CN115248843A - Method and device for assisting in generating record and record generating system - Google Patents
Method and device for assisting in generating record and record generating system Download PDFInfo
- Publication number
- CN115248843A CN115248843A CN202210753779.9A CN202210753779A CN115248843A CN 115248843 A CN115248843 A CN 115248843A CN 202210753779 A CN202210753779 A CN 202210753779A CN 115248843 A CN115248843 A CN 115248843A
- Authority
- CN
- China
- Prior art keywords
- information
- current
- target
- historical
- record
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3343—Query execution using phonetics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/166—Editing, e.g. inserting or deleting
- G06F40/186—Templates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/194—Calculation of difference between files
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/40—Processing or translation of natural language
- G06F40/58—Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Acoustics & Sound (AREA)
- Medical Informatics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application provides a method and a device for assisting in generating a record and a record generating system. The method comprises the following steps: acquiring historical information in a historical inquiry process, wherein the target historical information comprises a historical object element, a historical objective element, a historical subject element and a historical subjective element; constructing an artificial intelligence model; acquiring current information in the current inquiry process; and extracting target current information from the current information by adopting an artificial intelligence model, and generating a stroke record according to the target current information, wherein the target current information comprises a current object element, a current objective element, a current subject element and a current subjective element. According to the scheme, the artificial intelligence model is built to train the historical information and the target historical information corresponding to the historical information, the artificial intelligence model can be adopted to automatically extract the current target information in the current inquiry process, the structural expression of the current target information is formed, the record is generated, and the generated record is high in reliability.
Description
Technical Field
The application relates to the field of voice processing and natural language processing, in particular to a method and a device for assisting in generating a record and a record generating system.
Background
However, the existing record system cannot automatically extract target information, cannot perform structured analysis on the content of the record according to the target information, and cross comparison and case prediction are based on words, word frequency or word vectors of a record text, does not utilize effective information of the record, can only assist questioners to manually record through provided fixed prompts, and has low reliability due to the fact that the target information cannot be automatically extracted.
Disclosure of Invention
The application mainly aims to provide a method and a device for assisting in generating a record and a record generating system, so as to solve the problems that target information cannot be automatically extracted and the reliability of the record is low in the prior art.
According to an aspect of the embodiments of the present invention, a method for assisting in generating a record is provided, including: acquiring historical information in a historical inquiry process, wherein the historical information comprises historical voice information and/or historical text information, the historical voice information and/or the historical text information at least comprises target historical information, and the target historical information comprises a historical object element, a historical objective element, a historical subject element and a historical subjective element; constructing an artificial intelligence model, wherein the artificial intelligence model is obtained by using a plurality of groups of training data for training, and each group of training data in the plurality of groups of training data comprises the historical information and the target historical information corresponding to the historical information; acquiring current information in the current inquiry process, wherein the current information comprises current voice information and/or current text information; and extracting target current information from the current information by adopting the artificial intelligence model, and generating a stroke record according to the target current information, wherein the target current information comprises a current object element, a current objective element, a current subject element and a current subjective element.
Optionally, constructing an artificial intelligence model comprises: and extracting the target historical information in the historical information, and training by adopting the historical information and the target historical information to obtain a plurality of artificial intelligence models, wherein each artificial intelligence model is obtained by training by using a plurality of groups of training data, and each group of training data in the plurality of groups of training data comprises the historical information of a case of one type and the historical information corresponding to the target historical information.
Optionally, extracting target current information from the current information by using the artificial intelligence model, and generating a record according to the target current information, including: determining the case type corresponding to the current information; determining the artificial intelligence model corresponding to the current information according to the case type; and extracting the target current information from the current information by adopting the artificial intelligence model corresponding to the current information, and generating the record according to the target current information.
Optionally, when there are a plurality of pieces of target current information, generating a record according to the target current information, where the generating includes: acquiring a plurality of pieces of target current information, and sequencing the plurality of pieces of target current information according to the time sequence to obtain a plurality of pieces of sequenced target current information; and converting the sequenced current information of the plurality of targets to obtain target text information, and adding the target text information into a target template to generate the record.
Optionally, after converting the sorted current information of the plurality of targets to obtain target text information, adding the target text information to a target template, and generating the entry, the method further includes: determining whether the record conforms to a preset format, and generating first prompt information under the condition that the record does not conform to the preset format; and determining whether the four-element attributes of the record are complete, and generating second prompt information under the condition that the four-element attributes of the record are incomplete.
