CN111723178A - Method, system, server and equipment for providing sales suggestions in real time - Google Patents
Method, system, server and equipment for providing sales suggestions in real time Download PDFInfo
- Publication number
- CN111723178A CN111723178A CN202010424042.3A CN202010424042A CN111723178A CN 111723178 A CN111723178 A CN 111723178A CN 202010424042 A CN202010424042 A CN 202010424042A CN 111723178 A CN111723178 A CN 111723178A
- Authority
- CN
- China
- Prior art keywords
- information
- sales
- intention
- client
- category
- 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.)
- Withdrawn
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3343—Query execution using phonetics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0203—Market surveys; Market polls
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Acoustics & Sound (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A method, system, server, device and computer-readable storage medium for providing sales suggestions in real-time, wherein the method comprises: acquiring voice information of a conversation between a salesman and a customer, and determining intention information of the customer according to the voice information; and querying a knowledge base according to the intention information of the client, and generating a sales suggestion according to a query result. The embodiment of the application provides sales suggestions for the sales staff in real time by identifying the intention of the customers and combining the knowledge base, and assists the sales staff to meet the demands of the customers, so that the waiting time of the customers is shortened, the customer experience is improved, the singleton probability is improved, and the sales experts are not required to manually summarize the sales experience.
Description
Technical Field
The present disclosure relates to the field of information processing, and more particularly, to a method, system, server, device, and computer-readable storage medium for providing sales suggestions in real time.
Background
Although the off-line physical store faces huge impact with the rapid development of electronic commerce, the physical store still has the inherent advantages that the on-line e-commerce cannot match, can communicate with customers face to face and answer questions, and can enable the customers to actually experience commodities. To take advantage of the above advantages of the outlet lower storefront, two challenges associated with sales personnel training are faced: on one hand, the mobility of the salespersons is too high, and the salespersons generally leave the job about one year; on the other hand, the sales skills are insufficient, and the new salespersons lack the corresponding sales skills, especially in the more complex industries such as automobiles and finance.
However, the mainstream methods for improving sales capability still rely on offline training, and the contents of the methods mainly take manual summary of experience of sales experts as a main part and solidify the experience in a regular form.
Disclosure of Invention
Embodiments of the present application provide a method, system, server, device and computer-readable storage medium for providing sales suggestions in real time to quickly and efficiently provide sales suggestions to sales personnel through automated means.
The embodiment of the application provides a method for providing sales suggestions in real time, which comprises the following steps:
acquiring voice information of a conversation between a salesman and a customer, and determining intention information of the customer according to the voice information;
and querying a knowledge base according to the intention information of the client, and generating a sales suggestion according to a query result.
The embodiment of the present application further provides a system for providing sales suggestions in real time, including a server and a client, wherein:
the client is used for collecting voice information of conversation between a salesman and a client, sending the voice information to the server and acquiring a sales suggestion from the server;
the server is used for acquiring voice information of conversation between salesmen and a client from the client, determining intention information of the client according to the voice information, inquiring a knowledge base according to the intention information of the client, generating a sales suggestion according to an inquiry result and sending the sales suggestion to the client.
An embodiment of the present application further provides a server, including:
the voiceprint recognition module is used for acquiring voice information of the conversation between the salesman and the client and recognizing identity information corresponding to the voice information according to voiceprint characteristics;
the voice recognition module is used for converting the voice information into text information;
the keyword extraction module is used for extracting keywords corresponding to the identity information from the text information;
the state cache module is used for storing the keywords into the information of the sales process according to a preset data structure;
an intention identification module for determining the intention category of the customer according to the keyword and the sales process information;
and the suggestion generation module is used for inquiring the knowledge base according to the intention information of the client and generating the sales suggestion according to the inquiry result, wherein the intention information comprises intention categories, keywords and sales process information.
An embodiment of the present application further provides an apparatus for providing a sales suggestion in real time, including: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method of providing sales suggestions in real-time when executing the program.
Embodiments of the present application also provide a computer-readable storage medium storing computer-executable instructions for performing the method for providing sales suggestions in real time.
