CN109816423A - Product programming method and server based on speech recognition - Google Patents
Product programming method and server based on speech recognition Download PDFInfo
- Publication number
- CN109816423A CN109816423A CN201811530409.9A CN201811530409A CN109816423A CN 109816423 A CN109816423 A CN 109816423A CN 201811530409 A CN201811530409 A CN 201811530409A CN 109816423 A CN109816423 A CN 109816423A
- Authority
- CN
- China
- Prior art keywords
- product
- product attribute
- speech recognition
- attribute
- text information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Abstract
The product programming method based on speech recognition that the invention discloses a kind of, this method comprises: obtaining the voice messaging of Category of consulting message registration;It is identified as text information and searches INQUIRE statement therein;Sort out the regular product attribute identified in the INQUIRE statement according to preset;The classification and number of the product attribute in all INQUIRE statements are counted, and carries out number sequence, the forward product attribute classification of selected and sorted carries out product programming suggestion.The present invention also provides a kind of device, server and computer readable storage mediums.Product programming method, apparatus, server and computer readable storage medium provided by the invention based on speech recognition can identify voice messaging, then count the classification and number of the product attribute identified;Then the forward product attribute classification of selected and sorted carries out product programming suggestion, so that telephone service is also product programming acquisition market information while answering customer problem, to improve the output of telephone service.
Description
Technical field
The present invention relates to voice semantic technology field more particularly to a kind of product programming methods based on speech recognition, dress
It sets, server and computer readable storage medium.
Background technique
In order to answer the various accidents of user, and the complaint suggestion of processing user, many businessmans can provide round-the-clock
Telephone consultation service.However, essentially all of businessman can provide telephone service generally only as just the work of consulting
With, or reconcile the complaint of user and set up.Moreover, the time spent by a logical consulting class phone is often also long
, therefore the cost of telephone service is not perhaps reciprocity with income.In consideration of it, the present invention will propose that one kind maximally utilizes phone
Service, to reduce cost shared by telephone service indirectly.
Summary of the invention
In view of this, the present invention propose a kind of user by the product programming method, apparatus of speech recognition, server and based on
Calculation machine readable storage medium storing program for executing can identify the voice messaging of Category of consulting, to identify INQUIRE statement institute therein
Including product attribute, then count the classification and number of product attribute therein;According to the product attribute classification and number
Product programming suggestion is carried out, so that telephone service is also product programming acquisition market letter while answering customer problem
Breath, to improve the output of telephone service.
Firstly, to achieve the above object, the present invention provides a kind of product programming method based on speech recognition, this method is answered
For server, which comprises
Obtain the voice messaging of Category of consulting message registration;The voice messaging is identified to obtain corresponding text
Information;Search the INQUIRE statement in the text information;Sort out rule according to preset product attribute and identifies the inquiry language
Product attribute in sentence;Count the classification and number of the product attribute that all INQUIRE statements occur in the text information;According to
The number is ranked up the product attribute of each classification, and the forward product attribute classification of selected and sorted carries out product programming and builds
View.
Optionally, " the regular product category identified in the INQUIRE statement is sorted out according to preset product attribute described
Before property " step, further comprises the steps of: and record all product product attributes, and obtain the keyword of each product attribute;Setting produces
Product attribute sorts out rule are as follows: when the pass of keyword group and the product attribute in the text information for identifying the INQUIRE statement
When key word is consistent, then the keyword group is classified as the product attribute.
Optionally, the step of described " voice messaging for obtaining Category of consulting message registration " includes: according to preset consulting
The channel of dialling in of classification message registration filters out Category of consulting message registration in the message registration.
Optionally, the step of described " searching the INQUIRE statement in the text information ", comprising steps of the text is believed
Breath carries out text with preset inquiry keyword and compares, and finding out in the text information includes the inquiry for inquiring keyword
Ask sentence.
In addition, to achieve the above object, the present invention also provides a kind of product programming device based on speech recognition, the dress
It sets and includes:
Module is obtained, for obtaining the voice messaging of Category of consulting message registration;Identification module, for believing the voice
Breath is identified to obtain corresponding text information;Searching module, for searching the INQUIRE statement in the text information;Identification
Module is also used to sort out the regular product attribute identified in the INQUIRE statement according to preset product attribute;Statistical module,
For counting the classification and number of the product attribute that all INQUIRE statements occur in the text information;Suggestion module is used for root
It is ranked up according to product attribute of the number to each classification, the forward product attribute classification of selected and sorted carries out product programming
It is recommended that.
Optionally, the identification module is also used to: being recorded all product product attributes, and is obtained the pass of each product attribute
Key word;Be arranged product attribute sort out rule are as follows: when in the text information for identifying the INQUIRE statement keyword group with it is described
When the keyword of product attribute is consistent, then the keyword group is classified as the product attribute.