Optionally, the entry is generated by current information of a target object in a current inquiry process, the ordered current information of the targets is converted to obtain target text information, the target text information is added to a target template, and after the entry is generated, the method further includes: acquiring similarity among a plurality of the records; generating third prompt information under the condition that the similarity is greater than or equal to a similarity threshold value; and generating fourth prompt information under the condition that the similarity is smaller than the similarity threshold value.
Optionally, after obtaining the current information in the current inquiry process, the method further includes: determining the language of the current information; and under the condition that the language is not the target language, performing voice recognition on the current voice information in the current information, performing machine translation on the current text information in the current information, and converting the current information in the non-target language into the current information in the target language.
Optionally, after generating the record according to the target current information, the method further includes: and sending the record to display equipment so that the display equipment displays the record.
According to another aspect of the embodiments of the present invention, there is also provided an apparatus for assisting in generating a record, including: the device comprises a first acquisition unit, a second acquisition unit and a third acquisition unit, wherein the first acquisition unit is used for acquiring historical information in a historical inquiry process, the historical information comprises historical voice information and/or historical text information, the historical voice information and/or the historical text information at least comprises target historical information, and the target historical information comprises a historical object element, a historical objective element, a historical subject element and a historical subjective element; the artificial intelligence model is obtained by training a plurality of groups of training data, and each group of training data in the plurality of groups of training data comprises the historical information and the target historical information corresponding to the historical information; the second acquisition unit is used for acquiring current information in the current inquiry process, wherein the current information comprises current voice information and/or current text information; the first processing unit is used for extracting target current information from the current information by adopting the artificial intelligence model and generating a record according to the target current information, wherein the target current information comprises a current object element, a current objective element, a current subject element and a current subjective element.
According to still another aspect of the embodiments of the present invention, there is also provided a computer-readable storage medium, which includes a stored program, wherein when the program runs, the apparatus on which the computer-readable storage medium is located is controlled to execute any one of the methods.
According to still another aspect of the embodiments of the present invention, there is further provided a processor, configured to execute the program, where the program executes to perform any one of the methods.
According to another aspect of the embodiments of the present invention, there is also provided a stylus generating system, including: the device comprises a microphone, a display device and a device for assisting in generating a record, wherein the device for assisting in generating a record is respectively communicated with the microphone and the display device, and is used for executing any one of the methods.
In the embodiment of the invention, the historical information in the historical inquiry process is firstly acquired, then the artificial intelligence model is constructed, then the current information in the current inquiry process is acquired, finally the artificial intelligence model is adopted to extract the target current information from the current information, and the record is generated according to the target current information. According to the scheme, the artificial intelligence model is built to train the historical information and the target historical information corresponding to the historical information, the artificial intelligence model can be adopted to automatically extract the current target information in the current inquiry process, the structural expression of the current target information is formed, the record is generated, and the generated record is high in reliability.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the application and, together with the description, serve to explain the application and are not intended to limit the application. In the drawings:
fig. 1 is a flow chart illustrating a method for assisting in generating a transcript according to an embodiment of the present application;
fig. 2 shows a schematic structural diagram of an apparatus for assisting in generating a record according to an embodiment of the present application.
Detailed Description
It should be noted that, in the present application, the embodiments and features of the embodiments may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
In order to make the technical solutions of the present application better understood by those skilled in the art, 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.
It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It should be understood that the data so used may be interchanged under appropriate circumstances such that embodiments of the application described herein may be used. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It will be understood that when an element such as a layer, film, region, or substrate is referred to as being "on" another element, it can be directly on the other element or intervening elements may also be present. Also, in the specification and claims, when an element is described as being "connected" to another element, the element may be "directly connected" to the other element or "connected" to the other element through a third element.
As mentioned in the background art, target information cannot be automatically extracted in the prior art, and the reliability of the record is low, and in order to solve the above problem, in an embodiment of the present application, a method and an apparatus for assisting in generating a record and a record generation system are provided.
According to an embodiment of the application, a method for assisting in generating a record is provided. Fig. 1 is a flowchart of a method of generating a transcript according to an embodiment of the present application. As shown in fig. 1, the method comprises the steps of:
step S101, obtaining historical information in a historical inquiry process, wherein the historical information comprises historical voice information and/or historical text information, the historical voice information and/or the historical text information at least comprises target historical information, and the target historical information comprises a historical object element, a historical objective element, a historical subject element and a historical subjective element;
step S102, constructing an artificial intelligence model, wherein the artificial intelligence model is obtained by using a plurality of groups of training data for training, and each group of training data in the plurality of groups of training data comprises the historical information and the target historical information corresponding to the historical information;
specifically, the artificial intelligence model can be a linear regression model, a logistic regression model, a decision tree model, a She Beisi model, a deep neural network model, and the like.
