CN115022394A - Information pushing method and device and storage medium - Google Patents
Information pushing method and device and storage medium Download PDFInfo
- Publication number
- CN115022394A CN115022394A CN202110242110.9A CN202110242110A CN115022394A CN 115022394 A CN115022394 A CN 115022394A CN 202110242110 A CN202110242110 A CN 202110242110A CN 115022394 A CN115022394 A CN 115022394A
- Authority
- CN
- China
- Prior art keywords
- information
- vocabulary
- professional
- professional vocabulary
- interpretation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000003860 storage Methods 0.000 title claims abstract description 20
- 238000004590 computer program Methods 0.000 claims description 13
- 238000012549 training Methods 0.000 claims description 9
- 238000010586 diagram Methods 0.000 description 13
- 238000012545 processing Methods 0.000 description 8
- 238000004891 communication Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 208000006096 Attention Deficit Disorder with Hyperactivity Diseases 0.000 description 4
- 208000036864 Attention deficit/hyperactivity disease Diseases 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000012015 optical character recognition Methods 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 208000026738 Child Behavior disease Diseases 0.000 description 1
- MQJKPEGWNLWLTK-UHFFFAOYSA-N Dapsone Chemical compound C1=CC(N)=CC=C1S(=O)(=O)C1=CC=C(N)C=C1 MQJKPEGWNLWLTK-UHFFFAOYSA-N 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 208000015802 attention deficit-hyperactivity disease Diseases 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000005978 brain dysfunction Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 210000005069 ears Anatomy 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 208000011580 syndromic disease Diseases 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Images
Landscapes
- Machine Translation (AREA)
Abstract
The embodiment of the application provides an information pushing method, an information pushing device and a storage medium, wherein the method comprises the following steps: the method comprises the steps of obtaining text information and voice information, obtaining professional vocabularies based on the text information and the voice information, obtaining explanation information of the professional vocabularies based on a professional vocabulary dictionary, pushing the explanation information to a terminal corresponding to a target user, and enabling non-professional personnel to accurately know technical contents in a specific field.
Description
Technical Field
The present application relates to the field of artificial intelligence technologies, and in particular, to an information pushing method, an information pushing device, and a storage medium.
Background
With the rapid development of society, various academic and technical exchanges are increased, the requirements on meeting participants are higher and higher, many professional vocabularies are involved in the meeting, and the understanding of non-professional people is difficult. Therefore, how to reduce the threshold of the participants in various academic and technical exchanges to enable non-professionals to accurately understand the technical content in a specific field is a technical problem to be solved in the industry at present.
Disclosure of Invention
The embodiment of the application provides an information pushing method, an information pushing device and a storage medium, which are used for overcoming the defect that in the prior art, a conference involves many professional vocabularies, and non-professionals are difficult to understand, reducing the threshold of participants in various academic and technical conference, and enabling the non-professionals to conveniently know the technology in a specific field.
In a first aspect, an embodiment of the present application provides an information pushing method, including:
acquiring character information and voice information;
acquiring professional vocabularies based on the character information and the voice information;
and acquiring interpretation information of the professional vocabulary based on the professional vocabulary dictionary, and pushing the interpretation information to a terminal corresponding to the target user.
Optionally, the information pushing method according to an embodiment of the present application further includes:
acquiring a first professional vocabulary and interpretation information of the first professional vocabulary based on the character information and the voice information; the first professional vocabulary is professional vocabulary with corresponding explanation information in the text information and/or the voice information;
updating a target professional vocabulary in the first professional vocabulary and interpretation information of the target professional vocabulary to the professional vocabulary dictionary; and the target professional vocabulary is professional vocabulary without explanation information in a professional vocabulary dictionary.
Optionally, according to an information pushing method of an embodiment of the present application, the obtaining a first specialized vocabulary and interpretation information of the first specialized vocabulary based on the text information and the voice information includes:
acquiring a corresponding second professional vocabulary and interpretation information of the second professional vocabulary based on the character information;
acquiring a corresponding third professional vocabulary and interpretation information of the third professional vocabulary based on the voice information;
and acquiring the first professional vocabulary and the interpretation information of the first professional vocabulary based on the second professional vocabulary and the interpretation information of the second professional vocabulary, the third professional vocabulary and the interpretation information of the third professional vocabulary.
Optionally, according to an information pushing method in an embodiment of the present application, the obtaining, based on the text information, a corresponding second professional vocabulary and interpretation information of the second professional vocabulary includes:
determining a character recognition result of the character information based on a character recognition model;
determining the second professional vocabulary and interpretation information of the second professional vocabulary based on the character recognition result and the text typesetting format corresponding to the character information;
the character recognition model is obtained after training based on character sample data and a predetermined text label.
Optionally, according to an information pushing method in an embodiment of the present application, the obtaining, based on the voice information, a corresponding third specialized vocabulary and interpretation information of the third specialized vocabulary includes:
determining a voice recognition result of the voice information based on the large-scale continuous voice recognition LVCSR;
and determining the third professional vocabulary and interpretation information of the third professional vocabulary based on the voice recognition result.