Compared with the related art, the embodiment of the application comprises the following steps: acquiring voice information of a conversation between a salesman and a customer, and determining intention information of the customer according to the voice information; and querying a knowledge base according to the intention information of the client, and generating a sales suggestion according to a query result. The embodiment of the application provides sales suggestions for the sales staff in real time by identifying the intention of the customers and combining the knowledge base, and assists the sales staff to meet the demands of the customers, so that the waiting time of the customers is shortened, the customer experience is improved, the singleton probability is improved, and the sales experts are not required to manually summarize the sales experience.
Additional features and advantages of the application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the application. Other advantages of the present application may be realized and attained by the instrumentalities and combinations particularly pointed out in the specification and the drawings.
Drawings
The accompanying drawings are included to provide an understanding of the present disclosure and are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the examples serve to explain the principles of the disclosure and not to limit the disclosure.
FIG. 1 is a flow chart of a method of providing sales recommendations in real time in an embodiment of the present application;
FIG. 2 is a flowchart of step 101 of an embodiment of the present application;
FIG. 3 is a flowchart of step 102 according to an embodiment of the present application;
FIG. 4 is a partial schematic view of vehicle-related sales link conversion information according to an embodiment of the present application;
FIG. 5 is a schematic diagram of a system for providing sales recommendations in real-time, in accordance with an embodiment of the present application;
fig. 6 is a schematic composition diagram of a client and a server according to an embodiment of the present application.
Detailed Description
The present application describes embodiments, but the description is illustrative rather than limiting and it will be apparent to those of ordinary skill in the art that many more embodiments and implementations are possible within the scope of the embodiments described herein. Although many possible combinations of features are shown in the drawings and discussed in the detailed description, many other combinations of the disclosed features are possible. Any feature or element of any embodiment may be used in combination with or instead of any other feature or element in any other embodiment, unless expressly limited otherwise.
The present application includes and contemplates combinations of features and elements known to those of ordinary skill in the art. The embodiments, features and elements disclosed in this application may also be combined with any conventional features or elements to form a unique inventive concept as defined by the claims. Any feature or element of any embodiment may also be combined with features or elements from other inventive aspects to form yet another unique inventive aspect, as defined by the claims. Thus, it should be understood that any of the features shown and/or discussed in this application may be implemented alone or in any suitable combination. Accordingly, the embodiments are not limited except as by the appended claims and their equivalents. Furthermore, various modifications and changes may be made within the scope of the appended claims.
Further, in describing representative embodiments, the specification may have presented the method and/or process as a particular sequence of steps. However, to the extent that the method or process does not rely on the particular order of steps set forth herein, the method or process should not be limited to the particular sequence of steps described. Other orders of steps are possible as will be understood by those of ordinary skill in the art. Therefore, the particular order of the steps set forth in the specification should not be construed as limitations on the claims. Further, the claims directed to the method and/or process should not be limited to the performance of their steps in the order written, and one skilled in the art can readily appreciate that the sequences may be varied and still remain within the spirit and scope of the embodiments of the present application.
The embodiment of the application provides a method for providing sales suggestions in real time, and the sales suggestions are provided for sales personnel in real time according to the collected client intentions and by combining a background knowledge base, so that the sales personnel are helped to shorten the answering time and improve the sales success rate.
As shown in fig. 1, a method for providing a sales suggestion in real time according to an embodiment of the present application includes:
And 102, inquiring a knowledge base according to the intention information of the client, and generating a sale suggestion according to an inquiry result.
As shown in fig. 2, in an embodiment, the intention information includes intention information including intention category, keyword and selling process information, and the step 101 includes:
The obtained voice information can be converted into low-dimensional dense real numerical value vectors after being subjected to environmental noise removal preprocessing, and the low-dimensional dense real numerical value vectors are used for representing the identity of the speaker. By comparing with the voiceprint features in the historical voiceprint library, the identity information corresponding to the voice information can be judged, for example, whether the current voice information is from a salesperson or a customer, and if the current voice information is from a customer, whether the current voice information is from a new customer or an old customer can be further judged.
After the identity information is determined, the voice information can be subjected to identity labeling.
Among them, the voice information can be converted into text information by an ASR (Automatic Speech Recognition) technology.
The keyword extraction may be performed by various methods, for example, the method may be performed by machine learning, dictionary templates, and the like, to directly extract the keywords from the text information, or may be performed by extracting knowledge from the text information to generate a knowledge graph, and the keywords representing the intention of the client are filtered from the graph.
