CN113722470A - Information prompting method, device, equipment and storage medium - Google Patents
Information prompting method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN113722470A CN113722470A CN202111037874.0A CN202111037874A CN113722470A CN 113722470 A CN113722470 A CN 113722470A CN 202111037874 A CN202111037874 A CN 202111037874A CN 113722470 A CN113722470 A CN 113722470A
- Authority
- CN
- China
- Prior art keywords
- current
- text
- word frequency
- word
- offline
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000004364 calculation method Methods 0.000 claims abstract description 83
- 230000011218 segmentation Effects 0.000 claims abstract description 52
- 238000012545 processing Methods 0.000 claims abstract description 30
- 238000012216 screening Methods 0.000 claims abstract description 17
- 238000004590 computer program Methods 0.000 claims description 11
- 238000001914 filtration Methods 0.000 claims description 9
- 230000015654 memory Effects 0.000 claims description 9
- 238000004458 analytical method Methods 0.000 claims description 6
- 230000008859 change Effects 0.000 abstract description 5
- 230000006870 function Effects 0.000 description 12
- 230000008569 process Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 230000036632 reaction speed Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000012937 correction Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 230000002085 persistent effect Effects 0.000 description 2
- 238000012805 post-processing Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
- 230000007704 transition 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
- G06F16/338—Presentation of query results
-
- 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
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/253—Grammatical analysis; Style critique
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- 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
Abstract
The application discloses an information prompting method, an information prompting device, information prompting equipment and a storage medium, wherein the information prompting method comprises the following steps: acquiring a current input text, and performing word segmentation processing on the current input text to obtain a word segmented current text; performing online incremental calculation on the current offline word frequency by using the segmented current text to obtain the current online word frequency, and determining a target prompt corresponding to the current input text according to the current online word frequency; the current offline word frequency is obtained by performing offline calculation on a historical input text; and screening the target prompt words based on a preset rule representing an input habit and outputting the screened target prompt words. The method and the device have the advantages that online calculation and offline calculation are matched with each other, scene change is quickly responded, the problems that the calculation speed is low, prompting is not intelligent enough, the use is difficult across scenes and the like are solved, meanwhile, the prompting words with the highest relevance degree with the current input text are screened out through learning input habits of users, and the information prompting accuracy is improved.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to an information prompting method, apparatus, device, and storage medium.
Background
With the rapid development of artificial intelligence technology, large software or systems need to be more intelligent and humanized so as to improve the user viscosity. The intelligent prompting of the user input information belongs to an important branch of the technology, a formed prompting language integration function is not available in the market at present, software of each party is realized independently, the source is basically not opened, the prompting function is difficult to use in other industries or scenes, and the prompting is basically based on off-line calculation. And on one hand, because an online learning process is lacked, the cross-scene use capability is not available, the reaction speed is low, and flexible prompt cannot be input according to a user. On the other hand, the prompting result has no post-processing due to no prompting correction capability, namely no user habit acquisition, and the prompting is not accurate enough due to the simple dependence on the weight. In addition, the way of prompting the user that the habit of the user is not satisfied is performed through an objective rule, and the user behavior is corrected on the basis of the objective rule to prompt the user to want.
Therefore, how to improve the accuracy and the calculation efficiency of information prompting and simultaneously realize intelligent and cross-scene information prompting is a technical problem to be solved urgently by those skilled in the art.
Disclosure of Invention
In view of the above, the present invention provides an information prompting method, apparatus, device and storage medium, which can improve the accuracy and computational efficiency of information prompting and simultaneously achieve intelligent and cross-scene information prompting. The specific scheme is as follows:
a first aspect of the present application provides an information prompting method, including:
acquiring a current input text, and performing word segmentation processing on the current input text to obtain a word segmented current text;
performing online incremental calculation on the current offline word frequency by using the segmented current text to obtain the current online word frequency, and determining a target prompt corresponding to the current input text according to the current online word frequency; the current offline word frequency is obtained by performing offline calculation on a historical input text;
and screening the target prompt words based on a preset rule representing an input habit and outputting the screened target prompt words.