In a second aspect, an embodiment of the present application further provides an apparatus, including a memory, a transceiver, and a processor, where:
a memory for storing a computer program; a transceiver for transceiving data under control of the processor; a processor for reading the computer program in the memory and executing the steps of the information push method according to the first aspect.
In a third aspect, an embodiment of the present application further provides an information pushing apparatus, including:
the information acquisition unit is used for acquiring text information and voice information;
the professional vocabulary acquisition unit is used for acquiring professional vocabularies based on the character information and the voice information;
and the interpretation information pushing unit is used for acquiring the interpretation information of the professional vocabulary based on the professional vocabulary dictionary and pushing the interpretation information to a terminal corresponding to the target user.
In a fourth aspect, this application embodiment further provides a processor-readable storage medium, where the processor-readable storage medium stores a computer program for causing the processor to execute the steps of the information pushing method according to the first aspect.
According to the information pushing method, the information pushing device and the storage medium, the professional vocabulary is obtained based on the text information and the voice information, the explanation information of the professional vocabulary is obtained based on the professional vocabulary dictionary, and the explanation information is pushed to the terminal corresponding to the target user, so that non-professionals can accurately know technical contents in the specific field.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a schematic flowchart of an information pushing method provided in an embodiment of the present application;
FIG. 2 is a schematic view of an academic conference board for teaching directions provided by an embodiment of the present application;
FIG. 3 is a schematic flow chart illustrating the operation of an automatic speech recognition module provided by an embodiment of the present application;
FIG. 4 is a schematic structural diagram of an apparatus provided in an embodiment of the present application;
FIG. 5 is a schematic structural diagram of an information pushing apparatus provided in an embodiment of the present application;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In the embodiment of the present application, the term "and/or" describes an association relationship of associated objects, and means that there may be three relationships, for example, a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship.
In the embodiments of the present application, the term "plurality" means two or more, and other terms are similar thereto.
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only some embodiments of the present application, and not all 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 application.
The embodiment of the application provides an information pushing method, an information pushing device and a storage medium, which are used for overcoming the defect that in the prior art, a conference involves a plurality of professional vocabularies, and non-professionals have difficulty in understanding, reducing the threshold of participants in various academic and technical communication conferences, and enabling the non-professionals to conveniently know the technology in a specific field.
The method and the device are based on the same application concept, and because the principles of solving the problems of the method and the device are similar, the implementation of the device and the method can be mutually referred, and repeated parts are not described again.
Fig. 1 is a schematic flow chart of an information pushing method according to an embodiment of the present application. As shown in fig. 1, the method includes:
Specifically, the text information is text information in a current meeting scene, and includes text of a presentation on a large screen, text on a publicity page in a meeting place, and the like. The voice information is the voice of the speaker played in the current conference scene, the introduction voice played before and after the conference, and the like. To accurately push interpretation information, an information push device first needs to acquire text information and voice information in a conference scene, and determines a professional vocabulary needing to push the interpretation information based on the text information and the voice information.
And 102, acquiring a professional vocabulary based on the character information and the voice information.
Specifically, after acquiring the text information and the voice information, the information pushing device acquires the professional vocabulary to be explained based on the text information and the voice information. It can be understood that during the meeting, many professional vocabularies related to the meeting appear in the text information and the voice information, which causes difficulty for non-professional personnel participating in the meeting to understand. Therefore, the information pushing device can acquire the professional vocabularies mentioned in the text information and the voice information, inquire corresponding explanation information based on a preset professional vocabulary dictionary, and push the explanation information so as to facilitate the participants to accurately understand the technical content related to the conference.
And 103, acquiring interpretation information of the professional vocabulary based on the professional vocabulary dictionary, and pushing the interpretation information to a terminal corresponding to the target user.
Specifically, after the information pushing device obtains the professional vocabulary, the explanation information of the professional vocabulary is obtained based on the professional vocabulary dictionary, namely the explanation information corresponding to the professional vocabulary is quickly determined in a dictionary looking-up mode, and the explanation information is pushed to the terminal equipment corresponding to the target user, wherein the target user is preferably a nonprofessional person participating in a meeting. It can be understood that the target user may obtain the information through means such as participant information registration, and the interpretation information may be pushed through a contact means (for example, a mobile phone, a WeChat, a mailbox, and the like) registered by the participant, which is not specifically limited in this embodiment of the present application. Of course, the target user may be a general participant or a partial participant not in the field, and this is not particularly limited in this embodiment of the application.
According to the information pushing method provided by the embodiment of the application, the professional vocabulary is obtained based on the text information and the voice information, the explanation information of the professional vocabulary is obtained based on the professional vocabulary dictionary, and the explanation information is pushed to the terminal corresponding to the target user, so that non-professionals can accurately know the technical content in the specific field.