Step S103, acquiring current information in the current inquiry process, wherein the current information comprises current voice information and/or current text information;
and step S104, extracting target current information from the current information by adopting the artificial intelligence model, and generating a record according to the target current information, wherein the target current information comprises a current object element, a current objective element, a current subject element and a current subjective element.
In the method, the historical information in the historical inquiry process is firstly acquired, then the artificial intelligence model is constructed, the current information in the current inquiry process is acquired, finally the target current information is extracted from the current information by adopting the artificial intelligence model, and the record is generated according to the target current information. According to the scheme, the artificial intelligence model is built to train the historical information and the target historical information corresponding to the historical information, the artificial intelligence model can be adopted to automatically extract the current target information in the current inquiry process, the structural expression of the current target information is formed, the record is generated, and the generated record is high in reliability.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.
In one embodiment of the present application, constructing an artificial intelligence model includes: and extracting the target history information in the history information, and training by using the history information and the target history information to obtain a plurality of artificial intelligence models, wherein each artificial intelligence model is obtained by using a plurality of groups of training data, and each group of training data in the plurality of groups of training data comprises the history information and the history information of a case of one case type, and the history information corresponds to the target history information. In this embodiment, for cases of different case types, corresponding artificial intelligence models may be constructed, so that the historical information of the cases of different case types and the target historical information corresponding to the historical information may be trained, and subsequently, the corresponding artificial intelligence models may be used for the cases of different case types to extract the target current information.
In addition, the artificial intelligence model needs to be trained in advance, and a plurality of real records of cases of different case types can be labeled manually by a manual expert to find out the expression of the target information under the case and labeled in a manner that the target information can be read by a machine learning algorithm, the labeled data is divided into a training set and a testing set, the two data sets do not have an intersection, and the two data sets are input into the artificial intelligence model for training. And performing supervised learning on the training set by using a machine learning algorithm to form a trained model, extracting target information from the test set, wherein compared with manual labeling, the accuracy of the model extraction result is higher than a preset threshold value, and the trained model can be used as a working model to extract the target information.
In another embodiment of the present application, the extracting target current information from the current information by using the artificial intelligence model, and generating a record according to the target current information includes: determining the case type corresponding to the current information; determining the artificial intelligence model corresponding to the current information according to the case type; and extracting the target current information from the current information by adopting the artificial intelligence model corresponding to the current information, and generating the record according to the target current information. In the embodiment, for the current information, the artificial intelligence model corresponding to the case type can be determined from the multiple artificial intelligence models according to the case type of the current case, so that the target current information can be extracted by adopting different artificial intelligence models according to different cases, the corresponding record can be generated more efficiently and accurately, and the generated record is further ensured to have higher reliability.
In another embodiment of the present application, in a case that there are a plurality of target current information, generating a record according to the target current information includes: acquiring a plurality of pieces of target current information, and sequencing the plurality of pieces of target current information according to the time sequence to obtain a plurality of pieces of sequenced target current information; and converting the sequenced current information of the plurality of targets to obtain target text information, and adding the target text information into a target template to generate the record. In this embodiment, for the target current information, a specific event actually has a timeline, and therefore, the target current information can be sorted according to the chronological order, so that the timeline of the target current information is clearer and clearer, and the generated record is more accurate.
For example, the target current information spoken by the respondent includes information a, information B and information C, the information a is "i go to supermarket at 10 o ' clock", the information B is "i am 8 o ' clock today", the information C is "i check out payment at 11 o ' clock", and the sequence of the sorted target current information should be information B, information a and information C, which is favorable for questioners to comb cases.
In order to detect the format and integrity of the record and further improve the reliability of the record so as to provide a basis for consistent and quantitative determination for questioners, in a specific embodiment of the present application, after converting the sorted current information of a plurality of targets to obtain target text information, adding the target text information to a target template, and generating the record, the method further includes: determining whether the record conforms to a preset format, and generating first prompt information under the condition that the record does not conform to the preset format; and determining whether the four-element attributes of the record are complete, and generating second prompt information under the condition that the four-element attributes of the record are incomplete.