Optionally, the information prompting method further includes:
obtaining a historical input text, and performing word segmentation processing on the historical input text to obtain a word segmented historical text;
and utilizing a calculator to perform offline calculation on the segmented historical text to obtain the current offline word frequency, and storing the current offline word frequency in a database.
Optionally, the performing word segmentation processing on the current input text to obtain a segmented current text includes:
performing word segmentation processing on the current input text by using a word segmentation device to obtain a current text after word segmentation;
and filtering the segmented current text by using a filter to obtain the filtered segmented current text.
Optionally, the performing online incremental computation on the current offline word frequency by using the segmented current text to obtain the current online word frequency includes:
acquiring current offline word frequency from a database, and performing online incremental calculation on the current offline word frequency by using the segmented current text to obtain the current online word frequency;
and updating the current offline word frequency in the database by using the current online word frequency to obtain the real-time current offline word frequency.
Optionally, the determining, according to the current online word frequency, a target prompt corresponding to the current input text includes:
determining a target scene corresponding to the current input text according to the input text of preset time before the current time, and determining words corresponding to the target scene from a word list corresponding to the current online word frequency to obtain a target prompt.
Optionally, the filtering the target prompt based on a preset rule characterizing an input habit and outputting the filtered target prompt includes:
determining a preset rule based on a representation input habit by carrying out syntactic analysis on the historical input text;
and screening the target prompt words based on preset rules representing input habits and theoretical grammar rules and outputting the screened target prompt words.
Optionally, the information prompting method further includes:
carrying out corresponding configuration on a word segmentation device for carrying out word segmentation processing and a calculator for carrying out word frequency calculation according to target requirements;
and performing word segmentation operation and word frequency calculation operation through the configured word segmenter and the configured component interface of the calculator.
A second aspect of the present application provides an information presentation apparatus, including:
the acquisition module is used for acquiring a current input text and performing word segmentation processing on the current input text to obtain a word segmented current text;
the calculation module is used for performing online incremental calculation on the current offline word frequency by using the segmented current text to obtain the current online word frequency and determining a target prompt corresponding to the current input text according to the current online word frequency; the current offline word frequency is obtained by performing offline calculation on a historical input text;
and the screening module is used for screening the target prompt words based on a preset rule representing an input habit and outputting the screened target prompt words.
A third aspect of the application provides an electronic device comprising a processor and a memory; wherein the memory is used for storing a computer program which is loaded and executed by the processor to implement the aforementioned information prompting method.
A fourth aspect of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored, and when the computer-executable instructions are loaded and executed by a processor, the information prompting method is implemented.
In the method, a current input text is obtained first, word segmentation processing is carried out on the current input text to obtain a word segmented current text; then, performing online incremental calculation on the current offline word frequency by using the segmented current text to obtain the current online word frequency, and determining a target prompt corresponding to the current input text according to the current online word frequency; the current offline word frequency is obtained by performing offline calculation on a historical input text; and finally, screening the target prompt words based on a preset rule representing an input habit and outputting the screened target prompt words. Therefore, the method and the device have the advantages that the current online word frequency is obtained by performing online incremental calculation on the current offline word frequency on the basis of word segmentation processing on the current input text so as to determine the target prompt words corresponding to the current input text, the online calculation and the offline calculation are matched with each other, scene change is quickly responded, and the problems of low calculation speed, insufficient intelligence in prompt, difficult cross-scene use and the like are solved. And meanwhile, the prompt words are screened based on a preset rule representing the input habit, the prompt words with the highest relevance with the current input text are screened out by learning the input habit of the user, and the information prompting accuracy is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a flowchart of an information prompting method provided in the present application;
fig. 2 is a schematic diagram of a specific information prompting method provided in the present application;
FIG. 3 is a diagram illustrating a selection of a particular segmenter provided herein;
fig. 4 is a schematic structural diagram of an information prompt apparatus provided in the present application;
fig. 5 is a structural diagram of an information prompting electronic device provided in the present application.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
At present, no formed prompt language integration function exists in the market, software of each part has respective realization and basically does not open the source, the prompt function is difficult to use in other industries or scenes, and basically prompts are based on off-line calculation. And on one hand, because an online learning process is lacked, the cross-scene use capability is not available, the reaction speed is low, and flexible prompt cannot be input according to a user. On the other hand, the prompting result has no post-processing due to no prompting correction capability, namely no user habit acquisition, and the prompting is not accurate enough due to the simple dependence on the weight. Aiming at the technical defects, the information prompting scheme is provided, online calculation and offline calculation are matched with each other, scene change is quickly responded, the problems that the calculation speed is low, prompting is not intelligent enough, the use is difficult across scenes and the like are solved, meanwhile, the prompting words with the highest relevance degree with the current input text are screened out through learning the input habits of users, and the information prompting accuracy is improved.