Based on the above embodiment, further include:
acquiring a first professional vocabulary and interpretation information of the first professional vocabulary based on the character information and the voice information; the first professional vocabulary is professional vocabulary with corresponding explanation information in the text information and/or the voice information;
updating a target professional vocabulary in the first professional vocabulary and interpretation information of the target professional vocabulary to the professional vocabulary dictionary; and the target professional vocabulary is professional vocabulary without explanation information in a professional vocabulary dictionary.
Specifically, the professional vocabulary dictionary includes: terms of art, proper nouns, acronyms, etc., and corresponding interpretative information. According to the content of the current conference, a professional vocabulary dictionary can be preset so as to push explanation information according to professional vocabularies.
In the actual application process, the professional vocabulary dictionary does not necessarily cover all professional vocabularies related in a conference, and therefore, the knowledge capacity of the professional vocabulary dictionary needs to be continuously expanded in the application process. In the conference process, part of the professional vocabularies may be interpreted through words (e.g., words on a presentation or a publicity page) or voices (e.g., voices of a speaker or introduction voices played before and after the conference), so that the information pushing device may obtain the first professional vocabulary and the interpretation information of the first professional vocabulary based on the word information and the voice information, that is, obtain all the professional vocabularies in the word information and/or the voice information having corresponding interpretation information.
The target professional vocabulary is a professional vocabulary without interpretation information in a professional vocabulary dictionary, and the target professional vocabulary can be updated to the professional vocabulary dictionary after or during a meeting, so that the application range of the professional vocabulary dictionary is expanded, and the accuracy and comprehensiveness of interpretation information push in a subsequent application process are ensured.
As for the professional vocabulary which is not present in the professional vocabulary dictionary, and is not interpreted during the meeting, the professional vocabulary may be first included in the professional vocabulary dictionary and then learned and supplemented through other ways, which is not specifically limited in the embodiment of the present application.
The information push method that this application embodiment provided, through based on literal information with speech information, acquire first professional vocabulary and the explanatory information of first professional vocabulary, first professional vocabulary is in there is the professional vocabulary that corresponds explanatory information in literal information and/or speech information, will target professional vocabulary in the first professional vocabulary and the explanatory information of target professional vocabulary updates arrive in the professional vocabulary dictionary, wherein, target professional vocabulary does not exist the professional vocabulary of explanatory information in professional vocabulary dictionary, can constantly enlarge the range of application of professional vocabulary dictionary, guarantees accuracy and the comprehensiveness of explanatory letter propelling movement.
Based on the above embodiment, the obtaining of the first specialized vocabulary and the interpretation information of the first specialized vocabulary based on the text information and the voice information includes:
acquiring corresponding second professional vocabularies and interpretation information of the second professional vocabularies based on the text information;
acquiring a corresponding third professional vocabulary and interpretation information of the third professional vocabulary based on the voice information;
and acquiring the first professional vocabulary and the interpretation information of the first professional vocabulary based on the second professional vocabulary and the interpretation information of the second professional vocabulary, the third professional vocabulary and the interpretation information of the third professional vocabulary.
Specifically, in an actual conference scene, text information and voice information are not completely aligned, and there are often situations such as insertion and deletion of voice, that is, a speaker does not read according to a presentation but adds or deletes part of information. Therefore, the method and the device adopt combination of the character information and the voice information to acquire the professional vocabulary and the explanation information thereof, and finally determine the explanation information of the first professional vocabulary.
Information pusher is based on word information obtains the second professional vocabulary that corresponds and the explanatory information of second professional vocabulary, is based on speech information obtains the third professional vocabulary that corresponds and the explanatory information of third professional vocabulary, can understand that, first to third professional vocabulary is only for the definition of going on in order to distinguish conveniently, under practical application scene, second professional vocabulary and third professional vocabulary are probably the same, and the professional vocabulary that obtains from word information is the same with the professional vocabulary that obtains from speech information promptly, and first professional vocabulary probably contains in second professional vocabulary and/or third professional vocabulary.
And the information pushing device acquires the first professional vocabulary and the interpretation information of the first professional vocabulary based on the second professional vocabulary and the interpretation information of the second professional vocabulary, the third professional vocabulary and the interpretation information of the third professional vocabulary. It can be understood that, in an actual application scenario, there may be a case where the same professional vocabulary has a plurality of different interpretation information or the interpretation information of a plurality of different professional vocabularies is the same, and for these cases, the information pushing apparatus may compare the second professional vocabulary and the corresponding interpretation information with the third professional vocabulary and the corresponding interpretation information, so as to implement correction and deduplication of the first professional vocabulary and the interpretation information, and finally obtain the first accurate refined professional vocabulary and the corresponding interpretation information, and update the target professional vocabulary in the first professional vocabulary and the interpretation information of the target professional vocabulary to the professional vocabulary dictionary.