In order to accurately determine whether identity and contradiction exist among the records of a plurality of target objects of the same case, further improve the reliability of the records, and provide a basis for consistent and quantitative determination for questioners, in another specific embodiment of the present application, a plurality of records are included in the records, one record is generated from current information of one target object in a current questioning process, target text information is obtained by converting the sorted current information of the plurality of targets, the target text information is added to a target template, and after the records are generated, the method further includes: acquiring similarity among a plurality of the records; generating third prompt information under the condition that the similarity is greater than or equal to a similarity threshold; and generating fourth prompting information when the similarity is smaller than the similarity threshold.
Specifically, in the actual inquiry process, a first record generated by the voice information spoken by the answerer, a second record generated by the voice information spoken by the questioner, and a third record generated by the voice information spoken by the witness person may be acquired, of course, if there are a plurality of answerers, there are a plurality of third records correspondingly, and the similarity among the first record, the second record, and the third record is acquired.
In another specific embodiment of the present application, after obtaining the current information in the current inquiry process, the method further includes: determining the language of the current information; and if the language is not the target language, performing speech recognition on the current speech information in the current information, performing machine translation on the current text information in the current information, and converting the current information in a non-target language into the current information in the target language. In this embodiment, in order to generate the record more efficiently, speech recognition may be performed on the current speech information, machine translation may be performed on the current text information, and if the current information is not in the target language, the current information is converted into the current information in the target language.
For example, in a query site, the language used by a questioner is chinese, and the language spoken by some questioned people is not chinese, and may be english, chinese, french, etc., in order to generate a transcript more efficiently to provide a basis for determining consistency and quantification of the content of the transcript, current speech information in a non-target language can be converted into current text information in a target language.
In another embodiment of the present application, after generating the record according to the target current information, the method further includes: and sending the record to display equipment so that the display equipment displays the record. In this embodiment, the record is sent to the display device, and the questioning person can know the target current information of the case more clearly according to the record displayed on the display device.
The embodiment of the present application further provides a device for assisting in generating a record, and it should be noted that the device for assisting in generating a record of the embodiment of the present application may be used to execute the method for assisting in generating a record provided by the embodiment of the present application. The following describes an apparatus for assisting in generating a record according to an embodiment of the present application.
Fig. 2 is a schematic diagram of an apparatus for assisting in generating a record according to an embodiment of the present application. As shown in fig. 2, the apparatus includes:
a first obtaining unit 10, configured to obtain history information in a history inquiry process, where the history information includes history voice information and/or history text information, and the history voice information and/or the history text information at least includes target history information, and the target history information includes a history object element, a history objective element, a history subject element, and a history subjective element;
a constructing unit 20, configured to construct an artificial intelligence model, where the artificial intelligence model is obtained by training using multiple sets of training data, and each set of training data in the multiple sets of training data includes the historical information and the target historical information corresponding to the historical information;
specifically, the artificial intelligence model can be a linear regression model, a logistic regression model, a decision tree model, a She Beisi model, a deep neural network model, and the like.
A second obtaining unit 30, configured to obtain current information in a current inquiry process, where the current information includes current voice information and/or current text information;
the first processing unit 40 is configured to extract target current information from the current information by using the artificial intelligence model, and generate a record according to the target current information, where the target current information includes a current object element, a current objective element, a current subject element, and a current subjective element.
In the device, the first acquisition unit acquires historical information in a historical inquiry process, the construction unit constructs an artificial intelligence model, the second acquisition unit acquires current information in the current inquiry process, and the first processing unit extracts target current information from the current information by adopting the artificial intelligence model and generates a record according to the target current information. According to the scheme, the artificial intelligence model is built to train the historical information and the target historical information corresponding to the historical information, the artificial intelligence model can be adopted to automatically extract the current target information in the current inquiry process, the structural expression of the current target information is formed, the record is generated, and the generated record is high in reliability.
In an embodiment of the application, the construction unit includes a construction module, and the construction module is configured to extract the target history information from the history information, and train the target history information using the history information to obtain a plurality of artificial intelligence models, where each artificial intelligence model is obtained by using a plurality of sets of training data, and each set of training data in the plurality of sets of training data includes the history information of a case of one type and the target history information corresponding to the history information. In the embodiment, for cases of different case types, corresponding artificial intelligence models can be constructed, so that historical information of cases of different case types and target historical information corresponding to the historical information can be trained, and then target current information can be extracted for cases of different case types by adopting corresponding artificial intelligence models.
In addition, the artificial intelligence model needs to be trained in advance, an artificial expert can be used for manually marking a plurality of real records of cases of different case types, the expression of target information under the case is found out, the records can be marked in a manner that a machine learning algorithm can read the records, marked data are divided into a training set and a testing set, the two data sets do not have an intersection, and the two data sets are input into the artificial intelligence model for training. And performing supervised learning on the training set by using a machine learning algorithm to form a trained model, extracting target information from the test set, wherein compared with manual labeling, the accuracy of the model extraction result is higher than a preset threshold value, and the trained model can be used as a working model to extract the target information.
In another embodiment of the present application, the first processing unit includes a first determining module, a second determining module and a first processing module, and the first determining module is configured to determine the type of the case corresponding to the current information; the second determining module is used for determining the artificial intelligence model corresponding to the current information according to the case type; the first processing module is used for extracting the target current information from the current information by adopting the artificial intelligence model corresponding to the current information, and generating the record according to the target current information. In the embodiment, for the current information, the artificial intelligence model corresponding to the case type can be determined from the multiple artificial intelligence models according to the case type of the current case, so that the target current information can be extracted by adopting different artificial intelligence models according to different cases, the corresponding record can be generated more efficiently and accurately, and the generated record is further ensured to have higher reliability.
In another embodiment of the application, when there are a plurality of pieces of target current information, the first processing unit includes an obtaining module and a second processing module, where the obtaining module is configured to obtain a plurality of pieces of target current information, sort the plurality of pieces of target current information according to a time sequence, and obtain a plurality of pieces of sorted target current information; the second processing module is used for converting the sequenced current information of the targets to obtain target text information, and adding the target text information into a target template to generate the stroke record. In this embodiment, for the target current information, a specific event actually has a timeline, and therefore, the target current information can be sorted according to the chronological order, so that the timeline of the target current information is clearer and clearer, and the generated record is more accurate.
For example, the target current information spoken by the respondent includes information a, information B and information C, the information a is "i go to supermarket at 10 o ' clock", the information B is "i am 8 o ' clock today", the information C is "i check out payment at 11 o ' clock", and the sequence of the sorted target current information should be information B, information a and information C, which is favorable for questioners to comb cases.
In order to detect the format and integrity of the record and further improve the reliability of the record so as to provide a basis for consistent and quantitative determination for questioners, in a specific embodiment of the present application, the apparatus further includes a second processing unit and a third processing unit, where the second processing unit is configured to convert the sorted current target information to obtain target text information, add the target text information to a target template, generate the record, determine whether the record conforms to a predetermined format, and generate first prompt information when the record does not conform to the predetermined format; the third processing unit is used for determining whether the four-element attributes of the record are complete or not, and generating second prompt information under the condition that the four-element attributes of the record are incomplete.
In order to accurately determine whether the same identity and contradiction exist among the records of a plurality of target objects of the same case, further improve the reliability of the records, and provide a basis for judging consistency quantification for questioners, in another specific embodiment of the present application, a plurality of records are provided, one record is generated by current information of one target object in the current inquiry process, the apparatus further includes a third obtaining unit, a first generating unit and a second generating unit, the third obtaining unit is configured to convert the sequenced target current information to obtain target text information, add the target text information to a target template, and obtain the similarity among the records after the records are generated; the first generating unit is used for generating third prompt information when the similarity is larger than or equal to a similarity threshold value; the second generating unit is used for generating fourth prompting information when the similarity is smaller than the similarity threshold.
Specifically, in the actual inquiry process, a first record generated by the voice information spoken by the answerer, a second record generated by the voice information spoken by the questioner, and a third record generated by the voice information spoken by the witness person may be acquired, of course, if there are a plurality of answerers, there are a plurality of third records correspondingly, and the similarity among the first record, the second record, and the third record is acquired.
In another specific embodiment of the present application, the apparatus further includes a determining unit and a fourth processing unit, where the determining unit is configured to determine a language of the current information after obtaining the current information in the current query process; the fourth processing unit is configured to perform speech recognition on the current speech information in the current information, perform machine translation on the current text information in the current information, and convert the current information in a non-target language into the current information in the target language, when the language is not the target language. In this embodiment, in order to generate the record more efficiently, the current voice information may be subjected to voice recognition, the current text information may be subjected to machine translation, and if the current information is not in the target language, the current information is converted into the current information in the target language.
For example, in a query site, the language used by a questioner is chinese, and the language spoken by some questioned people is not chinese, and may be english, chinese, french, etc., in order to generate a transcript more efficiently to provide a basis for determining consistency and quantification of the content of the transcript, current speech information in a non-target language can be converted into current text information in a target language.
In another embodiment of the present application, the apparatus further includes a sending unit, where the sending unit is configured to send the record to a display device after generating the record according to the target current information, so that the display device displays the record. In this embodiment, the record is sent to the display device, and the questioning person can know the target current information of the case more clearly according to the record displayed on the display device.
The device for generating the record comprises a processor and a memory, wherein the first acquiring unit, the constructing unit, the second acquiring unit, the first processing unit and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions.
The processor comprises a kernel, and the kernel calls the corresponding program unit from the memory. One or more kernels can be set, and target information is automatically extracted by adjusting kernel parameters, so that the reliability of the record is improved.
The memory may include volatile memory in a computer readable medium, random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip.
An embodiment of the present invention provides a computer-readable storage medium, on which a program is stored, where the program, when executed by a processor, implements the method for generating a record.
The embodiment of the invention provides a processor, which is used for running a program, wherein the method for generating the record is executed when the program runs.
The application also provides a record generating system, which comprises a microphone, a display device and a device for assisting in generating the record, wherein the device for assisting in generating the record is respectively communicated with the microphone and the display device, and the device for assisting in generating the record is used for executing any one of the methods.
In the system, as the method comprises any one of the methods, the method firstly acquires the historical information in the historical inquiry process, then constructs the artificial intelligence model, then acquires the current information in the current inquiry process, finally adopts the artificial intelligence model to extract the target current information from the current information, and generates the record according to the target current information. According to the scheme, the artificial intelligence model is constructed to train the historical information and the target historical information corresponding to the historical information, the artificial intelligence model can be adopted to automatically extract the current target information in the current inquiry process, the structural expression of the current target information is formed, the record is generated, and the generated record is high in reliability.
The embodiment of the invention provides equipment, which comprises a processor, a memory and a program which is stored on the memory and can run on the processor, wherein when the processor executes the program, at least the following steps are realized:
step S101, obtaining historical information in a historical inquiry process, wherein the historical information comprises historical voice information and/or historical text information, the historical voice information and/or the historical text information at least comprises target historical information, and the target historical information comprises a historical object element, a historical objective element, a historical subject element and a historical subjective element;
step S102, constructing an artificial intelligence model, wherein the artificial intelligence model is obtained by using a plurality of groups of training data for training, and each group of training data in the plurality of groups of training data comprises the historical information and the target historical information corresponding to the historical information;
step S103, acquiring current information in the current inquiry process, wherein the current information comprises current voice information and/or current text information;
and step S104, extracting target current information from the current information by adopting the artificial intelligence model, and generating a record according to the target current information, wherein the target current information comprises a current object element, a current objective element, a current subject element and a current subjective element.
The device herein may be a server, a PC, a PAD, a mobile phone, etc.
The present application further provides a computer program product adapted to perform a program of initializing at least the following method steps when executed on a data processing device:
step S101, obtaining historical information in a historical inquiry process, wherein the historical information comprises historical voice information and/or historical text information, the historical voice information and/or the historical text information at least comprises target historical information, and the target historical information comprises a historical object element, a historical objective element, a historical subject element and a historical subjective element;
step S102, constructing an artificial intelligence model, wherein the artificial intelligence model is obtained by using a plurality of groups of training data for training, and each group of training data in the plurality of groups of training data comprises the historical information and the target historical information corresponding to the historical information;
step S103, acquiring current information in the current inquiry process, wherein the current information comprises current voice information and/or current text information;
and step S104, extracting target current information from the current information by adopting the artificial intelligence model, and generating a record according to the target current information, wherein the target current information comprises a current object element, a current objective element, a current subject element and a current subjective element.
In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the embodiments provided in the present application, it should be understood that the disclosed technical content can be implemented in other manners. The above-described embodiments of the apparatus are merely illustrative, and for example, the above-described division of the units may be a logical division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed coupling or direct coupling or communication connection between each other may be an indirect coupling or communication connection through some interfaces, units or modules, and may be electrical or in other forms.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one position, or may be distributed on a plurality of units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention 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 can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit may be stored in a computer-readable storage medium if it is implemented in the form of a software functional unit and sold or used as a separate product. Based on such understanding, the technical solution of the present invention, which is substantially or partly contributed by the prior art, or all or part of the technical solution may be embodied in 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 perform 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 Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
From the above description, it can be seen that the above-described embodiments of the present application achieve the following technical effects:
1) The method for generating the record in an auxiliary mode comprises the steps of firstly obtaining historical information in a historical inquiry process, then constructing an artificial intelligence model, then obtaining current information in the current inquiry process, finally extracting target current information from the current information by adopting the artificial intelligence model, and generating the record according to the target current information. According to the scheme, the artificial intelligence model is built to train the historical information and the target historical information corresponding to the historical information, the artificial intelligence model can be adopted to automatically extract the current target information in the current inquiry process, the structural expression of the current target information is formed, the record is generated, and the generated record is high in reliability.
2) According to the device for assisting in generating the record, the first acquisition unit acquires historical information in a historical inquiry process, the construction unit constructs an artificial intelligence model, the second acquisition unit acquires current information in the current inquiry process, and the first processing unit extracts target current information from the current information by adopting the artificial intelligence model and generates the record according to the target current information. According to the scheme, the artificial intelligence model is built to train the historical information and the target historical information corresponding to the historical information, the artificial intelligence model can be adopted to automatically extract the current target information in the current inquiry process, the structural expression of the current target information is formed, the record is generated, and the generated record is high in reliability.
3) The record generation system comprises any one of the methods, and comprises any one of the methods, so that the method comprises the steps of firstly obtaining historical information in a historical inquiry process, then constructing an artificial intelligence model, then obtaining current information in a current inquiry process, finally extracting target current information from the current information by adopting the artificial intelligence model, and generating the record according to the target current information. According to the scheme, the artificial intelligence model is built to train the historical information and the target historical information corresponding to the historical information, the artificial intelligence model can be adopted to automatically extract the current target information in the current inquiry process, the structural expression of the current target information is formed, the record is generated, and the generated record is high in reliability.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (10)
1. A method for assisting in generating a transcript, comprising:
acquiring historical information in a historical inquiry process, wherein the historical information comprises historical voice information and/or historical text information, the historical voice information and/or the historical text information at least comprises target historical information, and the target historical information comprises a historical object element, a historical objective element, a historical subject element and a historical subjective element;
constructing an artificial intelligence model, wherein the artificial intelligence model is obtained by using a plurality of groups of training data for training, and each group of training data in the plurality of groups of training data comprises the historical information and the target historical information corresponding to the historical information;
acquiring current information in the current inquiry process, wherein the current information comprises current voice information and/or current text information;
and extracting target current information from the current information by adopting the artificial intelligence model, and generating a stroke record according to the target current information, wherein the target current information comprises a current object element, a current objective element, a current subject element and a current subjective element.
2. The method of claim 1, wherein building an artificial intelligence model comprises:
extracting the target historical information in the historical information, and training by adopting the historical information and the target historical information to obtain a plurality of artificial intelligence models, wherein each artificial intelligence model is obtained by training by using a plurality of groups of training data, and each group of training data in the plurality of groups of training data comprises the historical information of a case of one type and the historical information corresponding to the target historical information.
3. The method of claim 2, wherein extracting target current information from the current information using the artificial intelligence model and generating a transcript from the target current information comprises:
determining the case type corresponding to the current information;
determining the artificial intelligence model corresponding to the current information according to the case type;
and extracting the target current information from the current information by adopting the artificial intelligence model corresponding to the current information, and generating the record according to the target current information.
4. The method of claim 1, wherein generating a record according to the target current information when there are a plurality of target current information comprises:
acquiring a plurality of pieces of target current information, and sequencing the plurality of pieces of target current information according to the time sequence to obtain a plurality of pieces of sequenced target current information;
and converting the sequenced current information of the plurality of targets to obtain target text information, and adding the target text information into a target template to generate the record.
5. The method of claim 4, wherein after converting the sorted target current information into target text information, adding the target text information to a target template, and generating the entry, the method further comprises:
determining whether the record conforms to a preset format, and generating first prompt information under the condition that the record does not conform to the preset format;
and determining whether the four-element attributes of the record are complete, and generating second prompt information under the condition that the four-element attributes of the record are incomplete.
6. The method of claim 4, wherein there are a plurality of said records, one said record is generated from current information of a target object during a current query, the target text information is obtained by converting the sorted current information of the plurality of targets, the target text information is added to the target template, and after the record is generated, the method further comprises:
acquiring similarity among a plurality of the records;
generating third prompt information under the condition that the similarity is greater than or equal to a similarity threshold value;
and generating fourth prompt information under the condition that the similarity is smaller than the similarity threshold value.
7. The method according to any one of claims 1 to 6, wherein after obtaining current information in a current challenge process, the method further comprises:
determining the language of the current information;
and under the condition that the language is not the target language, performing voice recognition on the current voice information in the current information, performing machine translation on the current text information in the current information, and converting the current information in the non-target language into the current information in the target language.
8. The method of any one of claims 1 to 6, wherein after generating a transcript from the target current information, the method further comprises:
and sending the record to display equipment so that the display equipment displays the record.
9. An apparatus for assisting in generating a transcript, comprising:
the device comprises a first acquisition unit, a second acquisition unit and a third acquisition unit, wherein the first acquisition unit is used for acquiring historical information in a historical inquiry process, the historical information comprises historical voice information and/or historical text information, the historical voice information and/or the historical text information at least comprises target historical information, and the target historical information comprises a historical object element, a historical objective element, a historical subject element and a historical subjective element;
the artificial intelligence model is obtained by training a plurality of groups of training data, and each group of training data in the plurality of groups of training data comprises the historical information and the target historical information corresponding to the historical information;
the second acquisition unit is used for acquiring current information in the current inquiry process, wherein the current information comprises current voice information and/or current text information;
the first processing unit is used for extracting target current information from the current information by adopting the artificial intelligence model and generating a record according to the target current information, wherein the target current information comprises a current object element, a current objective element, a current subject element and a current subjective element.
10. A system for generating a transcript, comprising: a microphone, a display device, and means for assisting in generating a transcript, the means for assisting in generating a transcript being in communication with the microphone and the display device, respectively, the means for assisting in generating a transcript being operative to perform the method of any of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210753779.9A CN115248843A (en) | 2022-06-29 | 2022-06-29 | Method and device for assisting in generating record and record generating system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210753779.9A CN115248843A (en) | 2022-06-29 | 2022-06-29 | Method and device for assisting in generating record and record generating system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115248843A true CN115248843A (en) | 2022-10-28 |
Family
ID=83699671
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210753779.9A Pending CN115248843A (en) | 2022-06-29 | 2022-06-29 | Method and device for assisting in generating record and record generating system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115248843A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108197449A (en) * | 2017-12-27 | 2018-06-22 | 廖晓曦 | A kind of interrogation record device based on mobile terminal, system and its notes method |
-
2022
- 2022-06-29 CN CN202210753779.9A patent/CN115248843A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108197449A (en) * | 2017-12-27 | 2018-06-22 | 廖晓曦 | A kind of interrogation record device based on mobile terminal, system and its notes method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107492379B (en) | Voiceprint creating and registering method and device | |
| CN110781276B (en) | Text extraction method, device, equipment and storage medium | |
| CN109446302B (en) | Question-answer data processing method and device based on machine learning and computer equipment | |
| CN110263150B (en) | Text generation method, device, computer equipment and storage medium | |
| CN112346567B (en) | Virtual interaction model generation method and device based on AI (Artificial Intelligence) and computer equipment | |
| CN110909137A (en) | Information pushing method and device based on man-machine interaction and computer equipment | |
| CN110096570A (en) | A kind of intension recognizing method and device applied to intelligent customer service robot | |
| CN111128394B (en) | Medical text semantic recognition method and device, electronic equipment and readable storage medium | |
| CN107844481B (en) | Text recognition error detection method and device | |
| CN105095415A (en) | Method and apparatus for confirming network emotion | |
| CN110717021B (en) | Input text acquisition and related device in artificial intelligence interview | |
| CN111145903A (en) | Method and device for acquiring vertigo inquiry text, electronic equipment and inquiry system | |
| CN114626380A (en) | Entity identification method and device, electronic equipment and storage medium | |
| CN112632248A (en) | Question answering method, device, computer equipment and storage medium | |
| CN114647713A (en) | Knowledge graph question-answering method, device and storage medium based on virtual confrontation | |
| CN112364622A (en) | Dialog text analysis method, dialog text analysis device, electronic device and storage medium | |
| CN115248843A (en) | Method and device for assisting in generating record and record generating system | |
| CN109408175B (en) | Real-time interaction method and system in general high-performance deep learning calculation engine | |
| CN112581297B (en) | Information pushing method and device based on artificial intelligence and computer equipment | |
| CN112151034B (en) | Voice control method and device of equipment, electronic equipment and storage medium | |
| CN113051384A (en) | User portrait extraction method based on conversation and related device | |
| CN112434953A (en) | Customer service personnel assessment method and device based on computer data processing | |
| CN109033078B (en) | The recognition methods of sentence classification and device, storage medium, processor | |
| CN113342932B (en) | Target word vector determining method and device, storage medium and electronic device | |
| CN111680514A (en) | Information processing and model training method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |