CN110347784A - Report form inquiring method, device, storage medium and electronic equipment - Google Patents
Report form inquiring method, device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN110347784A CN110347784A CN201910435937.4A CN201910435937A CN110347784A CN 110347784 A CN110347784 A CN 110347784A CN 201910435937 A CN201910435937 A CN 201910435937A CN 110347784 A CN110347784 A CN 110347784A
- Authority
- CN
- China
- Prior art keywords
- report
- target report
- query
- target
- text
- 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 48
- 238000010801 machine learning Methods 0.000 claims abstract description 55
- 238000012549 training Methods 0.000 claims description 8
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 description 11
- 230000006870 function Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000013500 data storage Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000005291 magnetic effect Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 210000004027 cell Anatomy 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 239000000470 constituent Substances 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000003014 reinforcing effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 210000000352 storage cell Anatomy 0.000 description 1
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
- G06F16/332—Query formulation
-
- 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
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Machine Translation (AREA)
Abstract
The disclosure is directed to a kind of report form inquiring method, device, storage medium and electronic equipments, belong to machine learning applied technical field, this method comprises: converting text for the voice inquirement of the target report when the voice inquirement for receiving target report；From the text that the voice inquirement of the target report converts, the query language element for inquiring the target report is obtained；Trained machine learning model in advance is inputted using the query language element of the target report as input data, obtains the structured query sentence of the target report；The target report is inquired according to the structured query sentence of the target report.The disclosure realizes target report query by way of receiving voice inquirement, based on machine learning model, effectively increases the accuracy and search efficiency of report query.
Description
Technical field
This disclosure relates to which machine learning applied technical field, in particular to a kind of report form inquiring method, device, is deposited
Storage media and electronic equipment.
Background technique
Report is exactly with formats such as table, charts come Dynamically Announce data；Report query is exactly to be filled according to inquiry needs
Inquiry request, to inquire the report of desired data.
Currently, carrying out the inquiry of target report by complicated self-service query interface when carrying out report query, lead to
It crosses and clicks the information that preset check box etc. carries out selected target report, and then carry out the inquiry of target report.Alternatively, enclosing
The mode of SQL or the hand-written query intention of business personnel and then report backstage conversion SQL are write around Data Analyst to generate report
As a result.
In the prior art, it is inconvenient to carry out inquiry mode when report query, when the report for carrying out relatively detailed, specific data
When table is inquired, it is easy error, it is complicated for operation；Meanwhile when mobile terminal carries out report query, more inconvenient, accuracy rate is not high.
It should be noted that information is only used for reinforcing the reason to the background of the disclosure disclosed in above-mentioned background technology part
Solution, therefore may include the information not constituted to the prior art known to persons of ordinary skill in the art.
Summary of the invention
The disclosure is designed to provide a kind of report query scheme, and then is based at least to a certain extent by realizing
Accurate, the convenient inquiry mode of language in-put, effectively improves the accuracy rate and efficiency of report query.
According to one aspect of the disclosure, a kind of report form inquiring method is provided, comprising:
When the voice inquirement for receiving target report, text is converted by the voice inquirement of the target report；
From the text that the voice inquirement of the target report converts, the inquiry language for inquiring the target report is obtained
Say element；
Trained machine learning model in advance is inputted using the query language element of the target report as input data,
Obtain the structured query sentence of the target report；
The target report is inquired according to the structured query sentence of the target report.
In a kind of exemplary embodiment of the disclosure, which is characterized in that the voice inquirement of the target report be according to
Scheduled reference format input,
In the text that the voice inquirement from the target report converts, obtains and inquire looking into for the target report
Ask language elements, comprising:
According to the scheduled reference format, the corresponding reference format template of voice inquirement of the target report is obtained,
The reference format template includes the location information of query language element；
Using the location information of the query language element, the inquiry for inquiring the target report is obtained from the text
Language elements.
In a kind of exemplary embodiment of the disclosure, the text that is converted from the voice inquirement of the target report
In, obtain the query language element for inquiring the target report, comprising:
The text participle that the voice inquirement of the target report is converted, obtains each word for forming the text；
The each word for forming the text is matched with pre-set report query language elements table respectively, is obtained
To the word for the composition text being matched to；
By the word of the composition text being matched to, as the query language element for inquiring the target report.
In a kind of exemplary embodiment of the disclosure, the training method of the machine learning model, comprising:
The query language element sample set of report is collected, the query language element sample of the report has demarcated correspondence in advance
Report structured query sentence；
The query language element sample of each report is inputted into machine learning model as input data respectively, is obtained
The structured query sentence of the corresponding report of query language element sample of each report；
If there is the sample, after inputting machine learning model, the structured query sentence of obtained report with to institute
The structured query sentence for stating the report that sample is demarcated in advance is inconsistent, then the coefficient of machine learning model is adjusted, until consistent.
If all samples, input machine learning model after, the structured query sentence of obtained report with to institute
The structured query sentence for the report for having the sample to demarcate in advance is consistent, and training terminates.
In a kind of exemplary embodiment of the disclosure, using the query language element of the target report as input data
Trained machine learning model in advance is inputted, the structured query sentence of the target report is obtained, comprising:
The term vector of the corresponding word of query language element of each target report is inquired from term vector dictionary；
By the term vector of the corresponding word of query language element of each target report, according to each target
Sequence of the query language element of report in the text in institute source, is sequentially connected in series as vector string as pre-input data；
The pre-input data are inputted into trained machine learning model in advance, obtain the structuring of the target report
Query statement.