And simultaneously, after a text recognition result is obtained through text recognition, named entities can be found out through named entity recognition, named entities outside a dictionary knowledge base are sent to an automatic voice recognition module, the recognition rate of the named entities by the automatic voice recognition module is improved, the named entities are added into dictionary knowledge base candidates, and the candidates are manually or automatically screened and then added into the dictionary knowledge base, so that the contents of the professional vocabulary dictionary are continuously updated and enriched, and the accuracy of message pushing is improved.
The information push method that this application embodiment provided, through based on the second professional vocabulary reaches the interpretation information of second professional vocabulary the third professional vocabulary reaches the interpretation information of third professional vocabulary acquires first professional vocabulary reaches the interpretation information of first professional vocabulary can accurately acquire first professional vocabulary and corresponding interpretation information, and will target professional vocabulary in the first professional vocabulary reaches the interpretation information of target professional vocabulary is used for updating professional vocabulary dictionary to the accurate propelling movement of interpretation information is carried out to the follow-up, makes non-professional can accurately know specific field's technical content.
Based on the above embodiment, the obtaining, based on the text information, the corresponding second specialized vocabulary and the interpretation information of the second specialized vocabulary includes:
determining a character recognition result of the character information based on a character recognition model;
determining the second professional vocabulary and interpretation information of the second professional vocabulary based on the character recognition result and the text typesetting format corresponding to the character information;
the character recognition model is obtained after training based on character sample data and a predetermined text label.
Specifically, the character recognition model needs to be trained accurately, and in the training stage, character information such as a character image is captured by a camera or other devices, and then feature extraction is performed in a Region Of Interest (ROI), for example, Haar features (a feature that reflects gray level change Of an image and a pixel division module finds a difference) are generally modeled by using a deep neural network model, and model parameters are found by model training, so as to finally obtain the character recognition model.
In the recognition stage, after character information is input, the characteristics same as those in the training stage are extracted, and the characteristics enter a neural network model for recognition to obtain a character recognition result.
The information pushing device automatically extracts the professional vocabulary and the explanation information of the professional vocabulary based on the character recognition result and the typesetting format of the text.
A specific process of acquiring a corresponding second professional vocabulary and interpretation information of the second professional vocabulary based on the text information is described below by using a specific example, as shown in fig. 2, which is a schematic diagram of an academic conference display board in a teaching direction provided by an embodiment of the present application, an information pushing device first acquires text information on the display board, then recognizes texts in the display board through OCR (Optical Character Recognition), and then finds a keyword by detecting a position relationship between pictures: evaluation feedback, classroom teaching, network lesson preparation, collaborative learning, and corresponding interpretation information.
According to the information pushing method, the second professional vocabulary and the interpretation information of the second professional vocabulary are determined based on the character recognition result and the text typesetting format corresponding to the character information, and the accuracy of the professional vocabulary and the interpretation information thereof acquired from the character information can be ensured.
Based on the above embodiment, the obtaining, based on the voice information, a corresponding third specialized vocabulary and interpretation information of the third specialized vocabulary includes:
determining a voice recognition result of the voice information based on the LVCSR;
and determining the third professional vocabulary and interpretation information of the third professional vocabulary based on the voice recognition result.
Specifically, the information pushing device determines a voice recognition result of the voice information based on a large-scale Continuous voice recognition lvcsr (large voice continuity recognition) technology, and determines the third professional Vocabulary and the interpretation information of the third professional Vocabulary based on the voice recognition result and the semantic understanding. Fig. 3 is a schematic view of a work flow of an automatic speech recognition module according to an embodiment of the present application.
As shown in fig. 3, considering the auditory characteristics of human ears, Mel cepstral coefficients or perceptual linear prediction coefficients have become one of the mainstream speech feature vector extraction methods, and after adding their first-order and second-order differences and normalizing the feature vectors, good results are obtained in terms of large-vocabulary continuous speech recognition.
The acoustic model is the underlying model of the automatic speech recognition module and is the most critical part of the speech recognition module. The continuous speech signal is composed of basic speech units, which may be sentences, phrases, words, syllables, Sub-syllables (syllables) or phonemes, and what speech unit is selected as the modeling unit of the acoustic model is determined by the specific application (objective factors such as the size of vocabulary, the number of speech libraries, required performance, etc.). In general, it should be ensured that the selected modeling unit satisfies the following condition: 1) robustness: each model has enough samples to estimate the model parameters; 2) consistency: the modeling unit should be stable with relatively small changes in acoustic characteristics under different conditions. In continuous speech, the modeling unit implementation in different contexts can sometimes be very different due to the effect of co-articulation. To improve the accuracy of the model, the influence of the context on the modeling unit needs to be considered. In the research of acoustic models, the context-dependent modeling units (such as diphone and triphone) are gradually gaining attention, and become the mainstream of the acoustic model modeling units at present.