Fig. 1 is a flowchart of an information prompting method according to an embodiment of the present application. Referring to fig. 1, the information prompting method includes:
s11: the method comprises the steps of obtaining a current input text, and carrying out word segmentation processing on the current input text to obtain a word segmented current text.
In this embodiment, a current input text is obtained, and word segmentation processing is performed on the current input text to obtain a word-segmented current text. In order to improve the accuracy of the final prompt message, on the basis of utilizing a word segmentation device to perform word segmentation processing on the current input text to obtain a current text after word segmentation, a filter can be utilized to filter the current text after word segmentation to obtain the filtered current text after word segmentation. The word segmenter can segment a segment of text or an article into a stack of word segments according to part of speech (rank, adverb, adjective, verb, subject, predicate, etc.) and grammar, and the filter is used for ignoring the output and semantic analysis of some words. The word segmentation device and the filter can be correspondingly configured according to target requirements, so that word segmentation operation and filtering operation can be performed through the configured word segmentation device and the configured component interface of the filter.
The embodiment combines online calculation and offline calculation, adopts two-line processing, and solves the problem of low calculation speed. For the offline part, a flow of 'storage → word segmenter → filter → calculator → cache → storage' is adopted, and specifically comprises document word segmentation, word frequency offline calculation, persistent storage, storage cache and the like. And aiming at the online part, adopting a flow of 'input → word segmenter → calculator → filter → prompter → prompting', and specifically comprising online word frequency calculation, persistent storage loading to cache and the like. The method adopts a flow differentiation and flow combination mode, solves the pain point that the prompt language program can only adapt to certain industries and can not learn online, and is particularly shown in figure 2. On one hand, the prediction capability of the whole system is improved according to the existing document offline learning, and on the other hand, the prediction capability is awakened through an online process during real-time input, and meanwhile, the real-time input is updated to a database for incremental calculation.
For the offline part, in this embodiment, a historical input text needs to be obtained in advance, word segmentation processing is performed on the historical input text to obtain a post-word segmentation historical text, then, a calculator is used to perform offline calculation on the post-word segmentation historical text to obtain the current offline word frequency, and the current offline word frequency is stored in a database. Namely, the current offline word frequency is persisted, the calculated word frequency is stored, and the statistical intermediate result is cached and used as incremental calculation. The intermediate results include the total number of words, the total number of times a word last occurred, and the number of times a word occurred in a particular grammar. In addition, the calculator is a tool for processing word segments, is mainly used for calculating the occurrence frequency of words, and similarly, the calculator can be correspondingly configured according to target requirements so as to perform word frequency calculation operation through a configured component interface of the calculator.
S12: performing online incremental calculation on the current offline word frequency by using the segmented current text to obtain the current online word frequency, and determining a target prompt corresponding to the current input text according to the current online word frequency; and the current offline word frequency is obtained by performing offline calculation on the historical input text.