In a kind of exemplary embodiment of the disclosure, using the query language element of the target report as input data
Trained machine learning model in advance is inputted, the structured query sentence of the target report is obtained, comprising:
The term vector of the corresponding word of query language element of each target report is inquired from term vector dictionary；
By the term vector of the corresponding word of query language element of each target report, according to random order,
Series connection is vector string as pre-input data；
The pre-input data are inputted into trained machine learning model in advance, obtain the structuring of the target report
Query statement.
In a kind of exemplary embodiment of the disclosure, it is provided with voice inquirement formatting hints interface in advance, feature exists
In also being wrapped before converting text for the voice inquirement of the target report when the voice inquirement that receive target report
It includes:
When the report speech polling for detecting user is requested, report query token sound format is shown in the inquiry
In phonetic matrix prompting interface, to prompt user according to the voice inquirement of reference format input target report.
According to one aspect of the disclosure, a kind of report query device is provided, comprising:
Conversion module, for when the voice inquirement for receiving target report, the voice inquirement of the target report to be converted
For text；
Module is obtained, for obtaining and inquiring the mesh from the text that the voice inquirement of the target report converts
Mark the query language element of report；
Judgment module, for the query language element of the target report is trained in advance as input data input
Machine learning model obtains the structured query sentence of the target report；
Enquiry module, for inquiring the target report according to the structured query sentence of the target report.
According to one aspect of the disclosure, a kind of computer readable storage medium is provided, report query journey is stored thereon with
Sequence, which is characterized in that the report query program realizes method described in any of the above embodiments when being executed by processor.
According to one aspect of the disclosure, a kind of electronic equipment is provided characterized by comprising
Processor；And
Memory, for storing the report query program of the processor；Wherein, the processor is configured to via execution
The report query program executes method described in any of the above embodiments.
A kind of report form inquiring method of the disclosure and device, firstly, when the voice inquirement for receiving target report, by the mesh
The voice inquirement of mark report is converted into text；By receiving report query voice, the friendship of the inquiry of report can be easily carried out
Mutually, meanwhile, the information of target report can accurately be obtained from text by converting text for voice.Then, from the target
In the text that the voice inquirement of report converts, the query language element for inquiring the target report is obtained；It is converted from voice
In obtained text, the language elements of the needs of inquiry target report are got, can be protected under the premise of excluding useless text
Demonstrate,prove the accuracy rate according to query language element inquiry target report.Using the query language element of the target report as input number
According to trained machine learning model in advance is inputted, the structured query sentence of the target report is obtained；By trained
Machine learning model can accurately and efficiently get the structured query sentence of inquiry target report.Finally, according to described
The structured query sentence of target report inquires the target report；Measured structured query sentence can accurately from
Report data save location inquires target report.
It should be understood that above general description and following detailed description be only it is exemplary and explanatory, not
The disclosure can be limited.
Detailed description of the invention
The drawings herein are incorporated into the specification and forms part of this specification, and shows the implementation for meeting the disclosure
Example, and together with specification for explaining the principles of this disclosure.It should be evident that the accompanying drawings in the following description is only the disclosure
Some embodiments for those of ordinary skill in the art without creative efforts, can also basis
These attached drawings obtain other attached drawings.
Fig. 1 schematically shows a kind of flow chart of report form inquiring method.
Fig. 2 schematically shows a kind of Application Scenarios-Example figure of report form inquiring method.
Fig. 3 schematically shows the method flow diagram that a kind of query language element of target report obtains.
Fig. 4 schematically shows a kind of block diagram of report query device.
Fig. 5 schematically shows a kind of electronic equipment example block diagram for realizing above-mentioned report form inquiring method.
Fig. 6 schematically shows a kind of computer readable storage medium for realizing above-mentioned report form inquiring method.
Specific embodiment
Example embodiment is described more fully with reference to the drawings.However, example embodiment can be with a variety of shapes
Formula is implemented, and is not understood as limited to example set forth herein；On the contrary, thesing embodiments are provided so that the disclosure will more
Fully and completely, and by the design of example embodiment comprehensively it is communicated to those skilled in the art.Described feature, knot
Structure or characteristic can be incorporated in any suitable manner in one or more embodiments.In the following description, it provides perhaps
More details fully understand embodiment of the present disclosure to provide.It will be appreciated, however, by one skilled in the art that can
It is omitted with technical solution of the disclosure one or more in the specific detail, or others side can be used
Method, constituent element, device, step etc..In other cases, be not shown in detail or describe known solution to avoid a presumptuous guest usurps the role of the host and
So that all aspects of this disclosure thicken.
In addition, attached drawing is only the schematic illustrations of the disclosure, it is not necessarily drawn to scale.Identical attached drawing mark in figure
Note indicates same or similar part, thus will omit repetition thereof.Some block diagrams shown in the drawings are function
Energy entity, not necessarily must be corresponding with physically or logically independent entity.These function can be realized using software form
Energy entity, or these functional entitys are realized in one or more hardware modules or integrated circuit, or at heterogeneous networks and/or place
These functional entitys are realized in reason device device and/or microcontroller device.
Report form inquiring method is provided firstly in this example embodiment, the service which can run on
Device can also run on server cluster or Cloud Server etc., and certainly, those skilled in the art can also be according to demand at other
Platform runs method of the invention, and particular determination is not done to this in the present exemplary embodiment.Refering to what is shown in Fig. 1, the report query
Method may comprise steps of:
Step S110 converts text for the voice inquirement of the target report when the voice inquirement for receiving target report
This；
Step S120 is obtained from the text that the voice inquirement of the target report converts and is inquired the target report
The query language element of table；
The query language element of the target report is inputted trained machine in advance by step S130
Learning model obtains the structured query sentence of the target report；
Step S140 inquires the target report according to the structured query sentence of the target report.