The keywords may include, but are not limited to, the following types: name of person, place name, organization name, product dimensions, time, currency, numbers, percentages, attribute names (e.g., screen, battery, pricing, age, marital status), attribute words (e.g., red, genuine), opinion words (e.g., hate, preferences), personal relationship words (e.g., couple, colleague), scene words (e.g., living room, office), other words in a predefined special-purpose dictionary (e.g., industry category dictionary).
And step 204, storing the keywords into the information of the sales process according to a preset data structure.
In the selling process, context information, customer information, time information and the like may be required to be referred to in each conversation, all keywords (namely keywords extracted by voice information at each time) in the selling process can be stored through the selling process information, and the selling process information can further comprise acquired information such as time characteristics, the number of customers, customer relations and the like. The sales process information may also be referred to as state cache information.
Wherein the time characteristic may refer to time information of the current session, such as whether it is a weekday, a weekend, a legal holiday, a month, a day, a night, etc.
Customer relationship may refer to what relationship is between multiple people in the case of multiple customers, such as: a couple, a lover, a friend, a classmate, a mother and a woman, etc.
The preset data structure may include customer attributes, which may include gender, occupation, age, education level, marital status, etc., customer intentions, which may include product type, preference, price range, etc., customer intentions, etc.
In step 205, the current voice information is classified into predefined intention categories according to the keyword and the sales process information, and the intention categories may include: query types (such as query: price, process, material, maintenance problem), read types (such as member welfare, purchase requisition), product recommendation types (which product matches the current customer's needs), etc.
The method can adopt a form that current keywords are used as the main part and keywords, time information and customer information obtained in the sales process information are used as auxiliary parts to perform character string matching, so as to perform classification. And the classification can also be carried out by expanding the synonym dictionary on the basis of keyword matching.
In one embodiment, step 205 comprises:
determining a probability value of each intention category according to the keyword and the sales process information; and comparing the probability value with a preset category threshold value, and determining a corresponding intention category according to a comparison result.
The input feature vector X can be sorted out from a large number of historical data sets by adopting a machine learning implementation manner, the intention category Y is labeled, and the mapping relation f from X to Y is learned by a classification learning algorithm, namely, Y ═ f (X).
The output intention category probability value may be a list of a set of fixed dimensions, the length of the list is equal to the number of predefined intention categories, and each dimension in the list has a value between (0,1) and represents the probability of the corresponding intention category.
And judging whether the probability value of each intention category exceeds a preset threshold value of each category according to the probability value of each intention category, and further generating a sales suggestion.
In the comparison, if there is only one probability value greater than or equal to the corresponding category threshold, the corresponding intent category may be directly determined.
In one embodiment, when a plurality of probability values greater than or equal to corresponding category thresholds exist in the comparison result, the intention categories are determined in a percentage sorting mode. Namely:
the categories may be sorted by percentage over a category threshold: (p)i-ti)/ti. Wherein p isiIndicates the probability, t, corresponding to the class iiIndicating the category threshold corresponding to category i.
If there is no probability value greater than or equal to the corresponding category threshold, then the intent category cannot be determined, and no sales suggestions are generated for this round.
As shown in FIG. 3, in one embodiment, step 102 includes:
The knowledge base may include one or more of product architecture information, product maintenance information, sales link conversion information.
The product system information may include a name, a model, a price, etc. of the product.
The product repair information may include repaired components, repair time, problem description, repair price, etc.
The sales link conversion information may include sales links, conversion probabilities, and the like. As shown in fig. 4, a partial diagram of sales link transition information related to vehicles is shown, wherein each node represents a sales link, such as product introduction, expense explanation, etc., and the number on the line between the nodes is between 0 and 1, which represents the transition probability between the links.
Among them, a plurality of text templates can be set according to the intention category.
For example, the user asks "are there several layers of paint? "according to the information of the sales process, the vehicle type of Toyota Camry is known, the primer is known to be inquired according to the result of the intention category, the information is converted into a knowledge base inquiry language (such as SPARQL) to be inquired, and the inquiry result is 5. Finally, the '5' is filled into a '____ model template with ___ layers of primer'.
In an embodiment, after step 102, the method further includes:
and generating and outputting a voice suggestion file according to the sales suggestion.
Wherein, the sales suggestions can be synthesized into a file in a voice form, and the file is output and played to the sales staff.