In the embodiment, online incremental calculation is performed on the current offline word frequency by using the segmented current text to obtain the current online word frequency, and a target prompt corresponding to the current input text is determined according to the current online word frequency; and the current offline word frequency is obtained by performing offline calculation on the historical input text. The process of acquiring the current offline word frequency is consistent with the description in the above steps, and is not described again here. The increment calculation is to calculate a new scene quickly by combining the intermediate result according to the newly added data. The specific process comprises the steps of obtaining current offline word frequency from a database, carrying out online incremental calculation on the current offline word frequency by using the segmented current text to obtain the current online word frequency, and updating the current offline word frequency in the database by using the current online word frequency on the basis of the current online word frequency to obtain the real-time current offline word frequency so that the basis of the next calculation is all input texts before. It can be understood that the online calculation is also a real-time calculation, the offline calculation is to calculate the previous word frequency and the like at regular time, for example, 0 point every day or every week, the previous data is calculated and processed by using the previous data, the online calculation is to combine the data after the previous calculation once every time the inputs are combined, the result of the online calculation is affected, and when the prompt is selected, the real-time accuracy and timeliness of the response can be better improved by combining the online weight and the offline weight.
On the basis, a target scene corresponding to the current input text is determined according to the input text of preset time before the current time, and words corresponding to the target scene are determined from a word list corresponding to the current online word frequency, so that a target prompt is obtained. And finding a word list needing prompting according to the prefix, carrying out filtering conversion based on the user behavior, the word weight and the built-in rule, and correcting a return result. The target scene is determined by internal rule matching, at the moment, a program has a set of rules, a locally optimal rule matching mode is selected, and the rules are dynamically switched according to real-time input of a user. For example, the vocabulary entered by the user is internet oriented, and when the program determines that the user is likely to be associated with the type within a short time after entering several keywords, the type weight should be increased. When the input words are converted to real estate, the weight of real estate words in the word stock is increased.
S13: and screening the target prompt words based on a preset rule representing an input habit and outputting the screened target prompt words.
In this embodiment, the target prompt is filtered based on a preset rule representing an input habit, and the filtered target prompt is output. The preset rules based on the characteristic input habits can be determined by carrying out grammatical analysis on the historical input texts, namely the preset rules cluster the user common sentence pattern rules by adopting a form of user input grammar collection to cover built-in objective rules, and the usability of the prompt words is improved. Meanwhile, the correction accuracy can be improved by using the theoretical grammar rule as a screening condition, namely, the target prompt is screened based on the preset rule representing the input habit and the theoretical grammar rule and the screened target prompt is output.
It should be clear that the word segmenter, the calculator and the filter in the above embodiments may be configured to switch between different implementations, for example, the word segmenter shown in fig. 3 may be selected. And switching different calculators to execute different weighting operations according to different items. Meanwhile, the expansibility is improved in a component interface mode, so that different word segmenters, calculators and filters are replaced in different scenes, and multi-scene adaptive use is completed. For example, the user a uses the hint function in this embodiment, and if the user needs to enhance the calculator function and increase the analysis speed, the user a can customize a calculator according to the provided criteria and replace the calculator into the program in this embodiment; the user B uses the prompt language function in this embodiment, and if the user needs to enhance the filter function, the user can customize a filter according to the provided criteria and replace the filter with the program in this embodiment; the user C uses the cue language function in this embodiment, and if the user needs to enhance the function of the word segmenter, the accuracy of the analysis of the part of speech is improved, and the user C can customize a word segmenter according to the provided standard and replace the word segmenter into the program of this embodiment. The embodiment can provide a standard and set corresponding default configuration in a matched manner to realize basic functions, if a user needs to replace a certain component, the user can realize the replacement according to the standard, and the prompt words are used in multiple scenes by component division and combination.