In above-mentioned report form inquiring method, firstly, when the voice inquirement for receiving target report, by looking into for the target report
It askes voice and is converted into text；By reception report query voice, the interaction of the inquiry of report can be easily carried out, meanwhile, it will
Voice is converted into text can accurately obtain the information of target report from text.Then, from the inquiry of the target report
In the text that voice converts, the query language element for inquiring the target report is obtained；The text converted from voice
In, the language elements of the needs of inquiry target report are got, can be guaranteed under the premise of excluding useless text according to inquiry
The accuracy rate of language elements inquiry target report.The query language element of the target report is preparatory as input data input
Trained machine learning model obtains the structured query sentence of the target report；Pass through trained machine learning mould
Type can accurately and efficiently get the structured query sentence of inquiry target report.Finally, according to the target report
Structured query sentence inquires the target report；Measured structured query sentence can be protected accurately from report data
Position enquiring is deposited to target report.
In the following, will be carried out in conjunction with attached drawing to each step in report form inquiring method above-mentioned in this example embodiment detailed
Explanation and explanation.
In step s 110, when the voice inquirement for receiving target report, the voice inquirement of the target report is converted
For text.
In this exemplary embodiment, refering to what is shown in Fig. 2, server 201 receives the target of the transmission of terminal device 202
After the voice inquirement of report, text is converted for voice by speech recognition.Wherein, server 201 can be it is any have hold
The terminal, such as mobile phone, computer etc. of line program instruction；Terminal device 202 can be any with application system execution, instruction hair
Send terminal of function, such as mobile phone, computer etc..When needing from the position enquiring target report of storage report, pass through voice
Mode gives expression to the voice inquirement of target report, so that it may without many and diverse report query such as being manually entered or being clicked
Process, such as pass through the selection picture frame of repeatedly click selection target report on report query interface.Speech polling is convenient, simple
It is single, high-efficient.After receiving the voice inquirement of report, need to be converted into structured query sentence in the next steps, with into
Row report query, so needing to convert textual form for voice inquirement；Turning text techniques using existing voice can be accurate
Realization speech-to-text original text conversion.For example, " me please be help to inquire the finance of the third season of company A speech form
Report " is converted into " me please be helped to inquire the financial statement of the third season of company A " of textual form.
In the step s 120, it from the text that the voice inquirement of the target report converts, obtains and inquires the mesh
Mark the query language element of report；
In this exemplary embodiment, after converting text for the voice inquirement of target report, so that it may according to text
The query demand of form carries out the generation of the structured query sentence of target report query.One complete structuring of composition is looked into
Sentence is ask, complete query path is needed, in the text for needing voice inquirement to convert, comprising can accurately inquire target
The nodal information in the path of report, that is, the query language element of the target report is inquired, for example, it is desired to inquire company A
The third season financial statement, it is necessary to three nodal informations, that is, inquire the company A the third season finance report
The query language element of table, because the storage of report is typically all to store according to corresponding node hierarchy.Wherein, the A is inquired
The query language element of the financial statement of the third season of company just includes: " company A " " third season " " financial statement ", in this way
It just can accurately inquire target report.It is obtained from the text that the voice inquirement of target report converts and inquires the target
The query language element of report, so that it may conveniently according to query language element, accurately and efficiently generate structuralized query
Sentence.
In a kind of originally exemplary embodiment, the voice inquirement of the target report is that format is defeated according to predetermined criteria
Enter, in the text that the voice inquirement from the target report converts, obtains the inquiry for inquiring the target report
Language elements, comprising:
According to the scheduled reference format, the corresponding reference format template of voice inquirement of the target report is obtained,
The reference format template includes the location information of query language element；
Using the location information of the query language element, the inquiry for inquiring the target report is obtained from the text
Language elements.
The voice inquirement of target report is that format inputs according to predetermined criteria, i.e. user in input inquiry voice,
The selected reference format for meeting user query demand of selective listing for selection criteria format is first passed through, for example, " me please be help to look into
Ask (finance) report of (secondary unit) of (level-one unit) " or " me please be help to inquire (secondary unit) of (level-one unit)
The reference formats such as (Item Detail) report of (three-level unit) ".Each scheduled reference format is associated with a reference format template,
For example, " me please be helped to inquire (finance) report of (secondary unit) of (level-one unit) " associated reference format template is that " please help
I inquires the * * * report of the * * * of * * * ".It in this way can be automatic according to scheduled reference format of the user in input inquiry voice
Obtain the corresponding reference format template of voice inquirement of target report.
Reference format template is for example: " me please be helped to inquire the * * * report of the * * * of * * * " * * * therein identifies inquiry language
Say the location information of element.When the voice of user's input are as follows: " me please be help to inquire the financial statement of the third season of company A "；Just
Reference format template be can use from the text that the voice that user inputs is converted to, it is corresponding accurately to get the position * * *
Query language element, such as: " company A " " third season " " financial statement ".
In a kind of originally exemplary embodiment, from the text that the voice inquirement of the target report converts, obtain
Take the query language element for inquiring the target report, including step S310, S320 and step S330:
Step S310, the text that the voice inquirement of the target report is converted segment, obtain forming the text
Each word；
Step S320, will form each word of the text respectively with pre-set report query language elements table into
Row matching, the word for the composition text being matched to；
Step S330, by the word of the composition text being matched to, as the inquiry language for inquiring the target report
Say element.