With the continuous development of speech recognition technology, the role of language models in speech recognition is becoming more and more important. Due to the dynamic time-varying, transient and random nature of acoustic signals, it is not possible to achieve error-free recognition and understanding of speech by matching and judging acoustic patterns alone. The utilization of some higher level language knowledge may reduce the ambiguity of pattern matching at the level of acoustic recognition, thereby improving the accuracy of recognition. And a large vocabulary continuous speech recognition system must detect whether a speech pronunciation boundary is encountered at each moment so that many different words or phrases will be recognized from different speech streams. To eliminate ambiguity between these words or phrases, a language model is essential. The language model may provide contextual information and semantic information between words or phrases. With the development of statistical language processing methods, statistical language models have become the mainstream technology for language processing in speech recognition.
The search is a process of finding an optimal sentence in a space formed by sentences according to a certain optimization criterion, that is, finding an optimal state sequence in a state (a state of a phrase, a word, a modeling unit or an HMM (Hidden Markov Model)) space by using mastered knowledge (acoustic knowledge, phonetic knowledge, dictionary knowledge, language Model knowledge, grammatical semantic knowledge, and the like). An acoustic model, a pronunciation dictionary, a language model and the like are tightly combined through an FST (Finite State Transducer), and searching is carried out on the FST, and finally a voice recognition result is obtained.
And the information pushing device automatically extracts the professional vocabulary and the interpretation information of the professional vocabulary according to the result of the voice recognition and the semantic understanding. For example, in an academic conference of medical directions, a speaker speaks: ADHD is known as a common child behavior disorder, and ADHD is also known as attention deficit hyperactivity disorder or mild brain dysfunction syndrome. By semantic understanding techniques, we can find the terms: ADHD, and corresponding explanations.
According to the information pushing method, the voice recognition result of the voice information is determined based on the large-scale continuous voice recognition LVCSR, the third professional vocabulary and the interpretation information of the third professional vocabulary are determined based on the voice recognition result, and the accuracy of the professional vocabulary and the interpretation information thereof obtained from the voice information can be ensured.
Fig. 4 is a schematic structural diagram of an apparatus according to an embodiment of the present application, and as shown in fig. 4, the apparatus 400 includes a memory 402, a transceiver 403, and a processor 401: wherein the processor 401 and the memory 402 may also be arranged physically separately.
A memory 402 for storing a computer program; a transceiver 403 for transceiving data under the control of the processor 401.
In particular, where in fig. 4 the bus architecture may include any number of interconnected buses and bridges, various circuits of one or more processors, in particular represented by processor 401, and memory, in particular represented by memory 402, are linked together. The bus architecture may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. The bus interface provides an interface. The transceiver 403 may be a number of elements including a transmitter and a receiver that provide a means for communicating with various other apparatus over a transmission medium including wireless channels, wired channels, fiber optic cables, and the like. The processor 401 is responsible for managing the bus architecture and general processing, and the memory 402 may store data used by the processor 401 in performing operations.
The processor 401 may be a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA), or a Complex Programmable Logic Device (CPLD), and may also have a multi-core architecture.
The processor 401 calls the computer program stored in the memory 402 to execute any of the methods provided by the embodiments of the present application according to the obtained executable instructions, for example:
acquiring text information and voice information;
acquiring professional vocabularies based on the character information and the voice information;
and acquiring interpretation information of the professional vocabulary based on the professional vocabulary dictionary, and pushing the interpretation information to a terminal corresponding to the target user.
Based on the above embodiment, further include:
acquiring a first professional vocabulary and interpretation information of the first professional vocabulary based on the character information and the voice information; the first professional vocabulary is professional vocabulary with corresponding explanation information in the text information and/or the voice information;
updating a target professional vocabulary in the first professional vocabulary and interpretation information of the target professional vocabulary to the professional vocabulary dictionary; and the target professional vocabulary is professional vocabulary without explanation information in a professional vocabulary dictionary.
Based on the above embodiment, the obtaining of the first specialized vocabulary and the interpretation information of the first specialized vocabulary based on the text information and the voice information includes:
acquiring corresponding second professional vocabularies and interpretation information of the second professional vocabularies based on the text information;
acquiring a corresponding third professional vocabulary and interpretation information of the third professional vocabulary based on the voice information;
and acquiring the first professional vocabulary and the interpretation information of the first professional vocabulary based on the second professional vocabulary and the interpretation information of the second professional vocabulary, the third professional vocabulary and the interpretation information of the third professional vocabulary.
Based on the above embodiment, the obtaining of the corresponding second professional vocabulary and the interpretation information of the second professional vocabulary based on the text information includes:
determining a character recognition result of the character information based on a character recognition model;
determining the second professional vocabulary and interpretation information of the second professional vocabulary based on the character recognition result and the text typesetting format corresponding to the character information;
the character recognition model is obtained after training based on character sample data and a predetermined text label.
Based on the above embodiment, the obtaining, based on the voice information, the corresponding third specialized vocabulary and the interpretation information of the third specialized vocabulary includes:
determining a voice recognition result of the voice information based on the LVCSR;
and determining the third professional vocabulary and the interpretation information of the third professional vocabulary based on the voice recognition result.
It should be noted that the apparatus provided in the embodiment of the present invention can implement all the method steps implemented by the method embodiment, and can achieve the same technical effects, and detailed descriptions of the same parts and beneficial effects as the method embodiment in this embodiment are not repeated herein.
Fig. 5 is a schematic structural diagram of an information pushing apparatus provided in an embodiment of the present application, and as shown in fig. 5, the apparatus includes:
an information obtaining unit 501, configured to obtain text information and voice information;
a professional vocabulary acquiring unit 502, configured to acquire a professional vocabulary based on the text information and the voice information;
the interpretation information pushing unit 503 is configured to obtain interpretation information of the professional vocabulary based on the professional vocabulary dictionary, and push the interpretation information to a terminal corresponding to the target user.
Based on the above embodiment, further include:
the dictionary updating unit is used for acquiring a first professional vocabulary and interpretation information of the first professional vocabulary based on the character information and the voice information; the first professional vocabulary is professional vocabulary with corresponding explanation information in the text information and/or the voice information;
updating a target professional vocabulary in the first professional vocabulary and interpretation information of the target professional vocabulary to the professional vocabulary dictionary; and the target professional vocabulary is professional vocabulary without explanation information in a professional vocabulary dictionary.
Based on the above embodiment, the obtaining of the first specialized vocabulary and the interpretation information of the first specialized vocabulary based on the text information and the voice information includes:
acquiring a corresponding second professional vocabulary and interpretation information of the second professional vocabulary based on the character information;
acquiring a corresponding third professional vocabulary and interpretation information of the third professional vocabulary based on the voice information;
and acquiring the first professional vocabulary and the interpretation information of the first professional vocabulary based on the second professional vocabulary and the interpretation information of the second professional vocabulary, and the third professional vocabulary and the interpretation information of the third professional vocabulary.
Based on the above embodiment, the obtaining, based on the text information, the corresponding second specialized vocabulary and the interpretation information of the second specialized vocabulary includes:
determining a character recognition result of the character information based on a character recognition model;
determining the second professional vocabulary and interpretation information of the second professional vocabulary based on the character recognition result and the text typesetting format corresponding to the character information;
the character recognition model is obtained by training based on character sample data and a predetermined text label.
Based on the above embodiment, the obtaining, based on the voice information, a corresponding third specialized vocabulary and interpretation information of the third specialized vocabulary includes:
determining a voice recognition result of the voice information based on the LVCSR;
and determining the third professional vocabulary and interpretation information of the third professional vocabulary based on the voice recognition result.
It should be noted that the division of the unit in the embodiment of the present application is schematic, and is only a logic function division, and there may be another division manner in actual implementation. In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit may be implemented in the form of hardware, or may also be implemented in the form of a software functional unit.
Fig. 6 illustrates a physical structure diagram of an electronic device, which may include, as shown in fig. 6: a processor (processor)601, a communication Interface (Communications Interface)602, a memory (memory)603 and a communication bus 604, wherein the processor 601, the communication Interface 602 and the memory 603 complete communication with each other through the communication bus 604. The processor 601 may call logic instructions in the memory 603 to perform the information pushing method provided by the above embodiments.
In addition, the logic instructions in the memory 603 may be implemented in the form of software functional units and stored in a computer readable storage medium when the logic instructions are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
It should be noted that, the apparatus provided in the embodiment of the present invention can implement all the method steps implemented by the method embodiment and achieve the same technical effect, and detailed descriptions of the same parts and beneficial effects as the method embodiment in this embodiment are omitted here.
On the other hand, an embodiment of the present application further provides a processor-readable storage medium, where the processor-readable storage medium stores a computer program, where the computer program is configured to cause the processor to execute the method provided in each of the above embodiments, and the method includes:
acquiring character information and voice information;
acquiring a professional vocabulary based on the text information and the voice information;
and acquiring interpretation information of the professional vocabulary based on the professional vocabulary dictionary, and pushing the interpretation information to a terminal corresponding to the target user.
The processor-readable storage medium can be any available medium or data storage device that can be accessed by a processor, including, but not limited to, magnetic memory (e.g., floppy disks, hard disks, magnetic tape, magneto-optical disks (MOs), etc.), optical memory (e.g., CDs, DVDs, BDs, HVDs, etc.), and semiconductor memory (e.g., ROMs, EPROMs, EEPROMs, non-volatile memory (NAND FLASH), Solid State Disks (SSDs)), etc.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-executable instructions. These computer-executable instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These processor-executable instructions may also be stored in a processor-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the processor-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These processor-executable instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.
Claims (12)
1. An information pushing method, comprising:
acquiring character information and voice information;
acquiring professional vocabularies based on the character information and the voice information;
and acquiring interpretation information of the professional vocabulary based on the professional vocabulary dictionary, and pushing the interpretation information to a terminal corresponding to the target user.
2. The information pushing method according to claim 1, further comprising:
acquiring a first professional vocabulary and interpretation information of the first professional vocabulary based on the text information and the voice information; the first professional vocabulary is professional vocabulary with corresponding explanation information in the text information and/or the voice information;
updating a target professional vocabulary in the first professional vocabulary and interpretation information of the target professional vocabulary to the professional vocabulary dictionary; and the target professional vocabulary is professional vocabulary without explanation information in a professional vocabulary dictionary.
3. The information pushing method according to claim 2, wherein the obtaining of the first specialized vocabulary and the interpretation information of the first specialized vocabulary based on the text information and the voice information includes:
acquiring a corresponding second professional vocabulary and interpretation information of the second professional vocabulary based on the character information;
acquiring a corresponding third professional vocabulary and interpretation information of the third professional vocabulary based on the voice information;
and acquiring the first professional vocabulary and the interpretation information of the first professional vocabulary based on the second professional vocabulary and the interpretation information of the second professional vocabulary, the third professional vocabulary and the interpretation information of the third professional vocabulary.
4. The information pushing method according to claim 3, wherein the obtaining of the corresponding second specialized vocabulary and the interpretation information of the second specialized vocabulary based on the text information includes:
determining a character recognition result of the character information based on a character recognition model;
determining the second professional vocabulary and interpretation information of the second professional vocabulary based on the character recognition result and the text typesetting format corresponding to the character information;
the character recognition model is obtained after training based on character sample data and a predetermined text label.
5. The information pushing method according to claim 3, wherein the obtaining of the corresponding third specialized vocabulary and the interpretation information of the third specialized vocabulary based on the voice information includes:
determining a voice recognition result of the voice information based on the large-scale continuous voice recognition LVCSR;
and determining the third professional vocabulary and interpretation information of the third professional vocabulary based on the voice recognition result.
6. An apparatus comprising a memory, a transceiver, a processor, wherein:
a memory for storing a computer program; a transceiver for transceiving data under control of the processor; a processor for reading the computer program in the memory and performing the following operations:
acquiring text information and voice information;
acquiring professional vocabularies based on the character information and the voice information;
and acquiring interpretation information of the professional vocabulary based on the professional vocabulary dictionary, and pushing the interpretation information to a terminal corresponding to the target user.
7. The apparatus of claim 6, further comprising the operations of:
acquiring a first professional vocabulary and interpretation information of the first professional vocabulary based on the text information and the voice information; the first professional vocabulary is professional vocabulary with corresponding explanation information in the text information and/or the voice information;
updating a target professional vocabulary in the first professional vocabulary and interpretation information of the target professional vocabulary to the professional vocabulary dictionary;
and the target professional vocabulary is professional vocabulary without explanation information in a professional vocabulary dictionary.
8. The apparatus of claim 7, wherein the obtaining of the first specialized vocabulary and the interpretation information of the first specialized vocabulary based on the text information and the voice information comprises:
acquiring corresponding second professional vocabularies and interpretation information of the second professional vocabularies based on the text information;
acquiring a corresponding third professional vocabulary and interpretation information of the third professional vocabulary based on the voice information;
and acquiring the first professional vocabulary and the interpretation information of the first professional vocabulary based on the second professional vocabulary and the interpretation information of the second professional vocabulary, the third professional vocabulary and the interpretation information of the third professional vocabulary.
9. The apparatus according to claim 8, wherein the obtaining of the corresponding second specialized vocabulary and the interpretation information of the second specialized vocabulary based on the text information specifically includes:
determining a character recognition result of the character information based on a character recognition model;
determining the second professional vocabulary and interpretation information of the second professional vocabulary based on the character recognition result and the text typesetting format corresponding to the character information;
the character recognition model is obtained by training based on character sample data and a predetermined text label.
10. The apparatus according to claim 8, wherein the obtaining of the corresponding third specialized vocabulary and the interpretation information of the third specialized vocabulary based on the speech information specifically includes:
determining a voice recognition result of the voice information based on the large-scale continuous voice recognition LVCSR;
and determining the third professional vocabulary and the interpretation information of the third professional vocabulary based on the voice recognition result.
11. An information pushing apparatus, comprising:
the information acquisition unit is used for acquiring character information and voice information;
the professional vocabulary acquisition unit is used for acquiring professional vocabularies based on the character information and the voice information;
and the interpretation information pushing unit is used for acquiring the interpretation information of the professional vocabulary based on the professional vocabulary dictionary and pushing the interpretation information to a terminal corresponding to the target user.
12. A processor-readable storage medium, characterized in that the processor-readable storage medium stores a computer program for causing a processor to perform the method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110242110.9A CN115022394A (en) | 2021-03-04 | 2021-03-04 | Information pushing method and device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110242110.9A CN115022394A (en) | 2021-03-04 | 2021-03-04 | Information pushing method and device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115022394A true CN115022394A (en) | 2022-09-06 |
Family
ID=83064247
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110242110.9A Pending CN115022394A (en) | 2021-03-04 | 2021-03-04 | Information pushing method and device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115022394A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010072786A (en) * | 2008-09-17 | 2010-04-02 | Toshiba Corp | Medical support system and method of providing explanation |
| CN102043563A (en) * | 2009-10-10 | 2011-05-04 | 英业达股份有限公司 | Vocabulary explication system with multiple floating windows and method thereof |
| CN106384108A (en) * | 2016-08-31 | 2017-02-08 | 上海斐讯数据通信技术有限公司 | Text content retrieval method, word interpreting device and mobile terminal |
| KR20190084370A (en) * | 2018-01-07 | 2019-07-17 | (주)킨스미디어 | A Intelligent Method for Searching Legal Information |
| CN110347978A (en) * | 2019-07-02 | 2019-10-18 | 深圳市数字星河科技有限公司 | A kind of method of e-book aid reading |
| CN111541904A (en) * | 2020-04-15 | 2020-08-14 | 腾讯科技（深圳）有限公司 | Information prompting method, device, equipment and storage medium in live broadcast process |
| CN111564157A (en) * | 2020-03-18 | 2020-08-21 | 浙江省北大信息技术高等研究院 | Conference record optimization method, device, equipment and storage medium |
| WO2020220914A1 (en) * | 2019-04-30 | 2020-11-05 | 京东方科技集团股份有限公司 | Voice question and answer method and device, computer readable storage medium and electronic device |
-
2021
- 2021-03-04 CN CN202110242110.9A patent/CN115022394A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010072786A (en) * | 2008-09-17 | 2010-04-02 | Toshiba Corp | Medical support system and method of providing explanation |
| CN102043563A (en) * | 2009-10-10 | 2011-05-04 | 英业达股份有限公司 | Vocabulary explication system with multiple floating windows and method thereof |
| CN106384108A (en) * | 2016-08-31 | 2017-02-08 | 上海斐讯数据通信技术有限公司 | Text content retrieval method, word interpreting device and mobile terminal |
| KR20190084370A (en) * | 2018-01-07 | 2019-07-17 | (주)킨스미디어 | A Intelligent Method for Searching Legal Information |
| WO2020220914A1 (en) * | 2019-04-30 | 2020-11-05 | 京东方科技集团股份有限公司 | Voice question and answer method and device, computer readable storage medium and electronic device |
| CN110347978A (en) * | 2019-07-02 | 2019-10-18 | 深圳市数字星河科技有限公司 | A kind of method of e-book aid reading |
| CN111564157A (en) * | 2020-03-18 | 2020-08-21 | 浙江省北大信息技术高等研究院 | Conference record optimization method, device, equipment and storage medium |
| CN111541904A (en) * | 2020-04-15 | 2020-08-14 | 腾讯科技（深圳）有限公司 | Information prompting method, device, equipment and storage medium in live broadcast process |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11514891B2 (en) | Named entity recognition method, named entity recognition equipment and medium | |
| US10176804B2 (en) | Analyzing textual data | |
| CN107016994B (en) | Voice recognition method and device | |
| US10621975B2 (en) | Machine training for native language and fluency identification | |
| KR102191425B1 (en) | Apparatus and method for learning foreign language based on interactive character | |
| CN113168828A (en) | Session proxy pipeline trained based on synthetic data | |
| CN110797010A (en) | Question-answer scoring method, device, equipment and storage medium based on artificial intelligence | |
| US20140350934A1 (en) | Systems and Methods for Voice Identification | |
| US11810471B2 (en) | Computer implemented method and apparatus for recognition of speech patterns and feedback | |
| CN109697988B (en) | Voice evaluation method and device | |
| CN112397056B (en) | Voice evaluation method and computer storage medium | |
| CN111312231A (en) | Audio detection method and device, electronic equipment and readable storage medium | |
| CN110992942B (en) | Voice recognition method and device for voice recognition | |
| CN112634866B (en) | Speech synthesis model training and speech synthesis method, device, equipment and medium | |
| KR20180062003A (en) | Method of correcting speech recognition errors | |
| KR20040068023A (en) | Method of speech recognition using hidden trajectory hidden markov models | |
| US20230298564A1 (en) | Speech synthesis method and apparatus, device, and storage medium | |
| CN112818680A (en) | Corpus processing method and device, electronic equipment and computer-readable storage medium | |
| CN109697975B (en) | Voice evaluation method and device | |
| CN115022394A (en) | Information pushing method and device and storage medium | |
| CN114242035A (en) | Speech synthesis method, apparatus, medium, and electronic device | |
| CN114067781A (en) | Method, apparatus and medium for detecting speech recognition result | |
| CN114420159A (en) | Audio evaluation method and device and non-transient storage medium | |
| Mann et al. | Tamil talk: What you speak is what you get! | |
| CN112133325A (en) | Wrong phoneme recognition method and device |
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 |