Aiming at the problems of no on-line calculation function and low reaction speed, the embodiment utilizes off-line calculation and combines on-line calculation to quickly cope with scene changes, so that the reaction speed is improved; aiming at the problem that prompting is not accurate enough due to the fact that users do not have habit to collect and only rely on weights, the method and the device improve prompting accuracy through calculation and filtering by means of combining the weights with objective rules and learned user input rules; for the non-cross-scene use capability, the method improves the expansibility by flow cutting and flow assembly, and configures different types of filters, calculators and memories in different scenes to realize multi-scene flexible transition. In summary, the embodiment improves the ability of quick decision making by matching online with offline, and the expansibility reserved for each process facilitates using the prediction model in each industry and each industry, and corrects the weight of the prompt result by learning the input of the user.
Therefore, the method comprises the steps of obtaining a current input text, and performing word segmentation processing on the current input text to obtain a word segmented current text; then, performing online incremental calculation on the current offline word frequency by using the segmented current text to obtain the current online word frequency, and determining a target prompt corresponding to the current input text according to the current online word frequency; the current offline word frequency is obtained by performing offline calculation on a historical input text; and finally, screening the target prompt words based on a preset rule representing an input habit and outputting the screened target prompt words. According to the method and the device, on the basis of word segmentation processing of the current input text, online incremental calculation is carried out on the current offline word frequency to obtain the current online word frequency, so that a target prompt word corresponding to the current input text is determined, online calculation and offline calculation are matched with each other, scene change is responded quickly, and the problems of low calculation speed, insufficient intelligence in prompt, difficulty in use across scenes and the like are solved. And meanwhile, the prompt words are screened based on a preset rule representing the input habit, the prompt words with the highest relevance with the current input text are screened out by learning the input habit of the user, and the information prompting accuracy is improved.
Referring to fig. 4, an embodiment of the present application further discloses an information prompting device, which includes:
the acquiring module 11 is configured to acquire a current input text, and perform word segmentation processing on the current input text to obtain a current text after word segmentation;
the calculation module 12 is configured to perform online incremental calculation on a current offline word frequency by using the segmented current text to obtain a current online word frequency, and determine a target prompt corresponding to the current input text according to the current online word frequency; the current offline word frequency is obtained by performing offline calculation on a historical input text;
and the screening module 13 is configured to screen the target prompt based on a preset rule representing an input habit and output the screened target prompt.
Therefore, the method comprises the steps of obtaining a current input text, and performing word segmentation processing on the current input text to obtain a word segmented current text; then, performing online incremental calculation on the current offline word frequency by using the segmented current text to obtain the current online word frequency, and determining a target prompt corresponding to the current input text according to the current online word frequency; the current offline word frequency is obtained by performing offline calculation on a historical input text; and finally, screening the target prompt words based on a preset rule representing an input habit and outputting the screened target prompt words. According to the method and the device, on the basis of word segmentation processing of the current input text, online incremental calculation is carried out on the current offline word frequency to obtain the current online word frequency, so that a target prompt word corresponding to the current input text is determined, online calculation and offline calculation are matched with each other, scene change is responded quickly, and the problems of low calculation speed, insufficient intelligence in prompt, difficulty in use across scenes and the like are solved. And meanwhile, the prompt words are screened based on a preset rule representing the input habit, the prompt words with the highest relevance with the current input text are screened out by learning the input habit of the user, and the information prompting accuracy is improved.
In some specific embodiments, the obtaining module 11 specifically includes:
the word segmentation unit is used for performing word segmentation processing on the current input text by using a word segmentation device to obtain a current text after word segmentation;
and the filtering unit is used for filtering the segmented current text by using a filter to obtain the filtered segmented current text.
In some specific embodiments, the calculation module 12 specifically includes:
the word frequency calculation unit is used for acquiring the current offline word frequency from the database and carrying out online incremental calculation on the current offline word frequency by using the segmented current text to obtain the current online word frequency;
the updating unit is used for updating the current offline word frequency in the database by using the current online word frequency to obtain the real-time current offline word frequency;
and the scene determining unit is used for determining a target scene corresponding to the current input text according to the input text of preset time before the current moment, and determining words corresponding to the target scene from the word list corresponding to the current online word frequency so as to obtain a target prompt.
In some embodiments, the screening module 13 specifically includes:
the rule determining unit is used for determining a preset rule based on a representation input habit by carrying out grammar determination on the historical input text;
and the rule matching unit is used for screening the target prompt words based on preset rules representing input habits and theoretical grammar rules and outputting the screened target prompt words.
In some specific embodiments, the information prompting device further includes:
the off-line calculation module is used for acquiring a historical input text, performing word segmentation processing on the historical input text to obtain a post-word-segmentation historical text, performing off-line calculation on the post-word-segmentation historical text by using a calculator to obtain the current off-line word frequency, and storing the current off-line word frequency to a database;
and the configuration module is used for carrying out corresponding configuration on the word segmentation device for carrying out word segmentation processing and the calculator for carrying out word frequency calculation according to the target requirement, and carrying out word segmentation operation and word frequency calculation operation through the configured word segmentation device and the configured component interface of the calculator.
Further, the embodiment of the application also provides electronic equipment. FIG. 5 is a block diagram illustrating an electronic device 20 according to an exemplary embodiment, and the contents of the diagram should not be construed as limiting the scope of use of the present application in any way.
Fig. 5 is a schematic structural diagram of an electronic device 20 according to an embodiment of the present disclosure. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input output interface 25, and a communication bus 26. The memory 22 is used for storing a computer program, and the computer program is loaded and executed by the processor 21 to implement the relevant steps in the information prompting method disclosed in any of the foregoing embodiments.
In this embodiment, the power supply 23 is configured to provide a working voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and an external device, and a communication protocol followed by the communication interface is any communication protocol applicable to the technical solution of the present application, and is not specifically limited herein; the input/output interface 25 is configured to obtain external input data or output data to the outside, and a specific interface type thereof may be selected according to specific application requirements, which is not specifically limited herein.
In addition, the storage 22 is used as a carrier for resource storage, and may be a read-only memory, a random access memory, a magnetic disk or an optical disk, etc., and the resources stored thereon may include an operating system 221, a computer program 222, data 223, etc., and the storage may be a transient storage or a permanent storage.
The operating system 221 is used for managing and controlling each hardware device and the computer program 222 on the electronic device 20, so as to realize the operation and processing of the mass data 223 in the memory 22 by the processor 21, and may be Windows Server, Netware, Unix, Linux, and the like. The computer program 222 may further include a computer program that can be used to perform other specific tasks in addition to the computer program that can be used to perform the information presentation method disclosed in any of the foregoing embodiments and executed by the electronic device 20. Data 223 may include input text collected by electronic device 20.
Further, an embodiment of the present application further discloses a storage medium, in which a computer program is stored, and when the computer program is loaded and executed by a processor, the steps of the information prompting method disclosed in any of the foregoing embodiments are implemented.
The embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same or similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The information prompting method, the information prompting device, the information prompting equipment and the storage medium are described in detail, specific examples are applied in the description to explain the principle and the implementation mode of the invention, and the description of the embodiments is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (10)
1. An information prompting method, comprising:
acquiring a current input text, and performing word segmentation processing on the current input text to obtain a word segmented current text;
performing online incremental calculation on the current offline word frequency by using the segmented current text to obtain the current online word frequency, and determining a target prompt corresponding to the current input text according to the current online word frequency; the current offline word frequency is obtained by performing offline calculation on a historical input text;
and screening the target prompt words based on a preset rule representing an input habit and outputting the screened target prompt words.
2. The information prompting method according to claim 1, further comprising:
obtaining a historical input text, and performing word segmentation processing on the historical input text to obtain a word segmented historical text;
and utilizing a calculator to perform offline calculation on the segmented historical text to obtain the current offline word frequency, and storing the current offline word frequency in a database.