Optionally, the acquisition module is also used to: being filtered out according to the channel of dialling in of preset Category of consulting message registration
Category of consulting message registration in the message registration.
Optionally, the searching module is also used to: the text information and preset inquiry keyword are carried out text ratio
Right, finding out in the text information includes the INQUIRE statement for inquiring keyword.
Further, the present invention also proposes that a kind of server, the server include memory, processor, the storage
It is stored with the product programming program based on speech recognition that can be run on the processor on device, it is described based on speech recognition
It realizes when product programming program is executed by the processor such as the step of the above-mentioned product programming method based on speech recognition.
Further, to achieve the above object, the present invention also provides a kind of computer readable storage medium, the computers
Readable storage medium storing program for executing is stored with the product programming program based on speech recognition, and the product programming program based on speech recognition can
It is executed by least one processor, so that at least one described processor executes such as the above-mentioned product programming based on speech recognition
The step of method.
Compared to the prior art, the product programming method, apparatus proposed by the invention based on speech recognition, server and
Computer readable storage medium can identify the voice messaging of Category of consulting, to identify INQUIRE statement therein
Then included product attribute counts the classification and number of product attribute therein;According to the product attribute classification and time
Number carries out product programming suggestion, so that telephone service is also product programming acquisition market letter while answering customer problem
Breath, to improve the output of telephone service.
Detailed description of the invention
Fig. 1 is the schematic diagram of the optional hardware structure of server one of the present invention;
Fig. 2 is the program module schematic diagram of one embodiment of product programming program the present invention is based on speech recognition;
Fig. 3 is the flow diagram of one embodiment of product programming method the present invention is based on speech recognition.
Appended drawing reference:
The object of the invention is realized, the embodiments will be further described with reference to the accompanying drawings for functional characteristics and advantage.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that described herein, specific examples are only used to explain the present invention, not
For limiting the present invention.Based on the embodiments of the present invention, those of ordinary skill in the art are not before making creative work
Every other embodiment obtained is put, shall fall within the protection scope of the present invention.
It should be noted that the description for being related to " first ", " second " etc. in the present invention is used for description purposes only, and cannot
It is interpreted as its relative importance of indication or suggestion or implicitly indicates the quantity of indicated technical characteristic.Define as a result, " the
One ", the feature of " second " can explicitly or implicitly include at least one of the features.In addition, the skill between each embodiment
Art scheme can be combined with each other, but must be based on can be realized by those of ordinary skill in the art, when technical solution
Will be understood that the combination of this technical solution is not present in conjunction with there is conflicting or cannot achieve when, also not the present invention claims
Protection scope within.
As shown in fig.1, being the schematic diagram of the optional hardware structure of server 1 one of the present invention.
The server 1 can be rack-mount server, blade server, tower server or Cabinet-type server etc.
Equipment is calculated, which can be independent server, be also possible to server cluster composed by multiple servers.
In the present embodiment, the server 1 may include, but be not limited only to, and can be in communication with each other connection by system bus and deposit
Reservoir 11, processor 12, network interface 13.
The server 1 connects network (Fig. 1 is not marked) by network interface 13, by network connection to other systems or
Person's terminal such as recording system, the end PC, mobile terminal etc..The network can be intranet (Intranet), internet
(Internet), global system for mobile communications (Global System of Mobile communication, GSM), broadband code
Divide multiple access (Wideband Code Division Multiple Access, WCDMA), 4G network, 5G network, bluetooth
(Bluetooth), the wirelessly or non-wirelessly network such as Wi-Fi, speech path network.
It should be pointed out that Fig. 1 illustrates only the server 1 with component 11-13, it should be understood that simultaneously should not
Realistic to apply all components shown, the implementation that can be substituted is more or less component.
Wherein, the memory 11 includes at least a type of readable storage medium storing program for executing, and the readable storage medium storing program for executing includes
Flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory etc.), random access storage device (RAM), it is static with
Machine accesses memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable
Read memory (PROM), magnetic storage, disk, CD etc..In some embodiments, the memory 11 can be the clothes
The internal storage unit of business device 1, such as the hard disk or memory of the server 1.In further embodiments, the memory 11
It can be the External memory equipment of the server 1, such as the plug-in type hard disk that the server 1 is equipped with, intelligent memory card
(Smart Media Card, SMC), secure digital (Secure Digital, SD) card, flash card (Flash Card) etc..When
So, the memory 11 can also both including the server 1 internal storage unit and also including its External memory equipment.This reality
It applies in example, the memory 11 is installed on the operating system and types of applications software of the server 1 commonly used in storage, such as
The program code etc. of product programming program based on speech recognition.In addition, the memory 11 can be also used for temporarily storing
The Various types of data that has exported or will export.