In other embodiments, the sales suggestions may also be displayed to the sales personnel by way of a display screen.
According to the embodiment of the application, the background knowledge base can be rapidly inquired according to the collected dialogue information, the inquiry result or the sales suggestion is given, and the sales staff is assisted to meet the requirements of the customers, so that the waiting time of the customers is shortened, the customer experience is improved, the singleton probability is improved, and the sales experts are not required to manually summarize the sales experience.
As shown in fig. 5, the system for providing a sales suggestion in real time according to the embodiment of the present application includes a client 51 and a server 52, wherein:
the client 51 is used for collecting voice information of conversation between a salesman and a client, sending the voice information to the server 52 and obtaining a sales suggestion from the server 52;
the server 52 is configured to obtain voice information of a conversation between a salesperson and a client from the client 51, determine intention information of the client according to the voice information, query a knowledge base according to the intention information of the client, generate a sales suggestion according to a query result, and send the sales suggestion to the client 51.
As shown in fig. 6, the client 51 may include a voice capture module 511 and a voice play module 512, wherein,
the voice collecting module 511 can be worn on the salesperson as an independent hardware device, and is responsible for collecting voice information of the conversation between the salesperson and the client, compressing the voice and uploading the compressed voice to the server 52.
The voice playing module 512 may be a speaker, and may be configured with the voice capturing module 511 to receive the voice suggestion file from the server 52 and play it to the salesperson.
The voice playing module 512 may be replaced by a display module, and the display module is used for displaying the sales suggestions to the sales staff.
In other embodiments, the client 51 may include both the voice playing module 512 and the display module.
The server 52 may include:
and the voiceprint recognition module 521 is configured to acquire voice information of a conversation between a salesperson and a client, and recognize identity information corresponding to the voice information according to voiceprint characteristics.
The voiceprint recognition module 521 may convert the obtained voice information into a low-dimensional dense real value vector after the preprocessing of the environmental noise, so as to represent the identity of the speaker. By comparing with the voiceprint features in the historical voiceprint library, the identity information corresponding to the voice information can be judged, for example, whether the current voice information is from a salesperson or a customer, and if the current voice information is from a customer, whether the current voice information is from a new customer or an old customer can be further judged.
And a voice recognition module 522, configured to convert the voice information into text information.
The Speech Recognition module 522 may convert the Speech information into text information through an ASR (Automatic Speech Recognition) technique.
A keyword extracting module 523, configured to extract a keyword corresponding to the identity information from the text information.
The keyword extraction module 523 extracts keywords from the input text message, and the keywords may include, but are not limited to, the following types: name of person, place name, organization name, product dimensions, time, currency, numbers, percentages, attribute names (e.g., screen, battery, pricing, age, marital status), attribute words (e.g., red, genuine), opinion words (e.g., hate, preferences), personal relationship words (e.g., couple, colleague), scene words (e.g., living room, office), other words in a predefined special-purpose dictionary (e.g., industry category dictionary).
The keyword extraction module 523 may extract keywords by various methods, for example, the method may be a machine learning method, a dictionary template method, or the like, and extract keywords directly from the text information, or extract knowledge from the text information to generate a knowledge graph, and filter out keywords representing the intention of the user from the graph.
And the state caching module 524 is configured to store the keyword into the sales process information according to a preset data structure.
In the selling process, context information, customer information, time information and the like may be required to be referred to in each conversation, all keywords (namely keywords extracted by voice information at each time) in the selling process can be stored through the selling process information, and the selling process information can further comprise acquired information such as time characteristics, the number of customers, customer relations and the like. The sales process information may also be referred to as state cache information.
Wherein the time characteristic may refer to time information of the current session, such as whether it is a weekday, a weekend, a legal holiday, a month, a day, a night, etc.
Customer relationship may refer to what relationship is between multiple people in the case of multiple customers, such as: a couple, a lover, a friend, a classmate, a mother and a woman, etc.
The preset data structure may include customer attributes, which may include gender, occupation, age, education level, marital status, etc., customer intentions, which may include product type, preference, price range, etc., customer intentions, etc. For example, the customer attributes: gender-male, occupation-IT, education-college pedigree, marital status-marriage, …; the intention of the client: product type-sofa, house type-second-hand house new decoration, preference color-white, style-modern simple, price range-within 5000, …, etc.
The state caching module 524 may be implemented in the form of a database.
And an intention identification module 525 for determining the intention category of the customer according to the keyword and the sales process information.
The intent recognition module 525 may classify the current voice information into predefined intent categories based on the keywords and sales process information, which may include: query types (such as query: price, process, material, maintenance problem), read types (such as member welfare, purchase requisition), product recommendation types (which product matches the current customer's needs), etc.
The intention identifying module 525 may perform character string matching in a form of mainly using the current keyword and secondarily using the keyword, the time information, and the customer information obtained in the sales process information, so as to perform classification. And the classification can also be carried out by expanding the synonym dictionary on the basis of keyword matching.
In an embodiment, the intention identifying module 525 is configured to determine a probability value of each intention category according to the keyword and the sales process information, compare the probability value with a preset category threshold, and determine a corresponding intention category according to a comparison result.
The intention identifying module 525 may adopt a machine learning implementation manner, sort out the input feature vector X on a large number of historical data sets, label the intention category Y, and learn the mapping relationship f from X to Y by a classification learning algorithm, that is, Y ═ f (X).
The output intention category probability value may be a list of a set of fixed dimensions, the length of the list is equal to the number of predefined intention categories, and each dimension in the list has a value between (0,1) and represents the probability of the corresponding intention category.
The intention identifying module 525 may further generate a sales suggestion according to the probability value of each intention category and according to a preset threshold value of each category, and whether the threshold value is exceeded.
In the comparison, if there is only one probability value greater than or equal to the corresponding category threshold, the intent recognition module 525 may directly determine the corresponding intent category.
In one embodiment, the intent recognition module 525 determines the intent categories in a percentage-ordered manner when there are multiple probability values in the comparison that are greater than or equal to the corresponding category thresholds. Namely:
the categories may be sorted by percentage over a category threshold: (p)i-ti)/ti. Wherein p isiIndicates the probability, t, corresponding to the class iiIndicating the category threshold corresponding to category i.
And a suggestion generating module 526, configured to query the knowledge base 527 according to the intention information of the client, and generate a sales suggestion according to a query result obtained by the query, where the intention information includes an intention category, a keyword, and sales process information.
The knowledge base 527 may include one or more of product architecture information, product maintenance information, and sales link conversion information.
The product system information may include a name, a model, a price, etc. of the product.
The product repair information may include repaired components, repair time, problem description, repair price, etc.
The sales link conversion information may include sales links, conversion probabilities, and the like. As shown in fig. 4, a partial diagram of sales link transition information related to vehicles is shown, wherein each node represents a sales link, such as product introduction, expense explanation, etc., and the number on the line between the nodes is between 0 and 1, which represents the transition probability between the links.
In an embodiment, the suggestion generation module 526 fills the query result into a preset text template according to the intention category to generate a sales suggestion.
Among them, a plurality of text templates can be set according to the intention category.
For example, the user asks "are there several layers of paint? "according to the information of the sales process, the vehicle type of Toyota Camry is known, the primer is known to be inquired according to the result of the intention category, the information is converted into a knowledge base inquiry language (such as SPARQL) to be inquired, and the inquiry result is 5. Finally, the '5' is filled into a '____ model template with ___ layers of primer'.
In one embodiment, the server may further include a speech synthesis module 528 for generating and outputting a speech suggestion file according to the sales suggestion.
The speech synthesis module 528 may synthesize the sales suggestions into a speech-form file for output to the client.
It should be noted that the voiceprint recognition module 521 and the voice recognition module 522 may also be disposed in the client, that is, the information uploaded to the server by the client is information in a text format.
The embodiment of the application provides sales suggestions for the sales staff in real time by identifying the intention of the customers and combining the knowledge base, and assists the sales staff to meet the demands of the customers, so that the waiting time of the customers is shortened, the customer experience is improved, the singleton probability is improved, and the sales experts are not required to manually summarize the sales experience.
An embodiment of the present application further provides an apparatus for providing a sales suggestion in real time, including: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method of providing sales suggestions in real-time when executing the program.
Embodiments of the present application also provide a computer-readable storage medium storing computer-executable instructions for performing the method for providing sales suggestions in real time.
In this embodiment, the storage medium may include, but is not limited to: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
It will be understood by those of ordinary skill in the art that all or some of the steps of the methods, systems, functional modules/units in the devices disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof. In a hardware implementation, the division between functional modules/units mentioned in the above description does not necessarily correspond to the division of physical components; for example, one physical component may have multiple functions, or one function or step may be performed by several physical components in cooperation. Some or all of the components may be implemented as software executed by a processor, such as a digital signal processor or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as is well known to those of ordinary skill in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, Digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can accessed by a computer. In addition, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media as known to those skilled in the art.
Claims (10)
1. A method of providing sales recommendations in real-time, comprising:
acquiring voice information of a conversation between a salesman and a customer, and determining intention information of the customer according to the voice information;
and querying a knowledge base according to the intention information of the client, and generating a sales suggestion according to a query result.
2. The method of claim 1, wherein the intent information includes intent categories, keywords, and sales process information, and wherein determining the intent information of the customer from the voice information comprises:
identifying identity information corresponding to the voice information according to the voiceprint characteristics;
converting the voice information into text information;
extracting keywords corresponding to the identity information from the text information;
storing the keywords into the information of the selling process according to a preset data structure;
and determining the intention category of the client according to the keywords and the sales process information.
3. The method of claim 2, wherein determining the intent category of the customer based on the keyword and sales process information comprises:
determining a probability value of each intention category according to the keyword and the sales process information;
and comparing the probability value with a preset category threshold value, and determining a corresponding intention category according to a comparison result.
4. The method of claim 3, wherein in the step of comparing the probability value with a preset category threshold value and determining a corresponding intention category according to the comparison result,
and when a plurality of probability values are larger than or equal to corresponding category thresholds in the comparison result, determining the intention category in a percentage sorting mode.
5. The method of claim 1, wherein generating sales suggestions from query results comprises:
and filling the query result into a preset text template according to the intention category to generate a sales suggestion.
6. The method of claim 1, wherein after querying a knowledge base according to the intention information of the customer and generating a sales suggestion according to the query result, the method further comprises:
and generating and outputting a voice suggestion file according to the sales suggestion.
7. A system for providing a sales proposal in real time, comprising a server and a client, wherein:
the client is used for collecting voice information of conversation between a salesman and a client, sending the voice information to the server and acquiring a sales suggestion from the server;
the server is used for acquiring voice information of conversation between salesmen and a client from the client, determining intention information of the client according to the voice information, inquiring a knowledge base according to the intention information of the client, generating a sales suggestion according to an inquiry result and sending the sales suggestion to the client.
8. A server, comprising:
the voiceprint recognition module is used for acquiring voice information of the conversation between the salesman and the client and recognizing identity information corresponding to the voice information according to voiceprint characteristics;
the voice recognition module is used for converting the voice information into text information;
the keyword extraction module is used for extracting keywords corresponding to the identity information from the text information;
the state cache module is used for storing the keywords into the information of the sales process according to a preset data structure;
an intention identification module for determining the intention category of the customer according to the keyword and the sales process information;
and the suggestion generation module is used for inquiring the knowledge base according to the intention information of the client and generating the sales suggestion according to the inquiry result, wherein the intention information comprises intention categories, keywords and sales process information.
9. An apparatus for providing sales advice in real time, comprising: memory, processor and computer program stored on the memory and executable on the processor, characterized in that the processor implements the method according to any of claims 1 to 6 when executing the program.
10. A computer-readable storage medium storing computer-executable instructions for performing the method of any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010424042.3A CN111723178A (en) | 2020-05-19 | 2020-05-19 | Method, system, server and equipment for providing sales suggestions in real time |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010424042.3A CN111723178A (en) | 2020-05-19 | 2020-05-19 | Method, system, server and equipment for providing sales suggestions in real time |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111723178A true CN111723178A (en) | 2020-09-29 |
Family
ID=72564747
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010424042.3A Withdrawn CN111723178A (en) | 2020-05-19 | 2020-05-19 | Method, system, server and equipment for providing sales suggestions in real time |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111723178A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112463947A (en) * | 2020-11-26 | 2021-03-09 | 上海明略人工智能(集团)有限公司 | Marketing scheme iteration method, marketing scheme iteration system, computer equipment and readable storage medium |
| CN112651787A (en) * | 2021-01-06 | 2021-04-13 | 上海明略人工智能(集团)有限公司 | Payment method and device for orally-played advertisement |
| CN112734467A (en) * | 2020-12-31 | 2021-04-30 | 北京明略软件系统有限公司 | Passenger flow prediction method and system for offline service scene |
| CN112967721A (en) * | 2021-02-03 | 2021-06-15 | 上海明略人工智能(集团)有限公司 | Sales lead information identification method and system based on voice identification technology |
| CN113283934A (en) * | 2021-05-28 | 2021-08-20 | 北京量冠科技有限公司 | Information determination method and device, electronic equipment and storage medium |
| CN115544125A (en) * | 2022-11-24 | 2022-12-30 | 云账户技术(天津)有限公司 | Management method and device based on guest expansion stage circulation record and electronic equipment |
-
2020
- 2020-05-19 CN CN202010424042.3A patent/CN111723178A/en not_active Withdrawn
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112463947A (en) * | 2020-11-26 | 2021-03-09 | 上海明略人工智能(集团)有限公司 | Marketing scheme iteration method, marketing scheme iteration system, computer equipment and readable storage medium |
| CN112734467A (en) * | 2020-12-31 | 2021-04-30 | 北京明略软件系统有限公司 | Passenger flow prediction method and system for offline service scene |
| CN112651787A (en) * | 2021-01-06 | 2021-04-13 | 上海明略人工智能(集团)有限公司 | Payment method and device for orally-played advertisement |
| CN112967721A (en) * | 2021-02-03 | 2021-06-15 | 上海明略人工智能(集团)有限公司 | Sales lead information identification method and system based on voice identification technology |
| CN112967721B (en) * | 2021-02-03 | 2024-05-31 | 上海明略人工智能(集团)有限公司 | Sales lead information recognition method and system based on voice recognition technology |
| CN113283934A (en) * | 2021-05-28 | 2021-08-20 | 北京量冠科技有限公司 | Information determination method and device, electronic equipment and storage medium |
| CN115544125A (en) * | 2022-11-24 | 2022-12-30 | 云账户技术(天津)有限公司 | Management method and device based on guest expansion stage circulation record and electronic equipment |
| CN115544125B (en) * | 2022-11-24 | 2023-04-07 | 云账户技术(天津)有限公司 | Management method and device based on guest expansion stage circulation record and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111723178A (en) | Method, system, server and equipment for providing sales suggestions in real time | |
| CN108256052B (en) | Tri-tracking-based potential customer identification method for automobile industry | |
| CN112346567B (en) | Virtual interaction model generation method and device based on AI (Artificial Intelligence) and computer equipment | |
| US11392645B2 (en) | Computerized domain expert | |
| CN109767787B (en) | Emotion recognition method, device and readable storage medium | |
| CN108492118B (en) | Two-stage extraction method for return visit text data of automobile after-sale service quality evaluation | |
| CN110827797B (en) | Voice response event classification processing method and device | |
| US11830017B2 (en) | System and method for providing a price for a vehicle | |
| CN111178940A (en) | Method and system for automatically generating sales call technology map | |
| CN111581360A (en) | Method, system and equipment for assisting customer service | |
| CN114218488A (en) | Information recommendation method and device based on multi-modal feature fusion and processor | |
| JP7068596B2 (en) | Learning data creation device, learning data creation method, and program | |
| CN117592489B (en) | Method and system for realizing electronic commerce commodity information interaction by using large language model | |
| CN110121108A (en) | Video value appraisal procedure and device | |
| CN113128284A (en) | Multi-mode emotion recognition method and device | |
| CN110765776A (en) | Method and device for generating return visit labeling sample data | |
| CN112633927A (en) | Combined commodity mining method based on knowledge graph rule embedding | |
| CN112053205A (en) | Product recommendation method and device through robot emotion recognition | |
| CN115269836A (en) | Intention identification method and device | |
| CN114398909A (en) | Question generation method, device, equipment and storage medium for dialogue training | |
| CN117114745B (en) | Method and device for predicting intent vehicle model | |
| CN113327132A (en) | Multimedia recommendation method, device, equipment and storage medium | |
| CN117034955A (en) | Telephone traffic text intention recognition method and device | |
| CN116049411A (en) | Information matching method, device, equipment and readable storage medium | |
| CN110413795A (en) | A kind of professional knowledge map construction method of data-driven |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20200929 |
|
| WW01 | Invention patent application withdrawn after publication |