3. The information prompting method according to claim 1, wherein the obtaining of the segmented current text by performing the segmentation processing on the current input text comprises:
performing word segmentation processing on the current input text by using a word segmentation device to obtain a current text after word segmentation;
and filtering the segmented current text by using a filter to obtain the filtered segmented current text.
4. The information prompting method of claim 1, wherein the obtaining of the current online word frequency by performing online incremental computation on the current offline word frequency using the segmented current text comprises:
acquiring current offline word frequency from a database, and performing online incremental calculation on the current offline word frequency by using the segmented current text to obtain the current online word frequency;
and updating the current offline word frequency in the database by using the current online word frequency to obtain the real-time current offline word frequency.
5. The information prompting method of claim 1, wherein the determining a target prompt corresponding to the currently input text according to the current online word frequency comprises:
determining a target scene corresponding to the current input text according to the input text of preset time before the current time, and determining words corresponding to the target scene from a word list corresponding to the current online word frequency to obtain a target prompt.
6. The information prompting method according to claim 1, wherein the filtering the target prompt based on a preset rule representing an input habit and outputting the filtered target prompt comprises:
determining a preset rule based on a representation input habit by carrying out syntactic analysis on the historical input text;
and screening the target prompt words based on preset rules representing input habits and theoretical grammar rules and outputting the screened target prompt words.
7. The information presentation method according to any one of claims 1 to 6, further comprising:
carrying out corresponding configuration on a word segmentation device for carrying out word segmentation processing and a calculator for carrying out word frequency calculation according to target requirements;
and performing word segmentation operation and word frequency calculation operation through the configured word segmenter and the configured component interface of the calculator.
8. An information presentation device, comprising:
the acquisition module is used for acquiring a current input text and performing word segmentation processing on the current input text to obtain a word segmented current text;
the calculation module is used for performing online incremental calculation on the current offline word frequency by using the segmented current text to obtain the current online word frequency and determining a target prompt corresponding to the current input text according to the current online word frequency; the current offline word frequency is obtained by performing offline calculation on a historical input text;
and the screening module is used for screening the target prompt words based on a preset rule representing an input habit and outputting the screened target prompt words.
9. An electronic device, comprising a processor and a memory; wherein the memory is for storing a computer program that is loaded and executed by the processor to implement the information prompting method according to any one of claims 1 to 7.
10. A computer-readable storage medium storing computer-executable instructions which, when loaded and executed by a processor, carry out the method of information prompting according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111037874.0A CN113722470B (en) | 2021-09-06 | 2021-09-06 | Information prompting method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111037874.0A CN113722470B (en) | 2021-09-06 | 2021-09-06 | Information prompting method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113722470A true CN113722470A (en) | 2021-11-30 |
| CN113722470B CN113722470B (en) | 2024-03-08 |
Family
ID=78681918
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111037874.0A Active CN113722470B (en) | 2021-09-06 | 2021-09-06 | Information prompting method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113722470B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000148780A (en) * | 1998-11-12 | 2000-05-30 | Nippon Telegr & Teleph Corp <Ntt> | Method and device for document retrieval and recording medium where document retrieving program is recorded |
