and the search text.
In at least one embodiment of the present invention, before generating the target vocabulary according to the forward input vocabulary in the operation interface, the identifying unit 112 is further configured to identify a starting display time of the mining template on the operation interface;
an obtaining unit 115, configured to obtain an operation log of the operation interface based on the initial display time;
the identifying unit 112 is further configured to identify, from the operation interface, a button position of an associated button associated with the mining template, and identify a frame position of a text frame in the operation interface;
A detection unit 116 for detecting whether the operation log includes the button position and the frame position;
and the determining unit 114 is configured to determine that the mining template is successfully triggered in the operation interface if the operation log includes the button position and/or the frame position.
The operation log can be accurately obtained through the initial display time and the operation interface, and whether the excavation template is successfully triggered in the operation interface can be accurately identified through identifying whether the operation log comprises the button position and the frame position.
In other embodiments, the determining unit 114 is further configured to determine that the mining template is not successfully triggered in the operation interface if the operation log does not include the button position and the frame position.
In at least one embodiment of the present invention, the box positions include a positive position and a negative position, and the generating unit 111 is further configured to obtain the positive input vocabulary from the positive position;
generating an associated vocabulary corresponding to the forward input vocabulary based on a pre-trained paraphrasing prediction model;
Detecting whether the associated vocabulary is successfully triggered;
determining the association vocabulary successfully triggered as the key vocabulary;
and generating the target vocabulary according to the forward input vocabulary and the key vocabulary.
Through the paraphrasing prediction model, the associated vocabulary can be generated, so that a user is assisted in text mining, the convenience of mining is improved, and the situation that search text cannot be comprehensively obtained due to the loss of structural labels is avoided.
In at least one embodiment of the present invention, the paraphrasing prediction model includes a semantic analysis network and a prediction output network, where the semantic analysis network includes a forward feature extraction network and a reverse feature extraction network, and the generating unit 111 is further configured to encode the forward input vocabulary to obtain an input vector;
performing feature extraction on the input vector based on the forward feature extraction network to obtain a first feature;
performing feature extraction on the input vector based on the reverse feature extraction network to obtain a second feature;
generating a semantic vector of the forward input vocabulary according to the first feature and the second feature;
based on the semantic vector, corresponding vocabulary is obtained from the prediction output network to be used as the associated vocabulary.
The input vector is analyzed by combining the forward feature extraction network and the reverse feature extraction network, so that the semantic vector can be accurately generated, the semantic vector can be accurately processed by the prediction output network, and the generation accuracy of the associated vocabulary is improved.
In at least one embodiment of the present invention, the generating unit 111 is further configured to identify a vocabulary type of the template vocabulary in the mining template, and identify a vocabulary relationship of the template vocabulary in the mining template;
generating a negative search vocabulary by using the template vocabulary with the vocabulary type of the negative type and the negative input vocabulary;
generating a forward search vocabulary by using the template vocabulary with the vocabulary type being the forward type and the target vocabulary;
and writing the vocabulary relation, the negative search vocabulary, the positive search vocabulary, the mining relation and the inter-word distance into a preset query sentence to obtain the search sentence.
Through recognizing the vocabulary types, the vocabulary with the vocabulary types of negative types can be screened out from the template vocabulary, the negative search vocabulary can be comprehensively generated by combining the negative input vocabulary, the vocabulary with the vocabulary types of positive types can be comprehensively generated by screening the template vocabulary, the positive search vocabulary can be comprehensively generated by combining the positive input vocabulary, and meanwhile, the search sentences can be rapidly generated by the preset query sentences, so that the text mining efficiency is improved.
In at least one embodiment of the present invention, the generating unit 111 is further configured to count a search number of the search text;
generating a search ratio according to the ratio of the search quantity to the text quantity;
counting the occurrence frequency of each forward search word in the search text;
calculating the matching degree of the search text and the search sentence according to the frequency;
screening target texts from a plurality of search texts according to the matching degree;
and writing the text quantity, the search ratio, the frequency and the target text into a preset interface to obtain the mining detail interface.
The matching degree can be accurately quantized through statistics of the frequency of each forward search word, the target text can be reasonably screened out through the matching degree, the target text is further displayed in the mining detail interface, and the intuitiveness of the target text is improved.
In at least one embodiment of the present invention, the execution unit 113 is further configured to quantize the public opinion text stored in the preset micro-service architecture based on the template type, to obtain the text quantity;
Acquiring the processing rate of an idle thread from the preset search engine;
extracting mining duration requirements from the text mining request;
determining the processing rate with the minimum value as a target rate;
calculating the number of threads according to the number of texts, the mining duration requirement and the target rate;
screening the search thread from a plurality of idle threads according to the thread number and the processing rate;
and calling the search thread, comparing the search sentence with the public opinion text, and determining the public opinion text successfully matched with the search sentence as the search text.
In this embodiment, since the text-mining request is a further defined search on the mining template, the text quantity can be reasonably quantified according to the template type, and then the thread quantity can be determined as large as possible by selecting the processing rate with the smallest value as the target rate, so that the search thread can be screened out in combination with the processing rate of the thread order, and the text-mining request can be ensured to complete the response within the mining duration requirement.
According to the technical scheme, the mining template corresponding to the text mining request is identified, and the user does not need to repeatedly input template content in the mining template in the operation interface, so that the search sentence can be generated rapidly, the generation efficiency of the search text is improved, when the mining template is monitored to be triggered, the mining template is required to be further improved, further the associated vocabulary which is input by an auxiliary user can be generated through the positive input vocabulary, the generation efficiency of the target vocabulary is improved, meanwhile, the locking of the mining range can be assisted on the premise that the user lacks a structured label, and further search sentences can be generated accurately by combining the template vocabulary, the negative input vocabulary, the mining relation and the inter-word distance, so that the generation accuracy of the search text is improved, the search thread can be reasonably called to process the search sentence through the text quantity, and the rapid processing of the search text can be realized on the premise that other request processing is not influenced. In addition, the mining detail interface is generated through the text quantity and the search text, so that a user can be assisted to quickly know the response condition of the text mining request.
Fig. 4 is a schematic structural diagram of an electronic device according to a preferred embodiment of the present invention for implementing the text mining method.
In one embodiment of the invention, the electronic device 1 includes, but is not limited to, a memory 12, a processor 13, and computer readable instructions, such as text-mining programs, stored in the memory 12 and executable on the processor 13.
It will be appreciated by those skilled in the art that the schematic diagram is merely an example of the electronic device 1 and does not constitute a limitation of the electronic device 1, and may include more or less components than illustrated, or may combine certain components, or different components, e.g. the electronic device 1 may further include input-output devices, network access devices, buses, etc.
The processor 13 may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. The general purpose processor may be a microprocessor or the processor may be any conventional processor, etc., and the processor 13 is an operation core and a control center of the electronic device 1, connects various parts of the entire electronic device 1 using various interfaces and lines, and executes an operating system of the electronic device 1 and various installed applications, program codes, etc.
Illustratively, the computer readable instructions may be partitioned into one or more modules/units that are stored in the memory 12 and executed by the processor 13 to complete the present invention. The one or more modules/units may be a series of computer readable instructions capable of performing a specific function, the computer readable instructions describing a process of executing the computer readable instructions in the electronic device 1. For example, the computer-readable instructions may be divided into a display unit 110, a generation unit 111, an identification unit 112, an execution unit 113, a determination unit 114, an acquisition unit 115, and a detection unit 116.
The memory 12 may be used to store the computer readable instructions and/or modules, and the processor 13 may implement various functions of the electronic device 1 by executing or executing the computer readable instructions and/or modules stored in the memory 12 and invoking data stored in the memory 12. The memory 12 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data created according to the use of the electronic device, etc. Memory 12 may include non-volatile and volatile memory, such as: a hard disk, memory, plug-in hard disk, smart Media Card (SMC), secure Digital (SD) Card, flash Card (Flash Card), at least one disk storage device, flash memory device, or other storage device.
The memory 12 may be an external memory and/or an internal memory of the electronic device 1. Further, the memory 12 may be a physical memory, such as a memory bank, a TF Card (Trans-flash Card), or the like.
The integrated modules/units of the electronic device 1 may be stored in a computer readable storage medium if implemented in the form of software functional units and sold or used as separate products. Based on such understanding, the present invention may also be implemented by implementing all or part of the processes in the methods of the embodiments described above, by instructing the associated hardware by means of computer readable instructions, which may be stored in a computer readable storage medium, the computer readable instructions, when executed by a processor, implementing the steps of the respective method embodiments described above.
Wherein the computer readable instructions comprise computer readable instruction code which may be in the form of source code, object code, executable files, or in some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying the computer readable instruction code, a recording medium, a USB flash disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory).
The blockchain is a novel application mode of computer technologies such as distributed text mining, point-to-point transmission, consensus mechanism, encryption algorithm and the like. The Blockchain (Blockchain), which is essentially a decentralised database, is a string of data blocks that are generated by cryptographic means in association, each data block containing a batch of information of network transactions for verifying the validity of the information (anti-counterfeiting) and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, an application services layer, and the like.
In connection with fig. 1, the memory 12 in the electronic device 1 stores computer readable instructions implementing a text mining method, the processor 13 being executable to implement:
when a text mining request is received, displaying a mining template in an operation interface according to the text mining request;
when the mining template is monitored to be successfully triggered in the operation interface, generating a target word according to a forward input word in the operation interface, wherein the target word comprises the forward input word and a key word in an associated word corresponding to the forward input word;
Identifying an excavation relation according to the input position of the target vocabulary in the operation interface;
generating search sentences according to template words in the mining template, negative input words in the operation interface, the mining relation and inter-word distances of the target words;
according to the text quantity of the template type corresponding to the mining template in a preset micro-service architecture, a search thread in a preset search engine is called to execute the search sentence, and a search text is obtained;
and generating a mining detail interface according to the text quantity and the search text.
In particular, the specific implementation method of the processor 13 on the computer readable instructions may refer to the description of the relevant steps in the corresponding embodiment of fig. 1, which is not repeated herein.
In the several embodiments provided in the present invention, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical function division, and there may be other manners of division when actually implemented.
The computer readable storage medium has stored thereon computer readable instructions, wherein the computer readable instructions when executed by the processor 13 are configured to implement the steps of:
When a text mining request is received, displaying a mining template in an operation interface according to the text mining request;
when the mining template is monitored to be successfully triggered in the operation interface, generating a target word according to a forward input word in the operation interface, wherein the target word comprises the forward input word and a key word in an associated word corresponding to the forward input word;
identifying an excavation relation according to the input position of the target vocabulary in the operation interface;
generating search sentences according to template words in the mining template, negative input words in the operation interface, the mining relation and inter-word distances of the target words;
according to the text quantity of the template type corresponding to the mining template in a preset micro-service architecture, a search thread in a preset search engine is called to execute the search sentence, and a search text is obtained;
and generating a mining detail interface according to the text quantity and the search text.
The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional module in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units can be realized in a form of hardware or a form of hardware and a form of software functional modules.
The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
Furthermore, it is evident that the word "comprising" does not exclude other elements or steps, and that the singular does not exclude a plurality. The units or means may also be implemented by one unit or means in software or hardware. The terms first, second, etc. are used to denote a name, but not any particular order.
Finally, it should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention.
Claims (10)
1. A text mining method, characterized in that the text mining method comprises:
when a text mining request is received, displaying a mining template in an operation interface according to the text mining request;
when the mining template is monitored to be successfully triggered in the operation interface, generating a target word according to a forward input word in the operation interface, wherein the target word comprises the forward input word and a key word in an associated word corresponding to the forward input word;
identifying an excavation relation according to the input position of the target vocabulary in the operation interface;
generating search sentences according to template words in the mining template, negative input words in the operation interface, the mining relation and inter-word distances of the target words;
according to the text quantity of the template type corresponding to the mining template in a preset micro-service architecture, a search thread in a preset search engine is called to execute the search sentence, and a search text is obtained;
and generating a mining detail interface according to the text quantity and the search text.
2. The text mining method of claim 1, wherein before generating the target vocabulary from the forward input vocabulary in the operator interface, the text mining method further comprises:
Identifying the initial display time of the excavation template on the operation interface;
acquiring an operation log of the operation interface based on the initial display time;
identifying a button position of an associated button associated with the mining template from the operation interface, and identifying a frame position of a text frame in the operation interface;
detecting whether the operation log includes the button position and the frame position;
and if the operation log comprises the button position and/or the frame position, determining that the mining template is successfully triggered in the operation interface.
3. The text-mining method of claim 2, wherein the box positions include a positive position and a negative position, and wherein generating the target vocabulary from the positive input vocabulary in the operator interface comprises:
acquiring the forward input vocabulary from the forward position;
generating an associated vocabulary corresponding to the forward input vocabulary based on a pre-trained paraphrasing prediction model;
detecting whether the associated vocabulary is successfully triggered;
determining the association vocabulary successfully triggered as the key vocabulary;
and generating the target vocabulary according to the forward input vocabulary and the key vocabulary.
4. The text-mining method of claim 3, wherein the paraphrasing model includes a semantic analysis network and a prediction output network, the semantic analysis network includes a forward feature extraction network and a reverse feature extraction network, and the generating the associated vocabulary corresponding to the forward input vocabulary based on the pre-trained paraphrasing model includes:
encoding the forward input vocabulary to obtain an input vector;
performing feature extraction on the input vector based on the forward feature extraction network to obtain a first feature;
performing feature extraction on the input vector based on the reverse feature extraction network to obtain a second feature;
generating a semantic vector of the forward input vocabulary according to the first feature and the second feature;
based on the semantic vector, corresponding vocabulary is obtained from the prediction output network to be used as the associated vocabulary.
5. The text mining method of claim 1, wherein the generating search sentences based on template words in the mining template, negative input words in the operation interface, the mining relation, and inter-word distances of the target words comprises:
Recognizing the vocabulary types of the template vocabularies in the mining template, and recognizing the vocabulary relations of the template vocabularies in the mining template;
generating a negative search vocabulary by using the template vocabulary with the vocabulary type of the negative type and the negative input vocabulary;
generating a forward search vocabulary by using the template vocabulary with the vocabulary type being the forward type and the target vocabulary;
and writing the vocabulary relation, the negative search vocabulary, the positive search vocabulary, the mining relation and the inter-word distance into a preset query sentence to obtain the search sentence.
6. The text mining method of claim 5, wherein the generating a mining details interface from the number of texts and the search text comprises:
counting the searching quantity of the searching text;
generating a search ratio according to the ratio of the search quantity to the text quantity;
counting the occurrence frequency of each forward search word in the search text;
calculating the matching degree of the search text and the search sentence according to the frequency;
screening target texts from a plurality of search texts according to the matching degree;
and writing the text quantity, the search ratio, the frequency and the target text into a preset interface to obtain the mining detail interface.
7. The text mining method according to claim 1, wherein the calling a search thread in a preset search engine to execute the search sentence according to the text quantity of the template type corresponding to the mining template in a preset micro service architecture, and obtaining the search text comprises:
quantizing public opinion texts stored in the preset micro-service architecture based on the template type to obtain the text quantity;
acquiring the processing rate of an idle thread from the preset search engine;
extracting mining duration requirements from the text mining request;
determining the processing rate with the minimum value as a target rate;
calculating the number of threads according to the number of texts, the mining duration requirement and the target rate;
screening the search thread from a plurality of idle threads according to the thread number and the processing rate;
and calling the search thread, comparing the search sentence with the public opinion text, and determining the public opinion text successfully matched with the search sentence as the search text.
8. A text mining apparatus, the text mining apparatus comprising:
The display unit is used for displaying the mining template in the operation interface according to the text mining request when the text mining request is received;
the generating unit is used for generating a target vocabulary according to forward input vocabulary in the operation interface when the mining template is monitored to be successfully triggered in the operation interface, wherein the target vocabulary comprises the forward input vocabulary and key vocabulary in associated vocabulary corresponding to the forward input vocabulary;
the identification unit is used for identifying the mining relation according to the input position of the target vocabulary in the operation interface;
the generating unit is further used for generating search sentences according to template words in the mining template, negative input words in the operation interface, the mining relation and inter-word distances of the target words;
the execution unit is used for calling a search thread in a preset search engine to execute the search sentence according to the text quantity of the template type corresponding to the mining template in the preset micro-service architecture to obtain a search text;
the generating unit is further used for generating a mining detail interface according to the text quantity and the search text.
9. An electronic device, the electronic device comprising:
a memory storing computer readable instructions; a kind of electronic device with high-pressure air-conditioning system
A processor executing computer readable instructions stored in the memory to implement the text mining method of any of claims 1 to 7.
10. A computer-readable storage medium, characterized by: stored in the computer readable storage medium are computer readable instructions that are executed by a processor in an electronic device to implement the text mining method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310416583.5A CN116383343A (en) | 2023-04-11 | 2023-04-11 | Text mining method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310416583.5A CN116383343A (en) | 2023-04-11 | 2023-04-11 | Text mining method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116383343A true CN116383343A (en) | 2023-07-04 |
Family
ID=86980572
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310416583.5A Pending CN116383343A (en) | 2023-04-11 | 2023-04-11 | Text mining method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116383343A (en) |
-
2023
- 2023-04-11 CN CN202310416583.5A patent/CN116383343A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112633419B (en) | Small sample learning method and device, electronic equipment and storage medium | |
| JP2020135853A (en) | Method, apparatus, electronic device, computer readable medium, and computer program for determining descriptive information | |
| WO2017137859A1 (en) | Systems and methods for language feature generation over multi-layered word representation | |
| CN109408829B (en) | Method, device, equipment and medium for determining readability of article | |
| CN112686036B (en) | Risk text recognition method and device, computer equipment and storage medium | |
| CN112417128B (en) | Method and device for recommending dialect, computer equipment and storage medium | |
| CN113032528B (en) | Case analysis method, case analysis device, case analysis equipment and storage medium | |
| US20140214402A1 (en) | Implementation of unsupervised topic segmentation in a data communications environment | |
| CN116304748B (en) | Text similarity calculation method, system, equipment and medium | |
| CN114090794A (en) | Event map construction method based on artificial intelligence and related equipment | |
| CN114387061A (en) | Product pushing method and device, electronic equipment and readable storage medium | |
| CN116151233A (en) | Data labeling and generating method, model training method, device and medium | |
| CN113342977B (en) | Invoice image classification method, device, equipment and storage medium | |
| CN116402166B (en) | Training method and device of prediction model, electronic equipment and storage medium | |
| US20230186212A1 (en) | System, method, electronic device, and storage medium for identifying risk event based on social information | |
| CN117275466A (en) | Business intention recognition method, device, equipment and storage medium thereof | |
| CN113627186B (en) | Entity relation detection method based on artificial intelligence and related equipment | |
| CN116795978A (en) | Complaint information processing method and device, electronic equipment and medium | |
| CN113326365B (en) | Reply sentence generation method, device, equipment and storage medium | |
| WO2023137903A1 (en) | Reply statement determination method and apparatus based on rough semantics, and electronic device | |
| CN115525750A (en) | Robot phonetics detection visualization method and device, electronic equipment and storage medium | |
| CN115510188A (en) | Text keyword association method, device, equipment and storage medium | |
| CN115358817A (en) | Intelligent product recommendation method, device, equipment and medium based on social data | |
| CN113408265B (en) | Semantic analysis method, device and equipment based on human-computer interaction and storage medium | |
| CN113050933B (en) | Brain graph data processing method, device, 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 |