The processor 12 can be in some embodiments central processing unit (Central Processing Unit,
CPU), controller, microcontroller, microprocessor or other data processing chips.The processor 12 is commonly used in the control clothes
The overall operation of business device 1, such as execute data interaction or the relevant control of communication and processing etc..In the present embodiment, the place
Reason device 12 is used to run the program code stored in the memory 11 or processing data, such as based on voice described in operation
Product programming program of identification etc..
The network interface 13 may include radio network interface or wired network interface, which is commonly used in
Communication is established at the server 1 and other systems such as recording system or other terminal devices such as end PC between mobile terminal etc.
Connection.
In the present embodiment, when being installed in the server 1 and running the product programming program based on speech recognition, when
It is described based on speech recognition product programming program operation when, the server 1 can by connection recording system or other
The terminal device such as end PC, mobile terminal etc. can also obtain Category of consulting in the storage unit by the server 1 itself
Then the voice messaging of message registration identifies the voice messaging of Category of consulting, to identify INQUIRE statement therein
Then included product attribute counts the classification and number of product attribute therein;According to the product attribute classification and time
Number carries out product programming suggestion, so that telephone service is also product programming acquisition market letter while answering customer problem
Breath, to improve the output of telephone service.
So far, oneself is through describing the application environment of each embodiment of the present invention and the hardware configuration and function of relevant device in detail
Energy.In the following, above-mentioned application environment and relevant device will be based on, each embodiment of the invention is proposed.
Firstly, the present invention proposes a kind of product programming program based on speech recognition.
As shown in fig.2, being the Program modual graph of one embodiment of product programming program the present invention is based on speech recognition.
In the present embodiment, the product programming program based on speech recognition includes a series of is stored on memory 11
Computer program instructions, when the computer program instructions by processor 12 execute when, various embodiments of the present invention may be implemented
Product programming operation based on speech recognition.In some embodiments, it is realized based on the computer program instructions each section
Specific operation, the product programming program based on speech recognition can be divided into one or more modules.For example, in Fig. 2,
The product programming program based on speech recognition, which can be divided into, obtains module 201, identification module 202, searching module
203, statistical module 204 and suggestion module 205.Wherein:
The acquisition module 201, for obtaining the voice messaging of Category of consulting message registration.
Specifically, the acquisition module 201 can by the recording system of connection or other terminal devices such as end PC,
Mobile terminal etc. in the storage unit by the server 1 itself, can also obtain the voice letter of Category of consulting message registration
Breath.In the present embodiment, it is described obtain module 201 according to preset Category of consulting message registration dial in channel filter out it is described
Category of consulting message registration in message registration.Specifically, the acquisition module 201 is searched and is consulted in all message registrations
The message registration of classification is ask, then the voice messaging in the message registration of acquisition each Category of consulting, and the Category of consulting
Call, then be according to dialling in channel and confirmed in call-information.Such as: channel packet is dialled in Category of consulting call
It includes: the phone that user is come in by customer service dial;Either user passes through the visitor on product official website or the relevant APP of product
Take the call transferred after icon is clicked;Or contact staff complete with after the voice communication of user actively by the call
The call of Category of consulting label on recording mark.Therefore, when the server 1 receives the request of the data analysis of user's sending
Afterwards, the acquisition module 201 can then search the message registration of Category of consulting in the database for including all message registrations, so
Obtain the voice messaging of the message registration of the Category of consulting of each respectively afterwards.
The identification module 202, for being identified to the voice messaging to obtain corresponding text information.
Specifically, after the acquisition module 201 gets the voice messaging of Category of consulting message registration, the identification mould
Block 202 identifies the voice messaging according to existing semantics recognition technology, to obtain corresponding text information.
The searching module 203, for searching the INQUIRE statement in the text information.
Specifically, the message registration of Category of consulting is all being identified and is being converted to text information by the identification module 202
Afterwards, the searching module 203 can also further respectively carry out each text information according to common word, word, phrase format
It divides, is divided into keyword group, whether includes then preset according to the keyword group in the text information of the Category of consulting
Inquiry keyword is to judge whether the voice messaging is INQUIRE statement.In the present embodiment, 203 basis of searching module
The text information is divided into the keyword group including at least a keyword by syntax rule, then again by the keyword group
It is compared with preset inquiry keyword, for example presetting inquiry keyword includes: " may I ask ", " either with or without " and " can
With ... ", when in the corresponding keyword group of the text information include the inquiry keyword, such as include above three inquiry
Ask that any of keyword then judges that the text information is INQUIRE statement.Wherein, the syntax rule is to combine dictionary number
According to library and user's word used in everyday, word, phrase be accustomed to caused by database and the common word, word, short that is counted
Language format.
The identification module 202 is also used to sort out rule according to preset product attribute and identify in the INQUIRE statement
Product attribute.
Specifically, product is provided to meet the needs of users and design.In general, the demand of user all can
Including multiple refinement demands;Correspondingly, the product that can satisfy user demand also generally will include multiple product attributes, and each
A refinement demand in user demand can accordingly be realized or be met to product attribute.In the present embodiment, the production
Product attribute includes such as realizing function, durable value, price and applicable object.However, due to different users, it is required
Refinement demand is simultaneously different, and therefore, the product attribute that required product includes is also different.That is, what product included
Multiple product attributes wherein perhaps a certain product attribute meets the needs of some of users, but are unsatisfactory for other user
Demand.Accordingly, it is determined that go out can satisfy most users demand product attribute be for product programming it is necessary to
's.
Therefore, in the present embodiment, the identification module 202 will be firstly the need of will include that all product attribute is united in product
Meter comes out, and obtains the keyword of each product attribute.For example, it includes 5 that the identification module 202, which gets insurance products A,
A product attribute are as follows: (applicable age) 0-10 years old, (applicable gender) male, (area of application) Guangdong Province, (applicable) unexpected and (suitable
With) disease;Insurance products B includes 3 product attributes are as follows: (applicable age) 35-50 years old, (be applicable in occupation) office office worker and
(applicable) occupational disease.So the product attribute inventory according to made of product A and B includes: (applicable age) 0-10 years old, (applicability
Not) male, (area of application) Guangdong Province, (applicable) accident, (applicable) disease, (applicable age) 35-50 years old, (being applicable in occupation) office
Office worker and (applicable) occupational disease.In addition, in the design of product or planning process, for the refinement function of user may be implemented
Product attribute can also be added in product attribute inventory although being not applied in product on sale.Such as: (it is applicable in year
Age) 0-10 years old, (applicable age) 10-20 years old, (applicable age) 20-35 years old, (applicable age) 50-65 years old and (applicable gender) female
Etc..Then, since the title of product attribute is generally all different, product attribute name can be referred to as to the product attribute
Keyword.
Then, the identification module 202 can also preset product attribute classification rule.In the present embodiment, described to return
Rule-like is used to the text information received being referred to product attribute, such as: for (applicable age) 0-10 years old, (applicability
Not) male, (area of application) Guangdong Province, (applicable) unexpected and (applicable) disease, then can be set classification rule: recognizing in 0-10
Any one number and " year " either " age " or " age " be then classified as product attribute: (applicable age) 0-10 years old;Work as identification
When to other urban district titles in " Guangdong " or " Shenzhen ", " Guangzhou " and subordinate Guangdong Province, then it is classified as product attribute: (is applicable in
Area) Guangdong Province;When recognizing " accident ", then it is classified as product attribute: (applicable) unexpected;When recognizing " disease ", then divide
Class is product attribute: (applicable) disease.Then, the identification module 202 is according to the rule of sorting out to the text letter received
Breath is sorted out, for example, when identifying that the keyword group in the text information is consistent with the keyword of the product attribute,
The keyword group is then classified as the product attribute.
Finally, the identification module 202 the searching module 203 find out all inquiries in the voice messaging
After sentence, the regular product attribute identified in the INQUIRE statement is sorted out according to the product attribute.
The statistical module 204, for counting the class for the product attribute that all INQUIRE statements occur in the text information
Other and number.
Specifically, after the identification module 202 identifies the product attribute occurred in the INQUIRE statement, the system
Meter module 204 is then recorded, and recognizes the product category occurred in the INQUIRE statement every time in the identification module 202
Property, the statistical module 204 is intended to be recorded.Therefore, the statistical module 204 can count in the text information and own
The classification for the product attribute for including in INQUIRE statement and corresponding number.
The suggestion module 205, for being ranked up according to product attribute of the number to each classification, selected and sorted
Forward product attribute classification carries out product programming suggestion.
The statistical module 204 count the product attribute occurred in INQUIRE statement classification and corresponding number it
Afterwards, after the completion of the suggestion module 205 can then count the number that each product attribute occurs in text information, further according to every
The number that a product attribute occurs is ranked up the product attribute, sorts forward, illustrates that user demand is more, then can be with
The design that the product attribute carries out Related product is perhaps planned or be can be used for improve or adjusting the production of current production
The structure of product attribute provides foundation.In the present embodiment, the forward product attribute classification of the selected and sorted carries out product programming
It is recommended that including being overlapped the forward product attribute of the sequence and the major product attribute as planning product, then should
Planning product model is exported.Such as: it only include " (applicable age) 0-10 years old " and " (applicable) disease in existing insurance products
The product of disease " product attribute, but the message registration of the Category of consulting according to statistics, wherein there is " (applicable age) 0-10 years old "
Before the number highest of " (being applicable in) unexpected ", sequence most, therefore system can be according to the statistical result, and suitably providing will be " (suitable
Use the age) 0-10 years old " and " (being applicable in) unexpected " major product attribute as planning product, then output includes " (applicable year
Age) 0-10 years old " and " (being applicable in) unexpected " product model.Certainly, other product attributes of the planning product then need subsequent
It is supplemented.