| WO2007000104A1 (en) * | 2005-06-25 | 2007-01-04 | Qiangguo Sun | A method for inputting the alphabetic writing using the number key |
| CN101630316A (en) * | 2008-07-18 | 2010-01-20 | 株式会社日立制作所 | Word message prompting system |
| CN103034407A (en) * | 2012-12-07 | 2013-04-10 | 东莞宇龙通信科技有限公司 | Terminal and method for inputting useful expressions quickly |
| CN105718071A (en) * | 2016-01-19 | 2016-06-29 | 努比亚技术有限公司 | Terminal and method for recommending associational words in input method |
| CN107423444A (en) * | 2017-08-10 | 2017-12-01 | 世纪龙信息网络有限责任公司 | Hot word phrase extracting method and system |
| CN108563965A (en) * | 2018-03-29 | 2018-09-21 | 广东欧珀移动通信有限公司 | Character input method and device, computer readable storage medium, terminal |
| CN108628461A (en) * | 2017-03-16 | 2018-10-09 | 北京搜狗科技发展有限公司 | A kind of input method and device, a kind of method and apparatus of update dictionary |
-
2021
- 2021-09-06 CN CN202111037874.0A patent/CN113722470B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000148780A (en) * | 1998-11-12 | 2000-05-30 | Nippon Telegr & Teleph Corp <Ntt> | Method and device for document retrieval and recording medium where document retrieving program is recorded |
| WO2007000104A1 (en) * | 2005-06-25 | 2007-01-04 | Qiangguo Sun | A method for inputting the alphabetic writing using the number key |
| CN101630316A (en) * | 2008-07-18 | 2010-01-20 | 株式会社日立制作所 | Word message prompting system |
| CN103034407A (en) * | 2012-12-07 | 2013-04-10 | 东莞宇龙通信科技有限公司 | Terminal and method for inputting useful expressions quickly |
| CN105718071A (en) * | 2016-01-19 | 2016-06-29 | 努比亚技术有限公司 | Terminal and method for recommending associational words in input method |
| CN108628461A (en) * | 2017-03-16 | 2018-10-09 | 北京搜狗科技发展有限公司 | A kind of input method and device, a kind of method and apparatus of update dictionary |
| CN107423444A (en) * | 2017-08-10 | 2017-12-01 | 世纪龙信息网络有限责任公司 | Hot word phrase extracting method and system |
| CN108563965A (en) * | 2018-03-29 | 2018-09-21 | 广东欧珀移动通信有限公司 | Character input method and device, computer readable storage medium, terminal |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113722470B (en) | 2024-03-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11663409B2 (en) | Systems and methods for training machine learning models using active learning | |
| US10831811B2 (en) | Resolution of ambiguous and implicit references using contextual information | |
| US20190180196A1 (en) | Systems and methods for generating and updating machine hybrid deep learning models | |
| US10102481B2 (en) | Hybrid active learning for non-stationary streaming data with asynchronous labeling | |
| CN111708869B (en) | Processing method and device for man-machine conversation | |
| JP2021056991A (en) | Recommendation method, device, electronic device, storage medium, and program | |
| CN109032381B (en) | Input method and device based on context, storage medium and terminal | |
| JP2021131528A (en) | User intention recognition method, device, electronic apparatus, computer readable storage media and computer program | |
| CN110765247A (en) | Input prompting method and device for question-answering robot | |
| US11935315B2 (en) | Document lineage management system | |
| CN111159341A (en) | Information recommendation method and device based on user investment and financing preference | |
| CN111400458A (en) | Automatic generalization method and device | |
| CN115840802A (en) | Service processing method and device | |
| EP4060517A1 (en) | System and method for designing artificial intelligence (ai) based hierarchical multi-conversation system | |
| CN114694644A (en) | Voice intention recognition method and device and electronic equipment | |
| CN109693244B (en) | Method and device for optimizing conversation robot | |
| US11010446B2 (en) | Intelligent feedback and context driven web navigation | |
| Armentano et al. | Modeling sequences of user actions for statistical goal recognition | |
| CN107943537B (en) | Application cleaning method and device, storage medium and electronic equipment | |
| CN110874399A (en) | Information processing method and device, computing equipment and terminal | |
| CN112667791A (en) | Latent event prediction method, device, equipment and storage medium | |
| US11100407B2 (en) | Building domain models from dialog interactions | |
| CN113722470A (en) | Information prompting method, device, equipment and storage medium | |
| CN111414460A (en) | Multi-round dialogue management method and device combining memory storage and neural network | |
| CN115329173A (en) | Method and device for determining enterprise credit based on public opinion monitoring |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |