[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

CN110413767A - System and method based on spatial term rendering content - Google Patents

System and method based on spatial term rendering content Download PDF

Info

Publication number
CN110413767A
CN110413767A CN201910718769.XA CN201910718769A CN110413767A CN 110413767 A CN110413767 A CN 110413767A CN 201910718769 A CN201910718769 A CN 201910718769A CN 110413767 A CN110413767 A CN 110413767A
Authority
CN
China
Prior art keywords
rendering content
input
template
natural language
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.)
Pending
Application number
CN201910718769.XA
Other languages
Chinese (zh)
Inventor
易峥
夏炜
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hithink Royalflush Information Network Co Ltd
Original Assignee
Hithink Royalflush Information Network Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Hithink Royalflush Information Network Co Ltd filed Critical Hithink Royalflush Information Network Co Ltd
Priority to CN201910718769.XA priority Critical patent/CN110413767A/en
Publication of CN110413767A publication Critical patent/CN110413767A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33Querying
    • G06F16/3331Query processing
    • G06F16/334Query execution
    • G06F16/3344Query execution using natural language analysis
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/33Querying
    • G06F16/338Presentation of query results
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/34Browsing; Visualisation therefor
    • G06F16/345Summarisation for human users
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/35Clustering; Classification

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Artificial Intelligence (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

The embodiment of the present application discloses a kind of system based on spatial term rendering content, method, apparatus and computer readable storage medium, and the method includes obtaining the natural language of input;The natural language of input is identified and analyzed, to extract keyword;It is generated based on the keyword and presents template;Entity and attribute are obtained based on the keyword, the entity and the corresponding information of attribute are inserted in the presentation template, rendering content is generated;The rendering content of generation is showed into user.The application passes through information processing, output diversification, personalized rendering content, to meet diversification, the individual demand of user using the most-often used natural language of the mankind as input.

Description

System and method based on spatial term rendering content
Technical field
This application involves field of information processing more particularly to a kind of systems based on spatial term rendering content, side Method, device and computer readable storage medium.
Background technique
Natural language is that the mankind are used to express a kind of expression way of certain specific meanings, natural language be Human communication and The most mainstream of thinking also most important tool.Currently, having had already appeared natural language processing (natural language Processing, NLP) Men Xueke, it is an important directions in computer science and artificial intelligence field, mainly Purpose is to realize between humans and machines natural language communication.But natural language processing at present is mainly used in translation field, i.e., it is simple real The function of existing semantics recognition.
It can therefore, it is necessary to provide a kind of system based on spatial term rendering content, method, apparatus and computer Read storage medium.
Summary of the invention
The application's in a first aspect, providing a kind of method based on spatial term rendering content, the method It is realized by least one processor, which comprises obtain the natural language of input;The natural language of input is identified And analysis, to extract keyword;It is generated based on the keyword and presents template;Entity and attribute are obtained based on the keyword, The entity and the corresponding information of attribute are inserted in the presentation template, rendering content is generated.
In some embodiments, the presentation template includes in report class template, table class template and figure class template It is at least one.
In some embodiments, the rendering content includes at least one of report, table, figure.
In some embodiments, described that the method for presenting template is generated based on the keyword further include: to recommend to user Applicable presentation template, or pop-up template selection window are selected for user.
In some embodiments, the presentation template is included at least for presenting the standard area of standard content and for filling out Enter the white space of information.
In some embodiments, the method for obtaining entity and attribute based on the keyword includes: based on the pass Keyword is retrieved from information source and obtains the entity and attribute, wherein the information source include the sector database constructed in advance, Universal Database and webpage.
In some embodiments, in the rendering content, wherein information is traced by way of remarks, footnote or link The information source.
In some embodiments, the input mode of the natural language include voice input, touch input, gesture input, Text input, expression in the eyes input and expression input.
In the second aspect of the application, a kind of system based on spatial term rendering content is provided, comprising: information Acquisition module, natural language for receiving input;Message processing module, for being identified to the natural language of input And analysis, to extract keyword;Template generation module is generated based on the keyword and presents template;Content generating module is based on The keyword obtains entity and attribute, and the entity and the corresponding information of attribute are inserted in the presentation template, raw At rendering content.
In the third aspect of the application, a kind of device that file is presented based on spatial term, described device are provided Including at least one processor and at least one processor;At least one processor is for storing computer instruction;Institute At least one processor is stated for executing at least partly instruction in the computer instruction to realize operation as described above.
In the fourth aspect of the application, a kind of computer-readable storage based on spatial term rendering content is provided Medium, the storage medium store computer instruction, realize when the computer instruction is executed by processor as described above Operation.
At the 5th aspect of the application, a kind of method based on spatial term rendering content is provided, comprising: obtain The natural language of input;The natural language is sent to server-side;Receive the rendering content that the server-side returns;It is described to be in Passing content includes server-side based on the presentation template that determines of natural language and server-side of the input based on the input The entity and the corresponding information of attribute that natural language determines;Show the rendering content.
In some embodiments, the method also includes: receive server-side return at least one present template for Family selection;It receives the selection of user and sends it to server-side.
In some embodiments, in the rendering content, wherein information is traced by way of remarks, footnote or link Information source.
In some embodiments, the rendering content includes at least one of report, table, figure.
At the 6th aspect of the application, a kind of system based on spatial term rendering content is provided, comprising: information Acquisition module, natural language for receiving input;Information sending module, for the natural language to be sent to server-side; Information receiving module, the rendering content returned for receiving the server-side;The rendering content includes described in server-side is based on The entity and attribute that the presentation template and server-side that the natural language of input determines are determined based on the natural language of the input Corresponding information;Output module, for showing the rendering content.
At the 7th aspect of the application, a kind of device based on spatial term rendering content, described device are provided Including at least one processor and at least one processor;At least one processor is for storing computer instruction;Institute At least one processor is stated for executing at least partly instruction in the computer instruction to realize operation as described above.
In the eighth aspect of the application, a kind of computer-readable storage based on spatial term rendering content is provided Medium, the storage medium store computer instruction, realize when the computer instruction is executed by processor as described above Operation.
The application passes through information processing, output diversification, individual character using the most-often used natural language of the mankind as input The rendering content of change, to meet diversification, the individual demand of user.
Detailed description of the invention
Technical solution in ord to more clearly illustrate embodiments of the present application, below will be to required use in embodiment description Attached drawing be briefly described.It should be evident that the accompanying drawings in the following description is only some examples or embodiment of the application, For those of ordinary skill in the art, without creative efforts, can also according to these attached drawings by The application is applied to other similar scenes.Wherein:
Fig. 1 is the illustrative system block diagram according to some embodiments of the present application;
Fig. 2 is the illustrative structural block diagram according to some embodiments of the present application;
Fig. 3 is the illustrative flow chart according to some embodiments of the present application;
Fig. 4 is the illustrative flow chart according to other embodiments of the application;
Fig. 5 is the illustrative structural block diagram according to the other embodiment of the application;
Fig. 6 is the illustrative flow chart according to the other embodiment of the application.
Specific embodiment
In order to illustrate more clearly of the technical solution of embodiments herein, will make below to required in embodiment description Attached drawing is briefly described.It should be evident that the accompanying drawings in the following description is only some examples or implementation of the application Example, for those of ordinary skill in the art, without creative efforts, can also be according to these attached drawings The application is applied to other similar scene.Unless being explained obviously or separately, identical label generation in figure from language environment The identical structure or operation of table.
As shown in the application and claims, unless context clearly prompts exceptional situation, " one ", "one", " one The words such as kind " and/or "the" not refer in particular to odd number, may also comprise plural number.It is, in general, that term " includes " only prompts to wrap with "comprising" Include clearly identify the step of and element, and these steps and element do not constitute one it is exclusive enumerate, method or apparatus The step of may also including other or element.
Although the application is made that various references to the certain module in system according to an embodiment of the present application, however, Any amount of disparate modules can be used and be operated on vehicular client and/or server.The module is only explanation Property, and disparate modules can be used in the different aspect of the system and method.
Flow chart used herein is used to illustrate operation performed by system according to an embodiment of the present application.It should Understand, before or operation below not necessarily accurately carry out in sequence.On the contrary, can be handled according to inverted order or simultaneously Various steps.It is also possible to during other operations are added to these, or remove a certain step from these processes or count step behaviour Make.
Fig. 1 is the illustrative system block diagram according to some embodiments of the present application, for illustrating the optional of whole system Hardware composition.System 100, which can be, has the function based on spatial term rendering content for referring in a network environment Wisdom system.The system 100 may include server 110, network 120, user terminal 130 and memory 140.
The server 110 can be computer server.Server 110 can be communicated with user terminal 130, to provide Various functions based on spatial term rendering content, for example, server 110 obtains oneself of input from user terminal 130 Right language;For another example the natural language of 110 pairs of server inputs is identified and analyzed, to extract keyword;In another example clothes The rendering content of generation is transferred to user terminal 130 by business device 110, for showing user etc..In some embodiments, it takes Business device 110 can be single server or server group.Server group can be the center connecting by access point with network 120 Server group or the distributed server group that network 120 is connected to by one or more access points.In some embodiments, it takes Business device 110 can be connected locally to network 120 or be connected remotely to network 120.
In some embodiments, server 110 can access via network 120 and be stored in user terminal 130 and/or storage Information and/or data in device 140.In some embodiments, the Back end data that memory 140 may be used as server 110 is deposited Reservoir.In some embodiments, server 110 can be implemented in cloud platform.It is only used as example, cloud platform may include privately owned Cloud, public cloud, mixed cloud, community cloud, distributed cloud, internal cloud, multi layer cloud etc. or any combination thereof.In some embodiments, Server 110 can execute on the computing device.
In some embodiments, server 110 may include processing engine 112.Processing engine 112 can handle and execute The related information of one or more functions described in this application and/or data.In some embodiments, processing engine 112 can Including one or more processing engine (for example, single-chip processing engine or multi-chip handle engine).Only it is used as example, processing Engine 112 may include central processing unit (CPU), application-specific integrated circuit (ASIC), specific application instruction set processor (ASIP), graphics processing unit (GPU), physical processing unit (PPU), digital signal processor (DSP), scene can program gate arrays Arrange (FPGA), can program logic device (PLD), controller, micro controller unit, Reduced Instruction Set Computer (RISC), micro- place Manage device etc. or any combination thereof.
Network 120 can promote the exchange of information and/or data.In some embodiments, one in system 100 or more A component (for example, server 110, user terminal 130 and memory 140) can pass through its into system 100 of network 120 He sends information and/or data by component.For example, server 110 can be accessed and/or be obtained from memory 140 via network 120 Data.As another example, server 110 can send memory 140 for related data via network 120.
In some embodiments, network 120 can be any form of wired or wireless network, or any combination thereof.Only As example, network 120 can be cable system, cable network, fiber optic network, telecommunication network, internal network, internet, office Domain network (LAN), wide area network (WAN), Wireless LAN (WLAN), Metropolitan Area Network (MAN) (MAN), public switched telephone network (PSTN), Blueteeth network, ZigBee-network, near-field communication (NFC) etc. or any combination thereof.For example, network 120 may include one or more A network access point.For example, network 120 may include wired or wireless network exchange point, such as base station and/or internet exchange Point 120-1,120-2 ..., by exchanging point, the one or more components of system 100 may be coupled to network 120 to exchange Data and/or information.
User terminal 130 can be used for obtaining the natural language of user's input, can also be sent to the natural language Server 110, and receive the rendering content of the return of server 110;Certainly it can be also used for showing the rendering content to user. User terminal 130 may include mobile device 130-1, tablet computer 130-2, portable computer 130-3, in vehicle 130-4 Built-in device etc. or any combination thereof.In some embodiments, mobile device 130-1 may include Intelligent home device, can Object wearing device, intelligent mobile device, virtual reality device, augmented reality device etc. or any combination thereof.In some embodiments, Intelligent home device may include Intelligent lightening device, the control device of intelligent electric appliance, intelligent monitoring device, smart television, intelligence Energy USB PC Video Camera, intercom etc. or any combination thereof.Wearable device may include Intelligent bracelet, intelligent footgear, Brilliant Eyes The combination of one or more of mirror, intelligent helmet, intelligent headband, intelligent clothing, intelligent knapsack and intelligent accessories etc..Some In embodiment, intelligent mobile device may include smart phone, personal digital assistant (PDA), game station, navigation device, pin Sell point (POS) device etc. or any combination thereof.In some embodiments, virtual reality device and/or augmented reality device can wrap Virtual implementing helmet, virtual reality glasses, virtual reality patch, the augmented reality helmet, augmented reality glasses, augmented reality is included to mend Fourth etc. or any combination thereof.For example, virtual reality device and/or augmented reality equipment may include Google GlassTM, Oculus RiftTM, HololensTM, Gear VRTMDeng.In some embodiments, the built-in device in vehicle 130-4 can wrap Include built-in computer, vehicle-mounted built-in television, built-in tablet computer etc..In some embodiments, user terminal 130 may include Signal transmitter and signal receiver, for being communicated with positioning system to position the position of user and/or user terminal 130 It sets.In some embodiments, positioning system can be global positioning system (GPS), Global Navigation Satellite System (GLONASS), Compass navigation systems (COMPASS), Beidou navigation satellite system, GALILEO positioning system, quasi- zenith satellite system (QZSS) etc..
Memory 140 can store data and/or instruction.The data may include number related with multiple industry characteristics According to, data related with multiple users, data related with multiple presentation templates, data related with external environment etc..
In some embodiments, memory 140 can store the data obtained from user terminal 130.For example, memory 140 can store information associated with user terminal 130.In some embodiments, memory 140 can store server 110 data and/or instruction that can be executed.It can execute instruction and described in this application be in based on spatial term to provide Pass content.
In some embodiments, memory 140 may include mass storage, removable memory, read-write volatile Memory, read-only memory (ROM) etc. or any combination thereof.Exemplary mass storage may include disk, CD, solid-state Driver etc..Exemplary removable memory may include flash drive, floppy disk, CD, storage card, zipper disk, tape etc.. Exemplary volatile read-write memory may include random access memory (RAM).Exemplary RAM may include dynamic ram (DRAM), double data rate synchronous dynamic ram (DDR SDRAM), static RAM (SRAM), the electricity of thyristor RAM (T-RAM) and zero Hold RAM (Z-RAM) etc..Exemplary ROM may include mask rom (MROM), programming ROM (PROM), erasable programmable ROM (EPROM), electrically erasable ROM (EEPROM), CD ROM (CD-ROM), digital versatile disc ROM etc..In some realities It applies in example, the memory 140 can be realized in cloud platform.It is only used as example, cloud platform may include private clound, public Cloud, mixed cloud, community cloud, distributed cloud, internal cloud, multi layer cloud etc. or any combination thereof.
In some embodiments, one or more components in system 100 can access via network 120 and be stored in storage Data or instruction in device 140.In some embodiments, memory 140 can be directly connected to server 110 and deposit as rear end Storage.In some embodiments, one or more components in system 100 (for example, server 110, user terminal 130) can have Access the license of memory 140.
In some embodiments, the system 100 can be applied to multiple fields, such as education, management, traffic, sport, joy Pleasure, manufacturing industry, agricultural etc., such as this system 100 can also be applied to wisdom finance/field of finance and economics (such as banking machine People, money-managing consultant robot etc.), such as: system 100 based on the natural language of input to the complicated and diversified company information of magnanimity into Row processing, to extract the data target that industry analyst most pays close attention to, and carries out investment analysis summary, and finally with finance report The form of announcement is shown to user, reduces unnecessary repetition manual labor to maximize, help is analyzed personnel and invested certainly Plan.Wherein, the financial report includes but is not limited to K line chart, offer curve figure, valence-amount trend graph, yield curve variation Figure, enterprise diagnosis report, bond rating report, throws preceding industry research report, the report of new listed company, enterprise at quotation information table Indicating risk report, listing prospectus etc. after statement of requirements, throwing during lasting tracking.
In some embodiments, system 100 can also be directed to the characteristics of industry or field to the rendering content ultimately generated It is particularly handled, equally by taking wisdom finance/field of finance and economics as an example, system can be automatically on the basis of existing rendering content Supplement auxiliary data (for example, security attribute, newest valuation, newest deal message etc.) is persistently monitored before user terminates order Market data, the real-time dynamic table of setting or report, drawn a portrait according to user customized prompting or early warning rule etc..
Certainly, the system 100 can also be applied to other field, such as smart home, intelligence manufacture, intelligent medical, Intelligent art etc., by taking system 100 is applied to News Field as an example, system 100 can quickly be obtained according to the natural language of input Content (such as current events, sport) are interrogated when the news of user demand, obtain demand to meet the diversified news information of user.
In some embodiments, system 100 can also realize the form and content of customized rendering content.For example, system 100 output rendering contents can for shares changing tendency figure, financial statement, industry analysis report etc. gauge outfits, transverse and longitudinal coordinate name and Unit etc..The content that system 100 defines is also diversified, comprising: be 1. based on/can be not based on template, define in presenting Every particular content, the content including the content and update filled in appearance;2. the friendship between rendering content and user can be defined Mutual mode, for example, deleting, splitting, merge, transfer, cancelling;3. can be with the display mode of definition tables etc., for example, passing through use The natural language at family inputs, and carries out multi-screen, multiwindow or multi-screen/multiwindow linkage display (that is, relevance is shown), e.g., Sheet1 is summary table, and sheet3 is the particular content of an item in summary table, carries out linkage display by the natural language of user, again For example, the natural language by user inputs, indication range, ratio, sequence of rendering content etc. are defined.
Fig. 2 is the module map of the system based on spatial term rendering content according to some embodiments of the application. The system 10 includes: information acquisition module 11, natural language for receiving input;Message processing module 12, for pair The natural language of input is identified and analyzed, to extract keyword;Template generation module 13, it is raw based on the keyword At presentation template;Content generating module 14 obtains entity and attribute based on the keyword, and the entity and attribute is respectively right The information answered is inserted in the presentation template, and rendering content is generated;It can also include output module 15, for showing the presentation Content.
It should be noted that in further embodiments, keyword can also be being extracted using message processing module 12 Entity and attribute are obtained simultaneously;Entity and attribute of the template generation module 13 based on the keyword and acquisition, which generate, presents mould Plate;Content generating module 14, entity and attribute based on the keyword and acquisition are corresponding by the entity and attribute Information is inserted in the presentation template, and rendering content is generated.In other words, it obtains entity and attribute can be in message processing module 12 realize, can also realize in content generating module 14.
It should be appreciated that system shown in Fig. 2 and its module can use various modes to realize.For example, in some implementations In example, system and its module can be realized by the combination of hardware, software or software and hardware.Wherein, hardware components can To be realized using special logic;Software section then can store in memory, by instruction execution system appropriate, for example (,) it is micro- Processor or special designs hardware execute.It will be appreciated by those skilled in the art that computer, which can be used, in above system to hold Row instruction and/or be included in the processor control code to realize, such as such as mounting medium of disk, CD or DVD-ROM, Such as programmable memory of read-only memory (firmware) or the data medium of such as optics or electrical signal carrier above mention Such code is supplied.The system and its module of the application can not only have such as ultra large scale integrated circuit or gate array, all Such as semiconductor of logic chip, transistor or field programmable gate array, programmable logic device etc. may be programmed The hardware circuit of hardware device is realized, such as software realization as performed by various types of processors can also be used, can be with By combination (for example, firmware) Lai Shixian of above-mentioned hardware circuit and software.
In other embodiments of the application, a kind of method based on spatial term rendering content, Fig. 3 are provided It is the illustrative flow chart according to some embodiments of the present application, for illustrating the step based on spatial term rendering content Suddenly.The method is realized by least one processor, which comprises step 101, the natural language for obtaining input;Step 102, the natural language of input is identified and analyzed, to extract keyword;Step 103, based on the keyword generation be in Pass template;And step 104, entity and attribute obtained based on the keyword, by the entity and the corresponding letter of attribute Breath is inserted in the presentation template, and rendering content is generated.The application is led to using the most-often used natural language of the mankind as input Cross information processing, output diversification, personalized rendering content, to meet diversification, the individual demand of user.Base below Method 100 is described in detail in attached drawing 3.
Step 101: obtaining the natural language of input;In some embodiments, step 101 can be by information acquisition module 11 It executes.
In some embodiments, the input mode of the natural language can include but is not limited to voice input and (such as send out Speech), touch input, gesture input, expression in the eyes is defeated for text input (text input can pass through hand-written, picture or other modes input) Enter (rotation of eyeball) and expression input etc..In some embodiments, user can pass through keyboard, microphone, mouse, tracking The equipment such as ball, touch tablet, camera input natural language.For example, user is by microphone input voice, " * * security share has Annual report of the limit company in net profit in 2018 ".
Step 102: the natural language of input being identified and analyzed, to extract keyword, entity and attribute;Some In embodiment, step 102 can be executed by message processing module 12.
In some embodiments, system can pass through ASR (automatic speech recognition, Automatic Speech Recognition) technology or OCR (optical character identification, Optical Character Recognition) technology are by voice shape The natural language of formula or graphic form is converted into corresponding text.In further embodiments, system can also be preset more The corresponding text of rotating manner of kind gesture or eyeball, system, can after the rotation of the gesture or eyeball that receive user To be translated into corresponding text automatically.Being converted into corresponding text can be in order to the identification of natural language.
In some embodiments, based on it is above-mentioned to text identified as a result, system can be by semantic analysis mould Type and/or sentiment classification model analyze the text after conversion, and to extract keyword, the keyword, which refers to, to be used for Express word, word or the phrase of subject content.In some embodiments, system can mention by least one of the following methods Take keyword, entity and attribute: participle and filtration treatment, training semantics recognition model, TF-IDF (term frequency- Inverse document frequency), Text Rank, Rake, Topic-Model, chi-square statistics, synonym rule, cloth Information gap etc. between your correlation rule, location rule, information gain, mutual information, probability ratio, cross entropy, class.
In some embodiments, the method that system obtains keyword, entity and attribute can also include deep learning method, Such as CNN, RNN, word2vec, char Embedding, pos Embedding, Attention etc..
In some embodiments, system can also carry out semantic cutting and activity classification to the natural language of input, described The meaning of semantic cutting are as follows: the natural language of input is divided into several independent clauses, every independent clause represents one The independent operation of kind, for example, " five classes of midterm examination mathematics achievements of the junior three are greater than 100 points, Chinese Achievement Test by natural language input Above-mentioned input is carried out semantic cutting by the list of results of first 50 all schoolgirls ", and available three independent operations are that is, " first Classmate of three or five classes of midterm examination mathematics achievements greater than 100 points ", " 50 classmates before five classes of midterm examination Chinese Achievement Tests of the junior three " And " five classes of all schoolgirls of the junior three ".The meaning of the activity classification are as follows: each of tell after aforementioned semantic cutting solely The classification of vertical operation, in the present embodiment, three independent operations are screening operation, that is, filter out and " examine in five shift of the junior three Classmate of the examination mathematics achievement greater than 100 points " filters out " 50 classmates before five classes of midterm examination Chinese Achievement Tests of the junior three " and sieves " five classes of all schoolgirls of the junior three " are selected, obtain three data sets according to above three screening conditions, in the present embodiment, three data Collection take intersection obtain this input finally screen result.It should be noted that the classification of the operation includes but is not limited to: sieve It selects, summarize, sorting, classifying, operation etc..
In some embodiments, semantic cutting can use semantic segmentation model and realize, for example, acquiring a large amount of primitive natures Sentence is inputted as sample, and for the cutting result of artificial division as label, training initial model obtains the semantic dividing die Type, in some embodiments, the semanteme segmentation model can select CNN, RNN even depth learning model, can also select CRF Algorithm (condition random field), naturally it is also possible to be the combination of CRF algorithm and deep learning model.In some embodiments, it operates Classification can use activity classification model realization, for example, using the cutting result after semantic segmentation model segments as sample This input, for the classification results of manual sort as label, training initial model obtains the activity classification model, in some realities It applies in example, the activity classification model can select text-CNN, decision tree, Markov model etc..
In some embodiments, specific operator can also be extracted after the activity classification, extracts the operator Step can carry out simultaneously with the step of extracting keyword, can also any sequencing.In some embodiments, extraction operation The method of symbol can not repeat herein with reference to the method for extracting keyword.
Step 103: being generated based on the keyword, entity and attribute and present template;In some embodiments, step 103 It can be executed by template generation module 13.
In some embodiments, the presentation template can for report type template, table class template and figure class template etc., Be also possible to two of them or more than combination, described present include at least standard area for presenting standard content in template With the white space for inserting information.For example, extracting keyword " annual report ", " 2018 " and " net profit in step 102 Profit ", system can determine that applicable template is financial report class, while can be according to financial report class mould according to the above keyword The fixed format of plate will determine that information (such as annual information) is shown in the standard area, by transverse and longitudinal coordinate name, unit It is stayed at equal positions and sets white space, remain to fill in specific entity and property content.
In some embodiments, the presentation template can be obtained from the template library constructed in advance, in some embodiments In, it can be based on deep learning model, construct the mould by the corpus pre-established or the data obtained using crawler technology Plate library.For example, establishing neural network model, the data obtained using the corpus or crawler technology that pre-establish are defeated as sample Enter, the presentation template that artificial or computer generates is as label, the training neural network model.In some embodiments, in advance The corpus first established, can be for the words such as the everyday words of specific area or proper noun (" capital " of such as financial field, " risk ", " assessment " etc.), and the data for utilizing the crawler technology to obtain, then it can be according to certain rule from internet The correlation word (such as " product ", " table ", " maximum ") of crawl, using these words as keyword with shape alone or in combination Formula inputs in neural network model, the sample input as training neural network model;In application, by all by neural network mould The presentation template of type output and the presentation template that early period is manually generated or computer generates, store into common template library, It is called for subsequent lookup.
In some embodiments, system, which can be searched based on the keyword and be matched from the template library, applicable is in Template is passed, for example, system can be according to keyword " annual report ", " 2018 " and " net profit ", in financial report class template It is middle search simultaneously match applicable presentation template, in yet other embodiments, the presentation template in the template library by industry, Field, technology or template type carry out classification storage, convenient for searching and matching.When there are multiple applicable presentation templates, it is System can be by certain regular (for example, matching degree, template creation time, template be applicable in frequency etc.) to multiple applicable presentation templates It is ranked up and numbers, and describe the feature of each applicable presentation template respectively, understand each presentation template convenient for user Difference and feature;In further embodiments, system can also recommend applicable presentation template, or pop-up template choosing to user It selects window to select for user, for example, user can manually select the presentation template for identifying oneself most suitably used, system can also pass through wheat The equipment such as gram wind, camera receive the selection instruction of user, for example, it is " 1 " that Systematic selection, which is numbered, when user says " 1 " Present template.
In some embodiments, contain nest relation if presenting in template, can also be determined by repeatedly selecting final Presentation template, wherein the nest relation refers in presentation comprising structure data, for example, " interim score of each subject list and Branch achievement pie chart " had not only included table class template (score of each subject list), but also has included figure class template (branch achievement pie chart), At this point it is possible to suitable presentation template be determined by repeatedly selecting, for example, the integral position of table and pie chart is first selected to close System, then confirm the grade classification of score of each subject, pie chart is finally drawn according to grade classification respectively.
In yet other embodiments, when that can not be searched from the template library and match applicable presentation template, for example, When the relevance grade of all presentation templates found is below preset relevance grade threshold value, system is also based on the keyword With deep learning model, corresponding presentation template is generated.For example, utilizing neural network model trained when establishing template library (referring to 68 sections) obtain the presentation mould of neural network model output using the keyword obtained in step 102 as input Plate.In addition, system can also store newly-generated presentation template into template library, user can also will be based on to the presentation The feedback of template and the presentation template modified is stored into template library, it is, of course, also possible to by the presentation template finally used by row Industry, field, technology, template type etc. are stored into template library.
Step 104: entity and attribute being obtained based on the keyword, the entity and the corresponding information of attribute are filled out Enter in the presentation template, generates rendering content;In some embodiments, step 104 can be executed by content generating module 14.
Firstly, being defined to entity, attribute, wherein entity refers to entity essence, specific things, individual main bodys, phenomenon The meanings such as supporter, meaning generally refer to the thing for capableing of bases and all things on earth basis self-existent, as all attributes. And attribute is exactly the mankind that the abstract aspect of one object is portrayed.One specific things, always there is various property With relationship, the property and relationship of a things are all called the attribute of things by we.Things is inseparable, things with attribute It is all the things for having attribute, attribute is also all the attribute of things.In this application, the entity can be used to indicate that things, general Thought, situation, state etc. can specifically include mechanism name, enterprise's name, name (for example, senior executive, shareholder, investor, partner Deng), industry, product, event, case, regulation, place name, time, currency, number, percentage etc.;The attribute is then used to indicate The corresponding data description of relationship and one or more entity between entity, can specifically include industry in mark relationship, industry Downstream relationship, stockholder's rights change history, increases between the relationship of great rearrangement of assets, multiple financial statements supply chain relationship calmly Data cross verifying, can also include such as annual revenue, net profit same period increase and decrease, total assets, total liabilities, stockholder's right Data such as beneficial total value etc..
In some embodiments, system can by Hidden Markov Model, maximum entropy model, support vector machines, be based on CNN, RNN even depth learning model, based on Boolean Association Rules, based on synonym configuration rule, based on the method for location rule The entity in the text is identified with the method for Statistics-Based Method or a combination of these methods;In other embodiment In, system can identify the category in the text by preset attributes extraction rule or trained attributes extraction model Property.
In some embodiments, system is also based on the operator extracted in step 102, targetedly extracts from Entity and attribute in right language.For example, the operator extracted is " operation ", then targetedly extract in natural language " summation " field.
In some embodiments, when the presentation template selected in step 103 is report class template, system can be according to one Set pattern then combines entity and attribute, generates the natural language sentence for industry or field, and then form report content, In the report class template that report content filling is selected again, to generate final rendering content.Particularly, system is generating After report content, algorithm can also be modified by writing style to adjust the writing style of report, comply with the report in corresponding industry or field Accuse style.The writing style modification algorithm includes: that the location information of text is exported by hidden layer in neural network model, is led to Writing style module adjustment writing writing style is crossed, achievees the effect that export personalized writing style, for example, it is directed to wisdom finance/field of finance and economics, report Accusing in content will appear the proper nouns such as financial statement, capital market, risk control.
In further embodiments, when the template selected in step 103 belongs to table class template, system can be according to one Set pattern then (for example, mapping relations between entity and entity, entity and attribute) fills out entity and the corresponding information of attribute Enter in selected table class template, to generate final rendering content.
In yet other embodiments, when the template selected in step 103 belongs to figure class template, system can be according to one Set pattern then (for example, mapping relations between entity and entity, the entity and attribute) graphing in selected figure class template, To generate final rendering content.Wherein, the contents such as the acquisition of entity and the corresponding information of attribute and corresponding information source Illustrate referring to the preceding paragraph, do not repeat herein.Certainly, the presentation template chosen in corresponding step 103 is different, ultimately generates Rendering content can be one of report, table, figure or a variety of combinations, for example, a portion is with table shape Data relationship is presented in formula, and another part describes to summarize with report form;In another example using figure description in report type rendering content The content of a portion keeps entire rendering content more intuitive, comprehensive.
In some embodiments, the entity and the corresponding information of attribute insert the presentation template and stay the blank set In region, wherein the entity and the corresponding information of attribute, which can be, to be obtained from the natural language that user inputs, It can be what system was retrieved from multiple information sources based on keyword.Wherein, multiple information sources may include the preparatory structure of system Sector database, Universal Database and the webpage built are (for example, wikipedia, Baidupedia, enterprise official website, news media's net Stand) etc..As supplement, system can also be ranked up the reliability of multiple information sources, to use the higher letter of reliability The information retrieved in breath source.It further, can be by way of remarks, footnote or link in final rendering content The information source of wherein information is traced, convenient for information in subsequent retrospect and lookup.
It in some embodiments, can when information matched in information source (including data or data acquisition system) has multiple To select multiple data or data acquisition system;It can certainly be best suitable for by natural language interaction or the selection of other exchange methods The data or data acquisition system of user demand.In further embodiments, if containing nest relation in data acquisition system, can also pass through It repeatedly selects to determine nested complex data or data acquisition system, wherein the nest relation refers in data acquisition system comprising knot Configuration data, for example, " interim score of each subject list and branch achievement pie chart ", had not only included score of each subject list, but also include each section The pie chart of each subject achievement, belongs to the complex data with nest relation in achievement, at this point it is possible to by repeatedly selecting come really Chinese Achievement Test for example, first selecting the Chinese Achievement Test in score of each subject, then is divided into several grades by fixed suitable data acquisition system, Pie chart is finally drawn according to the division of grade.
It should be noted that presenting the matching of template and/or the matching of information can show simultaneously for matching result Explanation, for example, display " the presentation template most often selected for your recommended user " or display " information that you selected last time " etc. Deng.
In some embodiments, the method can also include step 105: the rendering content of generation is showed use Family;In some embodiments, step 105 can be executed by output module 15, and certainly, which can also be by other execution Main body (such as display module etc.) executes.
In some embodiments, final rendering content can be showed user on interactive interface by system.Specifically, Final rendering content on interactive interface can be editable or can not edit version, system can will in final presentation Appearance is saved in historical record, and system can be by self defined time, type (for example, industry, field, technology, template type Deng) etc. final rendering content is inquired in historical record.Further, the natural language that system can also be inputted according to user Speech, calls and updates the rendering content in historical record.
In some embodiments, system can to modify to the pattern for presenting template, such as using natural language or Other interactive modes delete table row or column etc., increase, fractionation etc. (net profit as increased display stock);Or it repairs Change indication range, paging activity adjusts display scale, the unit of display, display order, display color, sort method, data summarization Deng, such as: greater than 0 numerical value green display, the numerical value red display less than 0, amount of increase and amount of decrease sorts from large to small, net profit With showing as unit of ten thousand yuan, the GDP of 100 Pagination Displays of every page of display, the one the second tertiary industry is shown with pie chart, and is increased Show percent project etc..Certainly, any one of the above operation can also be taken by natural language interaction or other interactive modes Disappear, such as cancels color and show.
In some embodiments, system can also be to the information (specific data or data acquisition system) inserted in presentation template It modifies, for example, increasing data item using natural language interaction or other interactive modes, deleted data item modifies data item, Increase summarizes, is averaging, the operational datas item such as Classifying Sum, increase or delete data screening mode (as: only remaining larger than 0 Data).Certainly, any one of the above operation can also be cancelled by natural language interaction or other interactive modes, such as cancel It is averaging.
In some embodiments, system can also modify to the incidence relation in rendering content, for example, utilizing nature Language interaction or other interactive modes increase the relationships of multiple tables, and (such as: pie chart shows that corresponding to the market of stock in list occupies Rate).Certainly, aforesaid operations can also be cancelled by natural language interaction or other interactive modes.
In some embodiments, above-mentioned all modifications can select visualized operation, i.e., be in for the operation of each step Preview results are passed, intuitively experiences and selects convenient for user.In some embodiments, system can also be to all operations of user It is collected and arranges with selection, based on the presentation template and information after collection and arrangement, to the matching process in abovementioned steps (such as obtaining entity and attribute based on the keyword) is learnt and is optimized, and uses after optimization in matching next time Method of completing the square improves accuracy to continuously improve matching process.
Fig. 4 is the illustrative flow chart according to some embodiments of the present application, is directed to other embodiments for illustrating The method and step based on spatial term rendering content:
Step 201: inputting natural language, include preset instruction, described instruction in the natural language of input It can be preset with letter, rotation of number, word, gesture, eyeball etc..For example, indicating starting tabulation operation, " 2 " with " 1 " Indicate setting gauge outfit, " 3 " and " 4 " indicate setting ranks number.In another example being indicated to search for established table or report with alphabetical " s " It accuses, transfers corresponding table or report with alphabetical " r " expression, indicate the table etc. that modification takes out with alphabetical " r ".The finger Order can also include table and/or title, the data item in table, the content of report of report etc..
Step 202: the natural language of input being identified and analyzed, and extracts described instruction;
Wherein it can refer to foregoing teachings about the input method of the natural language, recognition methods, analysis method etc., herein It repeats no more.The method for extracting described instruction can be with are as follows: matches the natural language of input with preset instruction.
Step 203: at least one step in the method for generating rendering content is triggered based on described instruction.
In some embodiments, system can be triggered based on instruction for the various processing of table, report or figure etc. It operates (referring to step 102~104), then inserts rendering content in corresponding table, report or figure, to generate finally Rendering content.In some embodiments, the step for, can carry out on interactive interface, that is, Preview results are presented in real time, so that Entire treatment process is visual, realization visualized operation, and after generating final rendering content, can be saved into In historical record.Other content can be found in the description in step 105.
It should be noted that instruction can be used as in other embodiments, the side based on spatial term rendering content A kind of supplement of method, such as: in a step 102, the natural language of input is identified and analyzed, to extract the same of keyword When extract instruction, certainly, described instruction need to be preset, in this way, handling a part of information using keyword, be handled using instruction Another part information, the operation that can not be identified or be difficult to such as system.
In some embodiments, the method based on spatial term rendering content further include: be in described in will generate It passs before or after content shows user, standardization processing is carried out to character express and/or numerical data.Such as it will be used to refer to The expression-form that unification or normalized number digital data are carried out for the front and back statement of same thing, for example, " three Wan Yuan " is converted into " 30000 yuan ", " reducing by 4 percent " are converted into " reducing by 4% " etc..
In some embodiments, the natural language supports multilingual input, and the rendering content supports multilingual output. In some embodiments, the rendering content of corresponding languages can be generated based on the languages of the natural language of input, naturally it is also possible to Final rendering content is switched to various other languages.
In other embodiments of the application, a kind of device based on spatial term rendering content, institute are provided Stating device includes at least one processor and at least one processor;At least one processor refers to for storing computer It enables;At least one described processor is used to execute at least partly instruction in the computer instruction to realize behaviour as described above Make.
In the other embodiment of the application, providing a kind of computer based on spatial term rendering content can Storage medium is read, the storage medium stores computer instruction, realizes when the computer instruction is executed by processor as above The operation.
It should be noted that above description, only for convenience of description, the application can not be limited in illustrated embodiment range Within.It is appreciated that for those skilled in the art, it, can be without departing substantially from this after the principle for understanding the application In the case where principle, to the various modifications and variations of progress in form and details such as the implementation above method, devices.However, these Change and modification do not depart from scope of the present application.
Fig. 5 is the module of the system based on spatial term rendering content according to other embodiments of the application Figure.The system 20 includes: information acquisition module 21, natural language for receiving input;Information sending module 22, is used for The natural language is sent to server-side;Information receiving module 23, the rendering content returned for receiving the server-side;It is defeated Module 24 out, for showing the rendering content.
It should be appreciated that system shown in fig. 5 and its module can use various modes to realize.For example, in some implementations In example, system and its module can be realized by the combination of hardware, software or software and hardware.Wherein, hardware components can To be realized using special logic;Software section then can store in memory, by instruction execution system appropriate, for example (,) it is micro- Processor or special designs hardware execute.It will be appreciated by those skilled in the art that meter can be used in above-mentioned method and system It calculation machine executable instruction and/or is included in the processor control code to realize, such as in such as disk, CD or DVD-ROM The programmable memory of mounting medium, such as read-only memory (firmware) or the data of such as optics or electrical signal carrier Such code is provided on carrier.The system and its module of the application can not only have such as super large-scale integration or door The semiconductor or field programmable gate array of array, logic chip, transistor etc., programmable logic device etc. The hardware circuit of programmable hardware device realize, can also be real with such as software as performed by various types of processors It is existing, it can also be by combination (for example, firmware) Lai Shixian of above-mentioned hardware circuit and software.
In another embodiment of the application, a kind of method based on spatial term rendering content is provided, it is described Method can be executed by the user terminal 130 in system 100, which comprises
Step 301: obtaining the natural language of input, in some embodiments, which can be by the information collection mould Block 21 executes.