Text participle is exactly that one section of text is divided into several words using existing participle technique, for example, when user inputs
Input voice are as follows: " financial statement, the third season of company A, me please be help to inquire ", the input of compromise arbitrarily format；Turn
The text got in return be also " financial statement, the third season of company A, please help I inquire ".Text participle can be obtained
To the word for the text being converted to, such as " financial statement ", " company A ", " ", " third season ", " ", " asking ", " side ",
" I ", " inquiry ".Pre-set report query language elements table exactly contains all such as filenames or storage road
The table of the word of report data is inquired in diameter node name etc., by pre-set report query language elements table and forms text
Each word is matched respectively, the word for the composition text that may be matched, that is, is present in report query language
Include: in word in element table, such as report query language elements table " company A " " third season " " financial statement "；And then it can
With " company A " " third season " " financial statement " being accurately matched in the word for forming text, as query language element, row
Except other useless vocabulary, accuracy rate is high.It is effectively ensured in subsequent step simultaneously and obtains looking into for target report with query language element
Ask language.
In step s 130, trained in advance using the query language element of the target report as input data input
Machine learning model obtains the structured query sentence of the target report；
In this exemplary embodiment, by preparatory training machine learning model, directly by the inquiry language of target report
It says that the conduct input data of element inputs trained machine learning model, accurately and efficiently generates the structure of target report
Change query statement, avoids through manual behaviors such as clicks, it is efficiently convenient.Wherein, query language element is defeated as input data
The method entered is exactly that the pre-input data that can be used as input machine learning model of query language element are carried out input machine
Learning model, term vector of the word of for example each query language element of pre-input data in term vector dictionary, such as " third quarter
The term vector " 12355685 " of degree ".Wherein, the structured query sentence of target report is exactly a kind of query language, for example,
The Select financial statement from company A where name=' third season '；And then it can be accurate according to structured query language
Ground carries out inquiring target report by file designation from report data storage location.
In a kind of originally exemplary embodiment, the training method of the machine learning model, comprising:
The query language element sample set of report is collected, the query language element sample of the report has demarcated correspondence in advance
Report structured query sentence；
The query language element sample of each report is inputted into machine learning model as input data respectively, is obtained
The structured query sentence of the corresponding report of query language element sample of each report；
If there is the sample, after inputting machine learning model, the structured query sentence of obtained report with to institute
The structured query sentence for stating the report that sample is demarcated in advance is inconsistent, then the coefficient of machine learning model is adjusted, until consistent.
If all samples, input machine learning model after, the structured query sentence of obtained report with to institute
The structured query sentence for the report for having the sample to demarcate in advance is consistent, and training terminates.
The query language element of report, such as usually there is the name rank of strict standard when report data storage, it is identical
The filename of rank is the word of same alike result, for example, the filename of second level is all company name.By collecting various combinations
Query language element sample, carrying out machine learning model training can accurately train to according to the corresponding report of various samples output
The structured query sentence of table.Wherein, query language element be exactly as input data input machine learning model can be quasi-
Really the pre-input data of input machine learning model are inputted, and the word of for example each query language element of pre-input data is in word
Term vector in vector dictionary, such as the term vector " 12355685 " of " third season ", when inputting machine learning model, each
The corresponding term vector of query language element can be random sequence input, be also possible to input in a certain order.
In a kind of originally exemplary embodiment, inputted the query language element of the target report as input data
Preparatory trained machine learning model, obtains the structured query sentence of the target report, comprising:
The term vector of the corresponding word of query language element of each target report is inquired from term vector dictionary；
By the term vector of the corresponding word of query language element of each target report, according to each target
Sequence of the query language element of report in the text in institute source, is sequentially connected in series as vector string as pre-input data；
The pre-input data are inputted into trained machine learning model in advance, obtain the structuring of the target report
Query statement.
Term vector of the word of each query language element in term vector dictionary, is exactly the term vector of such as " third season "
" 12355685 ", each word have unique corresponding term vector, it is ensured that machine learning model is accurately calculated.It will be every
The term vector of the corresponding word of query language element of a target report, is coming according to the query language element of each target report
Sequence in the text in source is sequentially connected in series as vector string as pre-input data；Each word has individual term vector, random to connect
Obtained vector string to a certain extent can also be with accurate characterization query intention.Then machine learning model is inputted, it can be in mesh
When text of the query language element of mark report in institute source is scheduled reference format, guarantee machine learning to a certain extent
The accuracy of the structured query sentence of model output.
It is in a kind of originally exemplary embodiment, the conduct input data of the query language element of the target report is defeated
Enter preparatory trained machine learning model, obtain the structured query sentence of the target report, comprising:
The term vector of the corresponding word of query language element of each target report is inquired from term vector dictionary；
By the term vector of the corresponding word of query language element of each target report, according to random order,
Series connection is vector string as pre-input data；
The pre-input data are inputted into trained machine learning model in advance, obtain the structuring of the target report
Query statement.
Term vector of the word of each query language element in term vector dictionary, is exactly the term vector of such as " third season "
" 12355685 ", each word have unique corresponding term vector, it is ensured that machine learning model is accurately calculated.By institute
The term vector for stating the corresponding word of query language element of each target report is connected according to random order as vector string
As pre-input data, machine learning model is then inputted, in machine learning model is instructed according to the term vector string of random sequence
In the case where white silk, it is ensured that, can also be with when the text in the query language element source of target report does not have standard input format
Accurately obtain the structured query sentence of the target report.
In step S140, the target report is inquired according to the structured query sentence of the target report.
In this exemplary embodiment, the structured query sentence of target report is exactly a kind of query language, for example,
The Select financial statement from company A where name=' third season '；And then it can be accurate according to structured query language
Ground carries out inquiring target report by file designation from report data storage location, thus can be easily according to various
Intricately query demand accurately obtains target report.
In a kind of originally exemplary embodiment, it is provided with voice inquirement formatting hints interface in advance, which is characterized in that
When the voice inquirement for receiving target report, convert the voice inquirement of the target report to before text, further includes:
When the report speech polling for detecting user is requested, report query token sound format is shown in the inquiry
In phonetic matrix prompting interface, to prompt user according to the voice inquirement of reference format input target report.
When the report speech polling for detecting user is requested, report query token sound format is shown in voice inquirement
On formatting hints interface, report query token sound format is exactly for example, me please be helped to inquire the finance report of the third season of company A
Table；User only needs to read according to inquiry needs: me please be helped to inquire the * * * report of the * * * of * * *；And then it can accurately parse
Inquiry request out, convenient for the accurate acquisition of query language element.
The disclosure additionally provides a kind of report query device.Refering to what is shown in Fig. 4, the report query device may include conversion
Module 410 obtains module 420, judgment module 430 and enquiry module 440.Wherein:
Conversion module 410 can be used for when the voice inquirement for receiving target report, by the inquiry language of the target report
Sound is converted into text；
Obtaining module 420 can be used for from the text that the voice inquirement of the target report converts, and obtain inquiry
The query language element of the target report；
Judgment module 430 can be used for inputting instruction in advance for the query language element of the target report as input data
The machine learning model perfected obtains the structured query sentence of the target report；
Enquiry module 440 can be used for inquiring the target report according to the structured query sentence of the target report.
The detail of each module has carried out in corresponding report form inquiring method in detail in above-mentioned report query device
Thin description, therefore details are not described herein again.
It should be noted that although being referred to several modules or list for acting the equipment executed in the above detailed description
Member, but this division is not enforceable.In fact, according to embodiment of the present disclosure, it is above-described two or more
Module or the feature and function of unit can embody in a module or unit.Conversely, an above-described mould
The feature and function of block or unit can be to be embodied by multiple modules or unit with further division.
In addition, although describing each step of method in the disclosure in the accompanying drawings with particular order, this does not really want
These steps must be executed in this particular order by asking or implying, or having to carry out step shown in whole could realize
Desired result.Additional or alternative, it is convenient to omit multiple steps are merged into a step and executed by certain steps, and/
Or a step is decomposed into execution of multiple steps etc..
Through the above description of the embodiments, those skilled in the art is it can be readily appreciated that example described herein is implemented
Mode can also be realized by software realization in such a way that software is in conjunction with necessary hardware.Therefore, according to the disclosure
The technical solution of embodiment can be embodied in the form of software products, which can store non-volatile at one
Property storage medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) in or network on, including some instructions are so that a calculating
Equipment (can be personal computer, server, mobile terminal or network equipment etc.) is executed according to disclosure embodiment
Method.
In an exemplary embodiment of the disclosure, a kind of electronic equipment that can be realized the above method is additionally provided.
Person of ordinary skill in the field it is understood that various aspects of the invention can be implemented as system, method or
Program product.Therefore, various aspects of the invention can be embodied in the following forms, it may be assumed that complete hardware embodiment, complete
The embodiment combined in terms of full Software Implementation (including firmware, microcode etc.) or hardware and software, can unite here
Referred to as circuit, " module " or " system ".
The electronic equipment 500 of this embodiment according to the present invention is described referring to Fig. 5.The electronics that Fig. 5 is shown
Equipment 500 is only an example, should not function to the embodiment of the present invention and use scope bring any restrictions.
As shown in figure 5, electronic equipment 500 is showed in the form of universal computing device.The component of electronic equipment 500 can wrap
It includes but is not limited to: at least one above-mentioned processing unit 510, at least one above-mentioned storage unit 520, the different system components of connection
The bus 530 of (including storage unit 520 and processing unit 510).
Wherein, the storage unit is stored with program code, and said program code can be held by the processing unit 510
Row, so that various according to the present invention described in the execution of the processing unit 510 above-mentioned " illustrative methods " part of this specification
The step of illustrative embodiments.For example, the processing unit 510 can execute step S110 as shown in fig. 1: working as reception
To the voice inquirement of target report, text is converted by the voice inquirement of the target report；S120: from the target report
In the text that voice inquirement converts, the query language element for inquiring the target report is obtained；Step S130: by the mesh
The query language element for marking report inputs trained machine learning model in advance as input data, obtains the target report
Structured query sentence；Step S140: the target report is inquired according to the structured query sentence of the target report.
Storage unit 520 may include the readable medium of volatile memory cell form, such as Random Access Storage Unit
(RAM) 5201 and/or cache memory unit 5202, it can further include read-only memory unit (ROM) 5203.
Storage unit 520 can also include program/utility with one group of (at least one) program module 5205
5204, such program module 5205 includes but is not limited to: operating system, one or more application program, other program moulds
It may include the realization of network environment in block and program data, each of these examples or certain combination.
Bus 530 can be to indicate one of a few class bus structures or a variety of, including storage unit bus or storage
Cell controller, peripheral bus, graphics acceleration port, processing unit use any bus structures in a variety of bus structures
Local bus.
Electronic equipment 500 can also be with one or more external equipments 700 (such as keyboard, sensing equipment, bluetooth equipment
Deng) communication, the equipment that also client can be enabled interact with the electronic equipment 500 with one or more communicates, and/or with make
Any equipment (such as the router, modulation /demodulation that the electronic equipment 500 can be communicated with one or more of the other calculating equipment
Device etc.) communication.This communication can be carried out by input/output (I/O) interface 550.Also, electronic equipment 500 can be with
By network adapter 560 and one or more network (such as local area network (LAN), wide area network (WAN) and/or public network,
Such as internet) communication.As shown, network adapter 560 is communicated by bus 530 with other modules of electronic equipment 500.
It should be understood that although not shown in the drawings, other hardware and/or software module can not used in conjunction with electronic equipment 500, including but not
Be limited to: microcode, device driver, redundant processing unit, external disk drive array, RAID system, tape drive and
Data backup storage system etc..
Through the above description of the embodiments, those skilled in the art is it can be readily appreciated that example described herein is implemented
Mode can also be realized by software realization in such a way that software is in conjunction with necessary hardware.Therefore, according to the disclosure
The technical solution of embodiment can be embodied in the form of software products, which can store non-volatile at one
Property storage medium (can be CD-ROM, USB flash disk, mobile hard disk etc.) in or network on, including some instructions are so that a calculating
Equipment (can be personal computer, server, terminal installation or network equipment etc.) is executed according to disclosure embodiment
Method.
In an exemplary embodiment of the disclosure, a kind of computer readable storage medium is additionally provided, energy is stored thereon with
Enough realize the program product of this specification above method.In some possible embodiments, various aspects of the invention may be used also
In the form of being embodied as a kind of program product comprising program code, when described program product is run on the terminal device, institute
Program code is stated for executing the terminal device described in above-mentioned " illustrative methods " part of this specification according to this hair
The step of bright various illustrative embodiments.
Refering to what is shown in Fig. 6, describing the program product for realizing the above method of embodiment according to the present invention
600, can using portable compact disc read only memory (CD-ROM) and including program code, and can in terminal device,
Such as it is run on PC.However, program product of the invention is without being limited thereto, in this document, readable storage medium storing program for executing can be with
To be any include or the tangible medium of storage program, the program can be commanded execution system, device or device use or
It is in connection.
Described program product can be using any combination of one or more readable mediums.Readable medium can be readable letter
Number medium or readable storage medium storing program for executing.Readable storage medium storing program for executing for example can be but be not limited to electricity, magnetic, optical, electromagnetic, infrared ray or
System, device or the device of semiconductor, or any above combination.The more specific example of readable storage medium storing program for executing is (non exhaustive
List) include: electrical connection with one or more conducting wires, portable disc, hard disk, random access memory (RAM), read-only
Memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disc read only memory
(CD-ROM), light storage device, magnetic memory device or above-mentioned any appropriate combination.
Computer-readable signal media may include in a base band or as carrier wave a part propagate data-signal,
In carry readable program code.The data-signal of this propagation can take various forms, including but not limited to electromagnetic signal,
Optical signal or above-mentioned any appropriate combination.Readable signal medium can also be any readable Jie other than readable storage medium storing program for executing
Matter, the readable medium can send, propagate or transmit for by instruction execution system, device or device use or and its
The program of combined use.
The program code for including on readable medium can transmit with any suitable medium, including but not limited to wirelessly, have
Line, optical cable, RF etc. or above-mentioned any appropriate combination.
The program for executing operation of the present invention can be write with any combination of one or more programming languages
Code, described program design language include object oriented program language-Java, C++ etc., further include conventional
Procedural programming language-such as " C " language or similar programming language.Program code can be fully in client
It calculates and executes in equipment, partly executes on the client device, being executed as an independent software package, partially in client's calculating
Upper side point is executed on a remote computing or is executed in remote computing device or server completely.It is being related to far
Journey calculates in the situation of equipment, and remote computing device can pass through the network of any kind, including local area network (LAN) or wide area network
(WAN), it is connected to client computing device, or, it may be connected to external computing device (such as utilize ISP
To be connected by internet).
In addition, above-mentioned attached drawing is only the schematic theory of processing included by method according to an exemplary embodiment of the present invention
It is bright, rather than limit purpose.It can be readily appreciated that the time that above-mentioned processing shown in the drawings did not indicated or limited these processing is suitable
Sequence.In addition, be also easy to understand, these processing, which can be, for example either synchronously or asynchronously to be executed in multiple modules.
Those skilled in the art after considering the specification and implementing the invention disclosed here, will readily occur to its of the disclosure
His embodiment.This application is intended to cover any variations, uses, or adaptations of the disclosure, these modifications, purposes or
Adaptive change follow the general principles of this disclosure and including the undocumented common knowledge in the art of the disclosure or
Conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the disclosure are by claim
It points out.
Claims (10)
1. a kind of report form inquiring method characterized by comprising
When the voice inquirement for receiving target report, text is converted by the voice inquirement of the target report；
From the text that the voice inquirement of the target report converts, the query language for obtaining the inquiry target report is wanted
Element；
Trained machine learning model in advance is inputted using the query language element of the target report as input data, is obtained
The structured query sentence of the target report；
The target report is inquired according to the structured query sentence of the target report.