It will be recalled from above that the server 1 is by connection recording system or other terminal devices such as end PC, it is mobile whole
End etc. can also obtain the voice messaging of Category of consulting message registration, so in the storage unit by the server 1 itself
The voice messaging of Category of consulting is identified afterwards, to identify product attribute included by INQUIRE statement therein, then
Count the classification and number of product attribute therein;Product programming suggestion is carried out according to the product attribute classification and number, from
And telephone service is made also to be product programming acquisition market information while answering customer problem, to improve telephone service
Output.
Certainly, in other embodiments, a base also can be set into the product programming program based on speech recognition
In the product programming device of speech recognition, which includes all program moulds of the product programming program based on speech recognition
The one-to-one functional module of block.The product programming device based on speech recognition can be used as independent product attribute and be attached to
On server or other terminal devices or the network equipment, in order to be to voice messaging and carry out product programming.
In addition, the present invention also proposes that a kind of product programming method based on speech recognition, the method are applied to server.
As shown in fig.3, being the flow diagram of one embodiment of product programming method the present invention is based on speech recognition.?
In the present embodiment, the execution sequence of the step in flow chart shown in Fig. 3 be can change according to different requirements, certain steps
It can be omitted.
Step S500 obtains the voice messaging of Category of consulting message registration.
Specifically, the server can be mobile whole by the recording system of connection or other terminal devices such as end PC
End etc. can also obtain the voice messaging of Category of consulting message registration in the storage unit by the server itself.At this
In embodiment, the server filters out in the message registration according to the channel of dialling in of preset Category of consulting message registration
Category of consulting message registration.Specifically, in all message registrations, the message registration of Category of consulting is searched, is then obtained every
Voice messaging in the message registration of one Category of consulting, and the call of the Category of consulting, then be according in call-information
Channel is dialled in be confirmed.Such as: the channel of dialling in of Category of consulting call includes: that user is come in by customer service dial
Phone;The either call that user transfers after being clicked by the customer service icon on product official website or the relevant APP of product;
Or the message registration is actively marked the logical of upper Category of consulting label after completing the voice communication with user by contact staff
Words.It therefore, then can include all message registrations after the server receives the request of data analysis of user's sending
Database in search Category of consulting message registration, then respectively obtain each Category of consulting message registration voice
Information.
Step S502 identifies the voice messaging to obtain corresponding text information.
It specifically, then can be according to existing semantics recognition technology to described after getting the voice messaging of Category of consulting
Voice messaging is identified, to obtain corresponding text information.
Step S504 searches the INQUIRE statement in the text information.
It specifically, can also further root after all identifying the message registration of Category of consulting and being converted to text information
Each text information is divided respectively according to common word, word, phrase format, is divided into keyword group, then according to institute
State whether the keyword group in the text information of Category of consulting includes preset inquiry keyword to judge the voice messaging
It whether is INQUIRE statement.In the present embodiment, the text information can be divided into including at least one according to syntax rule
Then the keyword group is compared again with preset inquiry keyword, for example presets by the keyword group of keyword
Inquiry keyword includes: " may I ask ", " either with or without " and " can with ... ", is wrapped when in the corresponding keyword group of the text information
The inquiry keyword is included, for example then judges the text information for inquiry including any of above three inquiry keyword
Sentence.Wherein, the syntax rule is in conjunction with produced by dictionary database and user's word used in everyday, word, phrase habit
Database and the common word, word, the phrase format that are counted.
Step S506 sorts out the regular product attribute identified in the INQUIRE statement according to preset product attribute.
Specifically, product is provided to meet the needs of users and design.In general, the demand of user all can
Including multiple refinement demands;Correspondingly, the product that can satisfy user demand also generally will include multiple product attributes, and each
A refinement demand in user demand can accordingly be realized or be met to product attribute.In the present embodiment, the production
Product attribute includes such as realizing function, durable value, price and applicable object.However, due to different users, it is required
Refinement demand is simultaneously different, and therefore, the product attribute that required product includes is also different.That is, what product included
Multiple product attributes wherein perhaps a certain product attribute meets the needs of some of users, but are unsatisfactory for other user
Demand.Accordingly, it is determined that go out can satisfy most users demand product attribute be for product programming it is necessary to
's.
Therefore, in the present embodiment, it is necessary first to will include that all product attributes come out, and obtain every in product
The keyword of a product attribute.For example, getting insurance products A includes 5 product attributes are as follows: (applicable age) 0-10 years old,
(applicable gender) male, (area of application) Guangdong Province, (applicable) unexpected and (applicable) disease;Insurance products B includes 3 product categories
Property are as follows: (applicable age) 35-50 years old, (being applicable in occupation) office office worker and (applicable) occupational disease.So it is made according to product A and B
Product attribute inventory include: (applicable age) 0-10 years old, (applicable gender) male, (area of application) Guangdong Province, it is (applicable) it is unexpected,
(applicable) disease, (applicable age) 35-50 years old, (being applicable in occupation) office office worker and (applicable) occupational disease.In addition, setting in product
In meter or planning process, the product attribute of the refinement function for user may be implemented, although being not applied to production on sale
In product, it can also be added in product attribute inventory.Such as: (applicable age) 0-10 years old, (applicable age) 10-20 years old (are applicable in
Age) 20-35 years old, (applicable age) 50-65 years old and (applicable gender) female etc..Then, since the title of product attribute is general
It is all different, therefore product attribute name can be referred to as to the keyword of the product attribute.
Then, the server can also preset product attribute classification rule.In the present embodiment, the classification rule
For the text information received to be referred to product attribute, such as: for (applicable age) 0-10 years old, (applicable gender) male,
(area of application) Guangdong Province, (applicable) unexpected and (applicable) disease, then can be set classification rule: recognizing any of 0-10
Number and " year " either " age " or " age " be then classified as product attribute: (applicable age) 0-10 years old;It is " wide when recognizing
When other urban district titles in east " or " Shenzhen ", " Guangzhou " and subordinate Guangdong Province, then it is classified as product attribute: (area of application)
Guangdong Province;When recognizing " accident ", then it is classified as product attribute: (applicable) unexpected;When recognizing " disease ", then it is classified as producing
Product attribute: (applicable) disease.
Then, the text information received is sorted out according to the classification rule, for example, when identifying the text
When keyword group in information is consistent with the keyword of the product attribute, then the keyword group is classified as the product category
Property.Finally, sorting out the regular product attribute identified in the INQUIRE statement according to the product attribute.
Step S508 counts the classification and number of the product attribute that all INQUIRE statements occur in the text information.
Specifically, it after the product attribute occurred in identifying the INQUIRE statement, while also will record,
In, the product attribute occurred in recognizing the INQUIRE statement every time is intended to be recorded.Therefore, therefore, the server
Can count the product attribute for including in all INQUIRE statements in the text information classification and corresponding number.
Step S510 is ranked up according to product attribute of the number to each classification, the forward product of selected and sorted
Attribute classification carries out product programming suggestion.
After the classification of the product attribute occurred in counting INQUIRE statement and corresponding number, the server is being incited somebody to action
Time then further occurred according to each product attribute after the completion of the number statistics that each product attribute occurs in text information
It is several that the product attribute is ranked up, it sorts forward, illustrates that user demand is more, then phase can be carried out to the product attribute
Close product design perhaps plan or can be used for for improve or adjust the structure of the product attribute of current production provide according to
According to.In the present embodiment, it includes by the sequence that the forward product attribute classification of the selected and sorted, which carries out product programming suggestion,
Forward product attribute is overlapped and the major product attribute as planning product, then carries out the planning product model defeated
Out.Such as: it only include the product of " (being applicable in the age) 0-10 years old " and " (being applicable in) disease " product attribute in existing insurance products,
But the message registration of the Category of consulting according to statistics, wherein there is time of " (being applicable in the age) 0-10 years old " and " (being applicable in) is unexpected "
Before number highests, sequence most, thus system can according to the statistical result, suitably provide " (applicable age) 0-10 years old " and
The major product attribute of " (being applicable in) is unexpected " as planning product, then output includes " (applicable age) 0-10 years old " and " (fits
With) it is unexpected " product model.Certainly, other product attributes of the planning product then need subsequent supplemented.
The product programming method based on speech recognition that the present embodiment is proposed, by connection recording system or other
The terminal device such as end PC, mobile terminal etc. can also obtain Category of consulting in the storage unit by the server 1 itself
Then the voice messaging of message registration identifies the voice messaging of Category of consulting, to identify INQUIRE statement therein
Then included product attribute counts the classification and number of product attribute therein;According to the product attribute classification and time
Number carries out product programming suggestion, so that telephone service is also product programming acquisition market letter while answering customer problem
Breath, to improve the output of telephone service.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior art
The part contributed out can be embodied in the form of software products, which is stored in a storage medium
In (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that a terminal device (can be mobile phone, computer, clothes
Business device, air conditioner or the network equipment etc.) execute method described in each embodiment of the present invention.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of product programming method based on speech recognition is applied to server, which is characterized in that the method includes steps
It is rapid:
Obtain the voice messaging of Category of consulting message registration;
The voice messaging is identified to obtain corresponding text information;
Search the INQUIRE statement in the text information;
Sort out the regular product attribute identified in the INQUIRE statement according to preset product attribute;
Count the classification and number of the product attribute that all INQUIRE statements occur in the text information;
It is ranked up according to product attribute of the number to each classification, the forward product attribute classification of selected and sorted is produced
Product planning proposal.
2. the product programming method based on speech recognition as described in claim 1, which is characterized in that described " according to default
Product attribute sort out rule and identify product attribute in the INQUIRE statement " before step, further comprise the steps of:
All product product attributes are recorded, and obtain the keyword of each product attribute;
Product attribute is set and sorts out rule are as follows: when the keyword group and the production in the text information for identifying the INQUIRE statement
When the keyword of product attribute is consistent, then the keyword group is classified as the product attribute.
3. the product programming method based on speech recognition as described in claim 1, which is characterized in that described " to obtain consulting class
The step of voice messaging of other message registration " includes:
According to preset Category of consulting message registration dial in channel filter out in the message registration Category of consulting call note
Record.
4. the product programming method based on speech recognition as claimed in claim 3, which is characterized in that described " to search the text
The step of INQUIRE statement in word information ", comprising steps of
The text information is carried out text with preset inquiry keyword to compare, finding out in the text information includes institute
State the INQUIRE statement of inquiry keyword.
5. a kind of product programming device based on speech recognition, which is characterized in that described device includes:
Module is obtained, for obtaining the voice messaging of Category of consulting message registration;
Identification module, for being identified to the voice messaging to obtain corresponding text information;
Searching module, for searching the INQUIRE statement in the text information;
Identification module is also used to sort out the regular product attribute identified in the INQUIRE statement according to preset product attribute;
Statistical module, for counting the classification and number of the product attribute that all INQUIRE statements occur in the text information;
Suggestion module, for being ranked up according to product attribute of the number to each classification, the forward product of selected and sorted
Attribute classification carries out product programming suggestion.
6. the product programming device based on speech recognition as claimed in claim 5, which is characterized in that the identification module is also used
In:
All product product attributes are recorded, and obtain the keyword of each product attribute;
Product attribute is set and sorts out rule are as follows: when the keyword group and the production in the text information for identifying the INQUIRE statement
When the keyword of product attribute is consistent, then the keyword group is classified as the product attribute.
7. the product programming device based on speech recognition as claimed in claim 5, which is characterized in that the acquisition module is also used
In:
According to preset Category of consulting message registration dial in channel filter out in the message registration Category of consulting call note
Record.
8. the product programming device based on speech recognition as claimed in claim 7, which is characterized in that the searching module is also used
In:
The text information is carried out text with preset inquiry keyword to compare, finding out in the text information includes institute
State the INQUIRE statement of inquiry keyword.
9. a kind of server, which is characterized in that the server includes memory, processor, and being stored on the memory can
The product programming program based on speech recognition run on the processor, the product programming program based on speech recognition
The step of the product programming method according to any one of claims 1-4 based on speech recognition is realized when being executed by the processor
Suddenly.
10. a kind of computer readable storage medium, which is characterized in that the computer-readable recording medium storage has based on voice
The product programming program of identification, the product programming program based on speech recognition can be executed by least one processor, so that
At least one described processor is executed such as the product programming method of any of claims 1-4 based on speech recognition
Step.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811530409.9A CN109816423A (en) | 2018-12-14 | 2018-12-14 | Product programming method and server based on speech recognition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811530409.9A CN109816423A (en) | 2018-12-14 | 2018-12-14 | Product programming method and server based on speech recognition |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109816423A true CN109816423A (en) | 2019-05-28 |
Family
ID=66602918
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811530409.9A Pending CN109816423A (en) | 2018-12-14 | 2018-12-14 | Product programming method and server based on speech recognition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109816423A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110428840A (en) * | 2019-07-19 | 2019-11-08 | 平安科技(深圳)有限公司 | Implementation of load balancing, device and computer equipment in speech recognition system |
CN111341312A (en) * | 2020-02-24 | 2020-06-26 | 百度在线网络技术(北京)有限公司 | Data analysis method and device based on intelligent voice device and storage medium |
CN112330400A (en) * | 2020-11-02 | 2021-02-05 | 泰康保险集团股份有限公司 | Product recommendation method and device, computer equipment and storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105513593A (en) * | 2015-11-24 | 2016-04-20 | 南京师范大学 | Intelligent human-computer interaction method drove by voice |
CN106357942A (en) * | 2016-10-26 | 2017-01-25 | 广州佰聆数据股份有限公司 | Intelligent response method and system based on context dialogue semantic recognition |
CN107437416A (en) * | 2017-05-23 | 2017-12-05 | 阿里巴巴集团控股有限公司 | A kind of consultation service processing method and processing device based on speech recognition |
CN108109618A (en) * | 2016-11-25 | 2018-06-01 | 宇龙计算机通信科技(深圳)有限公司 | voice interactive method, system and terminal device |
CN108231080A (en) * | 2018-01-05 | 2018-06-29 | 广州蓝豹智能科技有限公司 | Voice method for pushing, device, smart machine and storage medium |
CN108920513A (en) * | 2018-05-31 | 2018-11-30 | 深圳市图灵机器人有限公司 | A kind of multimedia data processing method, device and electronic equipment |
-
2018
- 2018-12-14 CN CN201811530409.9A patent/CN109816423A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105513593A (en) * | 2015-11-24 | 2016-04-20 | 南京师范大学 | Intelligent human-computer interaction method drove by voice |
CN106357942A (en) * | 2016-10-26 | 2017-01-25 | 广州佰聆数据股份有限公司 | Intelligent response method and system based on context dialogue semantic recognition |
CN108109618A (en) * | 2016-11-25 | 2018-06-01 | 宇龙计算机通信科技(深圳)有限公司 | voice interactive method, system and terminal device |
CN107437416A (en) * | 2017-05-23 | 2017-12-05 | 阿里巴巴集团控股有限公司 | A kind of consultation service processing method and processing device based on speech recognition |
CN108231080A (en) * | 2018-01-05 | 2018-06-29 | 广州蓝豹智能科技有限公司 | Voice method for pushing, device, smart machine and storage medium |
CN108920513A (en) * | 2018-05-31 | 2018-11-30 | 深圳市图灵机器人有限公司 | A kind of multimedia data processing method, device and electronic equipment |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110428840A (en) * | 2019-07-19 | 2019-11-08 | 平安科技(深圳)有限公司 | Implementation of load balancing, device and computer equipment in speech recognition system |
CN111341312A (en) * | 2020-02-24 | 2020-06-26 | 百度在线网络技术(北京)有限公司 | Data analysis method and device based on intelligent voice device and storage medium |
CN112330400A (en) * | 2020-11-02 | 2021-02-05 | 泰康保险集团股份有限公司 | Product recommendation method and device, computer equipment and storage medium |
CN112330400B (en) * | 2020-11-02 | 2023-12-26 | 泰康保险集团股份有限公司 | Product recommendation method and device, computer equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109634698B (en) | Menu display method and device, computer equipment and storage medium | |
CN109241427A (en) | Information-pushing method, device, computer equipment and storage medium | |
CN109636582B (en) | Credit information management method, apparatus, device and storage medium | |
CN108648012B (en) | Method, system and corresponding medium for providing content to a user | |
CN110502692B (en) | Information retrieval method, device, equipment and storage medium based on search engine | |
CN109816423A (en) | Product programming method and server based on speech recognition | |
CN110807085B (en) | Fault information query method and device, storage medium and electronic device | |
CN107995376A (en) | A kind of user reports a case to the security authorities processing method and terminal device | |
CN107483522A (en) | The method and apparatus of Operational Visit | |
CN104951544A (en) | User data processing method and system and method and system for providing user data | |
WO2016070673A1 (en) | Method and device for analyzing user attribute | |
CN1975772B (en) | Method and device for integrating information in multi-system | |
CN109299129A (en) | Data query method, apparatus, computer equipment and the storage medium of natural language | |
CN102438205B (en) | Method and system for pushing service based on action of mobile user | |
CN107870986A (en) | User behavior analysis method, application server and computer-readable recording medium based on reptile data | |
CN108428102A (en) | Attendance comprehensive control method, application server and computer readable storage medium | |
CN110166522A (en) | Server identification method, device, readable storage medium storing program for executing and computer equipment | |
CN109525647A (en) | Message pushes badge value control method, electronic device and storage medium | |
CN105408894A (en) | Method and device for determining user identity category | |
CN114091472B (en) | Training method of multi-label classification model | |
CN102387255B (en) | Method and device for utilizing intelligent card to process third-party expanded service data | |
CN112307318A (en) | Content publishing method, system and device | |
CN110362607A (en) | Abnormal number identification method, device, computer equipment and storage medium | |
CN108933870B (en) | Dialing control method and device for sales call, computer equipment and storage medium | |
CN111061785A (en) | Method and system for classified storage of orders in management platform |
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 |