In some embodiments, the input mode of the natural language can include but is not limited to voice input and (such as send out Speech), touch input, gesture input, text input (text input can pass through hand-written, picture or other modes input), expression in the eyes Input (rotation of eyeball) and expression input etc..In some embodiments, user can by keyboard, microphone, mouse, with The equipment such as track ball, touch tablet, camera input natural language.For example, user passes through microphone input voice " * * security share Annual report of the Co., Ltd in net profit in 2018 ".
Step 302: the natural language being sent to server-side, in some embodiments, which can be by the letter Sending module 22 is ceased to execute.
Step 303: receiving the rendering content that the server-side returns;The rendering content includes server-side based on described defeated The presentation template and server-side that the natural language entered determines are each based on the determining entity of the natural language of the input and attribute Self-corresponding information, in some embodiments, the step can be executed by the information receiving module 23.
In some embodiments, server-side can realize the information/data between user terminal 130 via network 120 Transmitting.
Step 304: showing the rendering content, in some embodiments, which can be held by the output module 24 Row.
In some embodiments, the rendering content may include presenting template and filling in the presentation template Entity and the corresponding information of attribute.In some embodiments, in the rendering content, can by remarks, footnote or The form of link traces the information source of wherein information, lookup, audit and retrospect convenient for user to information.
In some embodiments, the rendering content includes at least one of report, table, figure, for example, in response to The presentation template of selection is different, and the rendering content ultimately generated may include diversified forms, also may include multiple portions, example Such as: a portion is that data relationship is presented in a tabular form, and another part describes to summarize with report form;In another example report In class rendering content, with the content of figure description a portion, keep entire rendering content more intuitive, comprehensive.
It should be noted that the definition about entity, attribute, searches the concrete mode that matching presents template, information and letter The contents such as the concrete form of the definition in breath source and source and rendering content may refer to description above, and it will not go into details herein.
In some embodiments, the method based on spatial term rendering content further includes that user terminal 130 receives clothes At least one that end returns of being engaged in presents template for selection by the user;It receives the selection of user and sends it to server-side, change sentence It talks about, it can be with before server-side returns to final rendering content to user terminal 130, between user terminal 130 and server-side It is accomplished in several ways primary or multiple information exchange, until obtaining customer satisfaction system rendering content.
In some embodiments, user can be by retouching the feature for presenting template on the display interface of user terminal 130 The characteristics of stating, understanding each presentation template, further according to the demand of oneself, the presentation template for selecting server-side to provide;In some realities Apply in example, user is also based on the template selection window popped up on the display interface of user terminal 130, select most suitably used be in Pass template.In some embodiments, user can also be repaired by the presentation template that user terminal 130 provides server-side Change.
In other embodiments of the application, a kind of device based on spatial term rendering content, institute are provided Stating device includes at least one processor and at least one processor;At least one processor refers to for storing computer It enables;At least one described processor is used to execute at least partly instruction in the computer instruction to realize behaviour as described above Make.
In the other embodiment of the application, providing a kind of computer based on spatial term rendering content can Storage medium is read, the storage medium stores computer instruction, realizes when the computer instruction is executed by processor as above The operation.
It should be noted that above description, only for convenience of description, the application can not be limited in illustrated embodiment range Within.It is appreciated that for those skilled in the art, it, can be without departing substantially from this after the principle for understanding the application In the case where principle, to the various modifications and variations of progress in form and details such as the implementation above method, system, devices.However, These change and modification do not depart from scope of the present application.
Compared with prior art, the possible beneficial effect of the application the above various embodiments includes but is not limited to:
1, it using the most-often used natural language of the mankind as input, by information processing, exports in diversified presentation Hold, to meet the diversified demand of user;
2, the application can meet the individual demand of user with the concrete form and content of customized rendering content;
3, the application can be directed to industry characteristic, and the rendering content of generation is targetedly handled or adjusted, is made It meets the characteristics of corresponding industry or field, so that the application be made to be applied to a variety of different fields.
It should be noted that the different issuable beneficial effects of embodiment are different, in different embodiments, may produce Raw beneficial effect can be the combination of any of the above one or more, be also possible to other it is any can it is obtainable beneficial to effect Fruit.
The above content describes the application and/or some other examples.According to above content, the application can also be made Different deformations.Herein disclosed theme can be realized with example in different forms, and the application can be applied In a large amount of application program.All applications, modification and change claimed in claim belong to this Shen hereinafter Range please.
Meanwhile the application has used particular words to describe embodiments herein.Such as " one embodiment ", " one implements Example ", and/or " some embodiments " mean a certain feature relevant at least one embodiment of the application, structure or feature.Cause This, it should be highlighted that and it is noted that " embodiment " or " a reality referred to twice or repeatedly in this specification in different location Apply example " or " alternate embodiment " be not necessarily meant to refer to the same embodiment.In addition, one or more embodiments of the application In certain features, structure or feature can carry out combination appropriate.
It will be appreciated by those skilled in the art that a variety of variations and modifications can occur in content disclosed herein.For example, Different system components described above are all to be realized by hardware device, but may also only pass through the solution party of software Case is achieved.Such as: the installation system on existing server.In addition, the offer of location information described herein may It is to be achieved by a firmware, the combination of firmware/software, the combination of firmware/hardware or the combination of hardware/firmware/software.
All softwares or in which a part there may come a time when to be communicated by network, such as internet or other communication networks Network.Software can be loaded into another from a computer equipment or processor by such communication.Such as: from radiotherapy system A management server or host computer be loaded onto a computer environment hardware platform or other realize systems meter Calculation machine environment, or the system of similar functions relevant to information required for determining wheelchair object construction parameter is provided.Therefore, separately A kind of medium that can transmit software element is also used as the physical connection between local devices, such as light wave, electric wave, electricity Magnetic wave etc. is realized by cable, optical cable or air and is propagated.For physical medium such as cable, wireless connection or the optical cable of carrier wave Equal similar devices, are also considered the medium of carrying software.Usage herein is situated between unless limiting tangible " storage " Matter, other indicate that the term of computer or machine " readable medium " all indicates to participate in during processor executes any instruction Medium.
Computer program code needed for the operation of the application each section can use any one or more programming language, Including Object-Oriented Programming Language such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C++, C#, VB.NET, Python etc., conventional procedural programming language for example C language, Visual Basic, 2003 Fortran, Perl, COBOL 2002, PHP, ABAP, dynamic programming language such as Python, Ruby and Groovy or other programming languages etc..The program coding can be complete Entirely on the user computer run run on the user computer as independent software package or partially in subscriber computer Upper operation part runs in remote computer or runs on a remote computer or server completely.In the latter cases, remotely Computer can be connect by any latticed form with subscriber computer, for example, local area network (LAN) or wide area network (WAN) or company It is connected to outer computer (such as passing through internet) or is serviced in cloud computing environment or as service using such as software (SaaS)。
In addition, except clearly stating in non-claimed, the sequence of herein described processing element and sequence, digital alphabet Using or other titles use, be not intended to limit the sequence of the application process and method.Although by each in above-mentioned disclosure Kind of example discuss it is some it is now recognized that useful inventive embodiments, but it is to be understood that, such details only plays explanation Purpose, appended claims are not limited in the embodiment disclosed, on the contrary, claim is intended to cover and all meets the application The amendment and equivalent combinations of embodiment spirit and scope.For example, although system component described above can be set by hardware It is standby to realize, but can also be only achieved by the solution of software, such as pacify on existing server or mobile device Fill described system.
Similarly, it is noted that in order to simplify herein disclosed statement, to help real to one or more invention Apply the understanding of example, above in the description of the embodiment of the present application, sometimes by various features merger to one embodiment, attached drawing or In descriptions thereof.But this disclosure method is not meant to mention in aspect ratio claim required for the application object And feature it is more.In fact, the feature of embodiment will be less than whole features of the single embodiment of above-mentioned disclosure.
The number of description attribute, quantity is used in some embodiments, it should be appreciated that such to describe for embodiment Number, used qualifier " about ", " approximation " or " generally " to modify in some instances.Unless otherwise stated, " big About ", " approximation " or " generally " show the variation that the number allows to have ± 20%.Correspondingly, in some embodiments, explanation Numerical parameter used in book and claim is approximation, and approximation feature according to needed for separate embodiment can occur Change.In some embodiments, the method that numerical parameter is considered as defined significant digit and is retained using general digit.Although Numerical Range and parameter in some embodiments of the application for confirming its range range are approximation, in a particular embodiment, this Being set in for class numerical value is reported as precisely as possible in feasible region.
For each patent, patent application, patent application publication object and the other materials of the application reference, such as article, book Entire contents are incorporated herein as reference by nationality, specification, publication, document, object etc., spy.Not with teachings herein Except application history file that is consistent or generating conflict, to the conditional file of the claim of this application widest scope (it is current or Be additional in the application later) also except.It should be noted that if description in the application attaching material, definition and/ Or the use of term with it is herein described it is interior have place that is inconsistent or conflicting, with the description of the present application, definition and/or term Use subject to.
Finally, it will be understood that embodiment described herein is only to illustrate the principle of the embodiment of the present application.Other Deformation may also belong to scope of the present application.Therefore, as an example, not a limit, the alternative configuration of the embodiment of the present application is visual It is consistent with teachings of the present application.Correspondingly, embodiments herein is not limited to the embodiment that the application is clearly introduced and described.

Claims (18)

1. a kind of method based on spatial term rendering content, the method are realized by least one processor, feature It is, which comprises
Obtain the natural language of input;
The natural language of input is identified and analyzed, to extract keyword;
It is generated based on the keyword and presents template;
Entity and attribute are obtained based on the keyword, the entity and the corresponding information of attribute are inserted into the presentation mould In plate, rendering content is generated.
2. the method according to claim 1, wherein the presentation template includes report class template, table class mould At least one of plate and figure class template.
3. method according to claim 1 or 2, which is characterized in that the rendering content is including in report, table, figure At least one.
4. the method according to claim 1, wherein described generate the method for presenting template based on the keyword Further include: recommend applicable presentation template, or pop-up template selection window to select for user to user.
5. the method according to claim 1, wherein the presentation template is included at least for presenting standard content Standard area and white space for inserting information.
6. the method according to claim 1, wherein the side for obtaining entity and attribute based on the keyword Method includes: to retrieve to obtain the entity and attribute from information source based on the keyword, wherein the information source includes preparatory Sector database, Universal Database and the webpage of building.
7. according to the method described in claim 6, it is characterized in that, passing through remarks, footnote or link in the rendering content Form retrospect wherein information the information source.
8. the method according to claim 1, wherein the input mode of the natural language include voice input, Touch input, gesture input, text input, expression in the eyes input and expression input.
9. a kind of system based on spatial term rendering content characterized by comprising
Information acquisition module, natural language for receiving input;
Message processing module, for the natural language of input to be identified and analyzed, to extract keyword;
Template generation module is generated based on the keyword and presents template;
Content generating module obtains entity and attribute based on the keyword, by the entity and the corresponding information of attribute It inserts in the presentation template, generates rendering content.
10. a kind of device for presenting file based on spatial term, which is characterized in that described device includes at least one processing Device and at least one processor;
At least one processor is for storing computer instruction;
At least one described processor is used to execute at least partly instruction in the computer instruction to realize such as claim 1 To operation described in any one of 8.
11. a kind of computer readable storage medium based on spatial term rendering content, which is characterized in that the storage is situated between Matter stores computer instruction, realizes when the computer instruction is executed by processor such as any one of claim 1 to 8 institute The operation stated.
12. a kind of method based on spatial term rendering content characterized by comprising
Obtain the natural language of input;
The natural language is sent to server-side;
Receive the rendering content that the server-side returns;The rendering content includes natural language of the server-side based on the input Determining presentation template and server-side is based on the determining entity of the natural language of the input and the corresponding information of attribute;
Show the rendering content.
13. according to the method for claim 12, which is characterized in that further include: receiving at least one that server-side returns is in Pass template for selection by the user;
It receives the selection of user and sends it to server-side.
14. according to the method for claim 12, which is characterized in that in the rendering content, pass through remarks, footnote or chain The form connect traces the information source of wherein information.
15. according to the method for claim 12, which is characterized in that the rendering content includes report, table, in figure It is at least one.
16. a kind of system based on spatial term rendering content characterized by comprising
Information acquisition module, natural language for receiving input;
Information sending module, for the natural language to be sent to server-side;
Information receiving module, the rendering content returned for receiving the server-side;The rendering content includes that server-side is based on The entity that the presentations template and server-side that the natural language of the input determines are determined based on the natural language of the input with The corresponding information of attribute;
Output module, for showing the rendering content.
17. a kind of device based on spatial term rendering content, which is characterized in that described device includes at least one processing Device and at least one processor;
At least one processor is for storing computer instruction;
At least one described processor is used to execute at least partly instruction in the computer instruction to realize such as claim Operation described in any one of 12 to 15.
18. a kind of computer readable storage medium based on spatial term rendering content, which is characterized in that the storage is situated between Matter stores computer instruction, realizes when the computer instruction is executed by processor such as any one of claim 12 to 15 The operation.
CN201910718769.XA 2019-08-05 2019-08-05 System and method based on spatial term rendering content Pending CN110413767A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910718769.XA CN110413767A (en) 2019-08-05 2019-08-05 System and method based on spatial term rendering content

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910718769.XA CN110413767A (en) 2019-08-05 2019-08-05 System and method based on spatial term rendering content

Publications (1)

Publication Number Publication Date
CN110413767A true CN110413767A (en) 2019-11-05

Family

ID=68366061

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910718769.XA Pending CN110413767A (en) 2019-08-05 2019-08-05 System and method based on spatial term rendering content

Country Status (1)

Country Link
CN (1) CN110413767A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111158490A (en) * 2019-12-31 2020-05-15 重庆百事得大牛机器人有限公司 Auxiliary semantic recognition system based on gesture recognition
CN112270166A (en) * 2020-10-26 2021-01-26 摩森特(北京)科技有限公司 Method for quickly making and creating 5G message
TWI793432B (en) * 2020-08-07 2023-02-21 國立中央大學 Document management method and system for engineering project
CN116779109A (en) * 2023-05-24 2023-09-19 纬英(广州)教育科技有限公司 Self-feature discovery method and device based on exploration scene guidance

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1670733A (en) * 2004-03-18 2005-09-21 微软公司 Rendering tables with natural language commands
US20180011838A1 (en) * 2016-07-07 2018-01-11 International Business Machines Corporation Generating Semantic Variants of Natural Language Expressions Using Type-Specific Templates
CN108132933A (en) * 2017-12-28 2018-06-08 中译语通科技(青岛)有限公司 A kind of generation method across language analysis report
CN108509412A (en) * 2018-03-02 2018-09-07 北京搜狗科技发展有限公司 A kind of data processing method, device, electronic equipment and storage medium

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1670733A (en) * 2004-03-18 2005-09-21 微软公司 Rendering tables with natural language commands
US20180011838A1 (en) * 2016-07-07 2018-01-11 International Business Machines Corporation Generating Semantic Variants of Natural Language Expressions Using Type-Specific Templates
CN108132933A (en) * 2017-12-28 2018-06-08 中译语通科技(青岛)有限公司 A kind of generation method across language analysis report
CN108509412A (en) * 2018-03-02 2018-09-07 北京搜狗科技发展有限公司 A kind of data processing method, device, electronic equipment and storage medium

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111158490A (en) * 2019-12-31 2020-05-15 重庆百事得大牛机器人有限公司 Auxiliary semantic recognition system based on gesture recognition
TWI793432B (en) * 2020-08-07 2023-02-21 國立中央大學 Document management method and system for engineering project
CN112270166A (en) * 2020-10-26 2021-01-26 摩森特(北京)科技有限公司 Method for quickly making and creating 5G message
CN116779109A (en) * 2023-05-24 2023-09-19 纬英(广州)教育科技有限公司 Self-feature discovery method and device based on exploration scene guidance
CN116779109B (en) * 2023-05-24 2024-04-02 纬英数字科技(广州)有限公司 Self-feature discovery method and device based on exploration scene guidance

Similar Documents

Publication Publication Date Title
US20230351102A1 (en) Machine content generation
Narechania et al. NL4DV: A toolkit for generating analytic specifications for data visualization from natural language queries
US11714839B2 (en) Apparatus and method for automated and assisted patent claim mapping and expense planning
Pawar et al. Calculating the similarity between words and sentences using a lexical database and corpus statistics
CN110413767A (en) System and method based on spatial term rendering content
CN111177569A (en) Recommendation processing method, device and equipment based on artificial intelligence
WO2019245578A1 (en) Multi-modal virtual experiences of distributed content
Puri et al. Blockchain propels tourism industry—an attempt to explore topics and information in smart tourism management through text mining and machine learning
CN109154945A (en) New connection based on data attribute is recommended
CN110083645A (en) A kind of system and method for report generation
CN109325115A (en) A kind of role analysis method and analysis system
CN108108215A (en) Skin generation method, device, terminal and computer readable storage medium
US20230418572A1 (en) Learning To Personalize User Interfaces
Li [Retracted] Intelligent Environmental Art Design Combining Big Data and Artificial Intelligence
Alves et al. Exploring how personality models information visualization preferences
KR102132931B1 (en) System and method for customized value information retrieval and social network configuration
US11270070B1 (en) Method and apparatus for improved presentation of information
US11842147B1 (en) Method and apparatus for improved presentation of information
US11645352B1 (en) Method and apparatus for improved presentation of information
Moritz et al. Strategic modelling of web information systems
Quan et al. Protection of Guizhou Miao batik culture based on knowledge graph and deep learning
CN117609483A (en) Content generation method, electronic equipment and storage medium
CN115408611A (en) Menu recommendation method and device, computer equipment and storage medium
Fawcett The cultural classification of ‘things’
Reitmaier et al. Cultivating Spoken Language Technologies for Unwritten Languages

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20191105

RJ01 Rejection of invention patent application after publication