2. the method according to claim 1, wherein the voice inquirement of the target report is according to scheduled mark
Quasiconfiguaration input；
In the text that the voice inquirement from the target report converts, the inquiry language for inquiring the target report is obtained
Say element, comprising:
According to the scheduled reference format, the corresponding reference format template of voice inquirement of the target report is obtained, it is described
Reference format template includes the location information of query language element；
Using the location information of the query language element, the query language for inquiring the target report is obtained from the text
Element.
3. the method according to claim 1, wherein the text converted from the voice inquirement of the target report
In this, the query language element for inquiring the target report is obtained, comprising:
The text participle that the voice inquirement of the target report is converted, obtains each word for forming the text；
The each word for forming the text is matched with pre-set report query language elements table respectively, is obtained
The word for the composition text being fitted on；
By the word of the composition text being matched to, as the query language element for inquiring the target report.
4. the method according to claim 1, wherein the training method of the machine learning model, comprising:
The query language element sample set of report is collected, the query language element sample of the report has demarcated corresponding report in advance
The structured query sentence of table；
Machine learning model is inputted using the query language element sample of each report as input data, is obtained each described
The structured query sentence of the corresponding report of query language element sample of report；
If there is the sample, after inputting machine learning model, the structured query sentence of obtained report with to the sample
The structured query sentence of this report demarcated in advance is inconsistent, then the coefficient of machine learning model is adjusted, until consistent.
If all samples, input machine learning model after, the structured query sentence of obtained report with to all institutes
The structured query sentence for stating the report that sample is demarcated in advance is consistent, and training terminates.
5. the method according to claim 1, wherein it is described using the query language element of the target report as
Input data inputs trained machine learning model in advance, obtains the structured query sentence of the target report, comprising:
The term vector of the corresponding word of query language element of each target report is inquired from term vector dictionary；
By the term vector of the corresponding word of query language element of each target report, according to each target report
Sequence of the query language element in the text in institute source, be sequentially connected in series as vector string as pre-input data；
The pre-input data are inputted into trained machine learning model in advance, obtain the structuralized query of the target report
Sentence.
6. the method according to claim 1, wherein it is described using the query language element of the target report as
Input data inputs trained machine learning model in advance, obtains the structured query sentence of the target report, comprising:
The term vector of the corresponding word of query language element of each target report is inquired from term vector dictionary；
By the term vector of the corresponding word of query language element of each target report, according to random order, series connection
It is vector string as pre-input data；
The pre-input data are inputted into trained machine learning model in advance, obtain the structuralized query of the target report
Sentence.
7. according to the method described in claim 1, being provided with voice inquirement formatting hints interface in advance, which is characterized in that in institute
It states when the voice inquirement for receiving target report, converts the voice inquirement of the target report to before text, further includes:
When the report speech polling for detecting user is requested, report query token sound format is shown in the voice inquirement
On formatting hints interface, to prompt user according to the voice inquirement of reference format input target report.
8. a kind of report query device characterized by comprising
Conversion module, for converting text for the voice inquirement of the target report when the voice inquirement for receiving target report
This；
Module is obtained, for obtaining and inquiring the target report from the text that the voice inquirement of the target report converts
The query language element of table；
Judgment module, for inputting trained machine in advance for the query language element of the target report as input data
Learning model obtains the structured query sentence of the target report；
Enquiry module, for inquiring the target report according to the structured query sentence of the target report.
9. a kind of computer readable storage medium is stored thereon with report query program, which is characterized in that the report query journey
Claim 1-7 described in any item methods are realized when sequence is executed by processor.
10. a kind of electronic equipment characterized by comprising
Processor；And
Memory, for storing the report query program of the processor；Wherein, the processor is configured to via described in execution
Report query program carrys out perform claim and requires the described in any item methods of 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910435937.4A CN110347784A (en) | 2019-05-23 | 2019-05-23 | Report form inquiring method, device, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910435937.4A CN110347784A (en) | 2019-05-23 | 2019-05-23 | Report form inquiring method, device, storage medium and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110347784A true CN110347784A (en) | 2019-10-18 |
Family
ID=68173962
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910435937.4A Pending CN110347784A (en) | 2019-05-23 | 2019-05-23 | Report form inquiring method, device, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110347784A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110909127A (en) * | 2019-11-07 | 2020-03-24 | 中铁大桥科学研究院有限公司 | Method and system for inputting and inquiring bridge inspection information |
| CN111063340A (en) * | 2019-12-09 | 2020-04-24 | 用友网络科技股份有限公司 | Service processing method and device of terminal, terminal and computer readable storage medium |
| CN111062803A (en) * | 2019-12-04 | 2020-04-24 | 中国银行股份有限公司 | Financial business query and review method and system |
| CN111159220A (en) * | 2019-12-31 | 2020-05-15 | 北京百度网讯科技有限公司 | Method and apparatus for outputting structured query statement |
| CN111209367A (en) * | 2019-12-03 | 2020-05-29 | 泰康保险集团股份有限公司 | Information searching method, information searching device, electronic equipment and storage medium |
| CN111597776A (en) * | 2020-04-01 | 2020-08-28 | 深圳壹账通智能科技有限公司 | Self-adaptive form retrieval method, device, medium and electronic equipment |
| CN112069206A (en) * | 2020-03-31 | 2020-12-11 | 北京来也网络科技有限公司 | Data query method, device, medium and computing device based on RPA and AI |
| CN114201525A (en) * | 2022-02-15 | 2022-03-18 | 支付宝(杭州)信息技术有限公司 | Method and device for querying data |
| WO2022105493A1 (en) * | 2020-11-17 | 2022-05-27 | 深圳壹账通智能科技有限公司 | Semantic recognition-based data query method and apparatus, device and storage medium |
| CN116013296A (en) * | 2023-03-28 | 2023-04-25 | 国网浙江省电力有限公司营销服务中心 | Searching method based on computer natural language processing |
| CN116542800A (en) * | 2023-06-29 | 2023-08-04 | 天津星耀九洲科技有限公司 | Intelligent financial statement analysis system based on cloud AI technology |
-
2019
- 2019-05-23 CN CN201910435937.4A patent/CN110347784A/en active Pending
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110909127A (en) * | 2019-11-07 | 2020-03-24 | 中铁大桥科学研究院有限公司 | Method and system for inputting and inquiring bridge inspection information |
| CN111209367A (en) * | 2019-12-03 | 2020-05-29 | 泰康保险集团股份有限公司 | Information searching method, information searching device, electronic equipment and storage medium |
| CN111062803A (en) * | 2019-12-04 | 2020-04-24 | 中国银行股份有限公司 | Financial business query and review method and system |
| CN111063340A (en) * | 2019-12-09 | 2020-04-24 | 用友网络科技股份有限公司 | Service processing method and device of terminal, terminal and computer readable storage medium |
| CN111159220A (en) * | 2019-12-31 | 2020-05-15 | 北京百度网讯科技有限公司 | Method and apparatus for outputting structured query statement |
| CN112069206A (en) * | 2020-03-31 | 2020-12-11 | 北京来也网络科技有限公司 | Data query method, device, medium and computing device based on RPA and AI |
| CN112069206B (en) * | 2020-03-31 | 2022-02-22 | 北京来也网络科技有限公司 | Data query method, device, medium and computing device based on RPA and AI |
| CN111597776A (en) * | 2020-04-01 | 2020-08-28 | 深圳壹账通智能科技有限公司 | Self-adaptive form retrieval method, device, medium and electronic equipment |
| WO2022105493A1 (en) * | 2020-11-17 | 2022-05-27 | 深圳壹账通智能科技有限公司 | Semantic recognition-based data query method and apparatus, device and storage medium |
| CN114201525A (en) * | 2022-02-15 | 2022-03-18 | 支付宝(杭州)信息技术有限公司 | Method and device for querying data |
| CN114201525B (en) * | 2022-02-15 | 2022-05-20 | 支付宝(杭州)信息技术有限公司 | Method and device for querying data |
| CN116013296A (en) * | 2023-03-28 | 2023-04-25 | 国网浙江省电力有限公司营销服务中心 | Searching method based on computer natural language processing |
| CN116013296B (en) * | 2023-03-28 | 2023-05-30 | 国网浙江省电力有限公司营销服务中心 | Searching method based on computer natural language processing |
| CN116542800A (en) * | 2023-06-29 | 2023-08-04 | 天津星耀九洲科技有限公司 | Intelligent financial statement analysis system based on cloud AI technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110347784A (en) | Report form inquiring method, device, storage medium and electronic equipment | |
| CN107657017B (en) | Method and apparatus for providing voice service | |
| US11537798B2 (en) | Method and apparatus for generating dialogue model | |
| CN109325091B (en) | Method, device, equipment and medium for updating attribute information of interest points | |
| US10008204B2 (en) | Information processing system, and vehicle-mounted device | |
| US10706085B2 (en) | Method and system for exposing virtual assistant services across multiple platforms | |
| CN109961792A (en) | The method and apparatus of voice for identification | |
| EP3591338A2 (en) | Navigation method, navigation device, device and medium | |
| US20220358292A1 (en) | Method and apparatus for recognizing entity, electronic device and storage medium | |
| CN110502227A (en) | The method and device of code completion, storage medium, electronic equipment | |
| CN111508479A (en) | Voice recognition method, device, equipment and storage medium | |
| US20200184960A1 (en) | Rnnlm-based generation of templates for class-based text generation | |
| US11403462B2 (en) | Streamlining dialog processing using integrated shared resources | |
| CN111104796B (en) | Method and device for translation | |
| US20230108637A1 (en) | Generating sorted lists of chat bot design nodes using escalation logs | |
| CN117251557B (en) | Legal consultation sentence reply method, device, equipment and computer readable medium | |
| CN108491387B (en) | Method and apparatus for outputting information | |
| EP3843090B1 (en) | Method and apparatus for outputting analysis abnormality information in spoken language understanding | |
| US10991370B2 (en) | Speech to text conversion engine for non-standard speech | |
| US11195102B2 (en) | Navigation and cognitive dialog assistance | |
| JP7349523B2 (en) | Speech recognition method, speech recognition device, electronic device, storage medium computer program product and computer program | |
| KR20160101302A (en) | System and Method for Summarizing and Classifying Details of Consultation | |
| WO2021051565A1 (en) | Machine learning-based semantic parsing method and apparatus, electronic device, and computer non-volatile readable storage medium | |
| CN109036379B (en) | Speech recognition method, apparatus and storage medium | |
| CN106933999B (en) | Apache lucene score highlighting method for independent search |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 201, room 518000, building A, No. 1, front Bay Road, Qianhai Shenzhen Guangdong Shenzhen Hong Kong cooperation zone (Qianhai business secretary) Applicant after: Shenzhen one ledger Intelligent Technology Co., Ltd. Address before: 518000 Guangdong city of Shenzhen province Qianhai Shenzhen Hong Kong cooperation zone before Bay Road No. 1 building 201 room A Applicant before: Shenzhen one ledger Intelligent Technology Co., Ltd. |
|
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |