User voice calling system and method based on big data processing
Technical Field
The invention relates to the technical field of big data, in particular to a user voice calling system and a user voice calling method based on big data processing.
Background
With the rapid development of internet technology, people have become accustomed to online shopping. When shopping online, some problems, such as goods consultation problem, after-sale problem and the like, can be inevitably encountered, and at the moment, the problems can be solved by dialing a power provider hot line to communicate with customer service staff. In the prior art, after a hotline of a power supplier is dialed, voice broadcasting can be carried out, a user selects a corresponding number key according to the voice broadcasting, then the number key selected by the user is transferred to a corresponding functional area, and when the user needs to solve the after-sale problem urgently, the user needs to spend more steps and longer time to access manual after-sale service.
Disclosure of Invention
The present invention is directed to a system and method for voice calling based on big data processing, so as to solve the problems mentioned in the background art.
In order to solve the technical problems, the invention provides the following technical scheme: a user voice calling system based on big data processing comprises a call receiving module, a call analyzing module, a first call transfer-in module and a second call transfer-in module, wherein the call receiving module is used for receiving a voice call initiated by a user and acquiring a number of the voice call initiated by the user, the call analyzing module is used for analyzing and selecting whether to transmit information to enable the first call transfer-in module to work or enable the second call transfer-in module to work according to the historical voice call condition of the user and the historical order condition in the latest period of time, the first call transfer-in module is used for transferring the voice call initiated by the user to a manual after-sale customer service, and the second call transfer-in module is used for transferring the voice call initiated by the user to a voice broadcasting service.
Further, the call analysis module comprises a product keyword acquisition module, a keyword first search module, a first analysis module and a second analysis module, wherein the product keyword acquisition module is used for acquiring product keywords of each product in a historical order in a recent period of time, the keyword first search module acquires historical webpage search records of a user by taking the product keywords as keywords, information is transmitted to enable the first analysis module to perform analysis work when the historical webpage search records contain the product keywords of a certain product, and information is transmitted to enable the second analysis module to perform analysis work when the historical webpage search records do not contain the product keywords of all products.
Further, the first analysis module comprises an access content acquisition module, an access content statistics module and a first comparison module, the access content acquisition module is used for acquiring a plurality of link addresses corresponding to product keywords in the search records and acquiring webpage content corresponding to the link addresses accessed by the user, the access content statistics module is used for counting the number of the link addresses accessed by the user and the number of the passive tendency webpages and calculating the passive tendency webpage ratio according to the number of the passive tendency webpages, the first comparison module compares the passive tendency webpage ratio with a passive webpage ratio threshold value, and selects whether to transmit information to enable the first call forwarding module to work or to enable the second call forwarding module to work according to a comparison result.
Further, the second analysis module comprises a keyword second search module, a maintenance identifier acquisition module, a voice call record acquisition module and a second comparison module, wherein the keyword second search module is used for searching product keywords of a product in a pre-established identifier database, the maintenance identifier acquisition module acquires maintenance identifiers of corresponding product keywords according to search results of the identifier database, when the maintenance identifiers are primary product identifiers, information is transmitted to enable the first call transfer module to work, when the maintenance identifiers are secondary product identifiers, information is transmitted to the call record acquisition module, the call record acquisition module acquires historical voice call initiation record times of a user initiating a voice call and times of call contents in each historical voice call being negative contents, and accordingly calculates a user negative time ratio, and the second comparison module compares the user negative time ratio with a user negative time ratio threshold value, and selecting whether to transmit information to enable the first call forwarding module or the second call forwarding module to work according to the comparison result.
Furthermore, the voice call system further comprises an identification database establishing module, wherein the identification database establishing module comprises a product voice call counting module, a third comparing module and an identification adding module, the product voice call counting module is used for counting the number of times of receiving historical voice calls of a certain product and the number of times of calling contents of the product in the historical voice calls as negative contents, and calculating the negative number ratio of the product according to the count, the third comparing module is used for comparing the negative number ratio of the product with the negative number ratio threshold of the product, and the identification adding module is used for adding a primary maintenance identification or a secondary maintenance identification to product keywords of the corresponding product according to a comparison result.
A user voice calling method based on big data processing comprises the following steps: when a voice call initiated by a user is received, acquiring the number of the voice call initiated by the user, acquiring the historical voice call condition of the user and the historical order condition in the latest period of time according to the number, and accordingly selecting to transfer the voice call initiated by the user to a manual after-sales service or to a voice broadcast service.
Further, the step of selecting to transfer the voice call initiated by the user to the manual after-sales service or to the voice broadcast service according to the selection comprises:
obtaining product keywords of each product in the historical order in the recent period of time, obtaining historical webpage search records of the user by taking the product keywords as keywords,
if the historical webpage search records of the user contain the product keywords of a certain product, a plurality of link addresses corresponding to the product keywords in the search records are obtained, webpage contents corresponding to the link addresses accessed by the user are obtained,
if the number of the active words contained in the webpage content is less than or equal to the number of the passive words contained in the webpage content, the webpage content is a passive tendency webpage, the number Z of the link addresses visited by the user and the number P of the passive tendency webpages are respectively counted, the passive tendency webpage ratio Q is calculated to be P/Z,
if the passive webpage proportion is larger than or equal to the passive webpage proportion threshold value, the voice call is directly transferred to manual after-sale customer service, and order information containing the product is transmitted to corresponding manual customer service;
if the passive webpage proportion is smaller than the passive webpage proportion threshold value, switching the voice call to a voice broadcasting service;
and if the historical webpage search records of the user do not contain the product keywords of the product, selecting whether to transfer the voice call of the user to the manual after-sales service according to the product related information and the historical voice call condition of the user.
Further, the selecting whether to transfer the voice call of the user to the manual after-sales service according to the product related information and the historical voice call condition of the user includes:
searching product keywords of products in a pre-established identification database, and acquiring maintenance identifications of corresponding product keywords, wherein the maintenance identifications of the products are stored in the identification database and comprise primary product identifications and secondary product identifications
If the maintenance identification of the product keyword is a primary product identification, switching the voice call to a voice broadcasting service;
if the maintenance identification of the product keyword is a secondary product identification, acquiring the recording times D of the voice call initiated by the user history, counting the times H of the call content in each historical voice call of the user as negative content, calculating the ratio F of the negative times of the user as H/D, directly switching the voice call into manual after-sale customer service if the ratio of the negative times of the user is more than or equal to the threshold value of the ratio of the negative times of the user, and transmitting order information containing the product to corresponding manual customer service;
and if the user negative frequency ratio is smaller than the user negative frequency ratio threshold value, switching the voice call to a voice broadcasting service.
Further, the pre-established identification database includes:
the identification database stores product keywords of each product in advance, counts the number of times K of receiving historical voice calls related to a certain product and the number of times T of calling contents of the product in the historical voice calls to be negative contents, calculates the ratio J of the product negative times to be T/K, adds a primary maintenance identification to the product keywords of the product in the identification database if the ratio of the product negative times is smaller than a product negative times ratio threshold, and adds a secondary maintenance identification to the product keywords of the product in the identification database if the ratio of the product negative times is larger than or equal to the product negative times ratio threshold.
Further, if the voice information in the historical voice call of a certain product includes after-sales information of the product, the call content is negative content.
Compared with the prior art, the invention has the following beneficial effects: the invention judges whether to directly transfer the voice call of the user to the manual after-sales service by analyzing the historical voice call condition of the user and the historical order condition in the recent period of time, thereby shortening the step of connecting the manual after-sales service by the user, reducing the time spent by the user for connecting the manual after-sales service and leading the voice call to be more humanized.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
fig. 1 is a block diagram of a subscriber voice call system based on big data processing according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, the present invention provides a technical solution: a user voice calling system based on big data processing comprises a call receiving module, a call analyzing module, a first call transfer-in module and a second call transfer-in module, wherein the call receiving module is used for receiving a voice call initiated by a user and acquiring a number of the voice call initiated by the user, the call analyzing module is used for analyzing and selecting whether to transmit information to enable the first call transfer-in module to work or enable the second call transfer-in module to work according to the historical voice call condition of the user and the historical order condition in the latest period of time, the first call transfer-in module is used for transferring the voice call initiated by the user to a manual after-sale customer service, and the second call transfer-in module is used for transferring the voice call initiated by the user to a voice broadcasting service.
The call analysis module comprises a product keyword acquisition module, a keyword first search module, a first analysis module and a second analysis module, wherein the product keyword acquisition module is used for acquiring product keywords of each product in a historical order in a recent period of time, the keyword first search module acquires historical webpage search records of a user by taking the product keywords as keywords, information is transmitted to enable the first analysis module to analyze and work when the historical webpage search records contain the product keywords of a certain product, and information is transmitted to enable the second analysis module to analyze and work when the historical webpage search records do not contain the product keywords of all products.
The first analysis module comprises an access content acquisition module, an access content counting module and a first comparison module, wherein the access content acquisition module is used for acquiring a plurality of link addresses corresponding to product keywords in a search record and acquiring webpage content corresponding to the link addresses accessed by a user, the access content counting module is used for counting the number of the link addresses accessed by the user and the number of negative tendency webpages and calculating the negative tendency webpage ratio according to the number of the negative tendency webpages, the first comparison module compares the negative tendency webpage ratio with a negative webpage ratio threshold value, and selects whether to transmit information to enable the first call forwarding module to work or to enable the second call forwarding module to work according to a comparison result.
The second analysis module comprises a keyword second search module, a maintenance identifier acquisition module, a voice call record acquisition module and a second comparison module, wherein the keyword second search module is used for searching product keywords of a product in a pre-established identifier database, the maintenance identifier acquisition module acquires maintenance identifiers of corresponding product keywords according to search results of the identifier database, when the maintenance identifiers are primary product identifiers, information is transmitted to enable the first call transfer module to work, when the maintenance identifiers are secondary product identifiers, information is transmitted to the call record acquisition module, the call record acquisition module acquires historical voice call initiation record times of a user initiating a voice call and times of call contents in each historical voice call being negative contents, and calculates a user negative time ratio according to the times, and the second comparison module compares the user negative time ratio with a user negative time ratio threshold value, and selecting whether to transmit information to enable the first call forwarding module or the second call forwarding module to work according to the comparison result.
The voice call system also comprises an identification database establishing module, wherein the identification database establishing module comprises a product voice call counting module, a third comparing module and an identification adding module, the product voice call counting module is used for counting the times of receiving historical voice calls related to a certain product and the times of calling contents of the product in the historical voice calls as negative contents, and calculating the negative times ratio of the product according to the times of receiving the historical voice calls, the third comparing module is used for comparing the negative times ratio of the product with the product times ratio threshold value, and the identification adding module is used for adding a primary maintenance identification or a secondary maintenance identification to product keywords of the corresponding product according to the comparison result.
A user voice calling method based on big data processing comprises the following steps: when a voice call initiated by a user is received, acquiring the number of the voice call initiated by the user, acquiring the historical voice call condition of the user and the historical order condition in the latest period of time according to the number, and accordingly selecting to transfer the voice call initiated by the user to a manual after-sales service or to a voice broadcast service.
The step of switching the voice call initiated by the user to the manual after-sales service or switching the voice call to the voice broadcasting service according to the selection comprises the following steps:
obtaining product keywords of each product in the historical order in the recent period of time, obtaining historical webpage search records of the user by taking the product keywords as keywords,
if the historical webpage search records of the user contain the product keywords of a certain product, a plurality of link addresses corresponding to the product keywords in the search records are obtained, webpage contents corresponding to the link addresses accessed by the user are obtained,
if the number of the active words contained in the webpage content is less than or equal to the number of the passive words contained in the webpage content, the webpage content is a passive tendency webpage, the number Z of the link addresses visited by the user and the number P of the passive tendency webpages are respectively counted, the passive tendency webpage ratio Q is calculated to be P/Z,
if the passive webpage proportion is larger than or equal to the passive webpage proportion threshold value, the voice call is directly transferred to manual after-sale customer service, and order information containing the product is transmitted to corresponding manual customer service;
if the passive webpage proportion is smaller than the passive webpage proportion threshold value, switching the voice call to a voice broadcasting service;
if the historical web page search records of the user do not contain the product keywords of the product:
searching product keywords of products in a pre-established identification database, and acquiring maintenance identifications of corresponding product keywords, wherein the maintenance identifications of the products are stored in the identification database and comprise primary product identifications and secondary product identifications
If the maintenance identification of the product keyword is a primary product identification, switching the voice call to a voice broadcasting service;
if the maintenance identification of the product keyword is a secondary product identification, acquiring the recording times D of the voice call initiated by the user history, counting the times H of the call content in each historical voice call of the user as negative content, calculating the ratio F of the negative times of the user as H/D, directly switching the voice call into manual after-sale customer service if the ratio of the negative times of the user is more than or equal to the threshold value of the ratio of the negative times of the user, and transmitting order information containing the product to corresponding manual customer service;
and if the user negative frequency ratio is smaller than the user negative frequency ratio threshold value, switching the voice call to a voice broadcasting service.
The pre-established identity database comprises:
the identification database stores product keywords of each product in advance, counts the number of times K of receiving historical voice calls related to a certain product and the number of times T that the call content of the product in the historical voice calls is negative, calculates the product negative number ratio J as T/K, adds a primary maintenance identifier to the product keyword of the product in the identification database if the product negative number ratio is smaller than a product negative number ratio threshold, and adds a secondary maintenance identifier to the product keyword of the product in the identification database if the product negative number ratio is larger than or equal to the product negative number ratio threshold, wherein the call content is negative content if the voice information in the historical voice calls of the certain product comprises after-sales information of the product.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that changes may be made in the embodiments and/or equivalents thereof without departing from the spirit and scope of the invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.