CN113469710A - Method, system, electronic device and storage medium for predicting consultation order - Google Patents
Method, system, electronic device and storage medium for predicting consultation order Download PDFInfo
- Publication number
- CN113469710A CN113469710A CN202110762430.7A CN202110762430A CN113469710A CN 113469710 A CN113469710 A CN 113469710A CN 202110762430 A CN202110762430 A CN 202110762430A CN 113469710 A CN113469710 A CN 113469710A
- Authority
- CN
- China
- Prior art keywords
- order
- consultation
- orders
- incoming call
- probability
- 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.)
- Granted
Links
Images
Classifications
-
- 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
- G06Q30/01—Customer relationship services
-
- 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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0633—Lists, e.g. purchase orders, compilation or processing
- G06Q30/0635—Processing of requisition or of purchase orders
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention relates to the technical field of Internet, and provides a method and a system for predicting a consultation order, electronic equipment and a storage medium. The prediction method of the consultation order comprises the following steps: responding to an incoming call request of a client, and acquiring a related order according to an incoming call number; extracting a feature value of each consultation dimension according to the incoming call request and each associated order to form a feature value group of each associated order, and calculating the consultation probability of each associated order according to the feature value group of each associated order; and predicting one or more associated orders with the maximum consultation probability as alternative consultation orders, and sequentially broadcasting the alternative consultation orders to the client through AI customer service. The method and the system can predict the consultation order according to the incoming call number, are efficient and convenient, improve the utilization rate of intelligent customer service, save the cost of manual customer service, and improve the user experience.
Description
Technical Field
The invention relates to the technical field of internet, in particular to a method and a system for predicting a consultation order, electronic equipment and a storage medium.
Background
Under the current internet environment, after a user places an order on a ticket service platform, the user often needs to contact customer service to make telephone consultation on the order. To improve response speed and save cost, the ticketing services platform replies to most queries using AI (Artificial Intelligence) customer service instead of human.
However, in the current AI customer service, that is, the way of acquiring a consultation order by an intelligent customer service, a user needs to manually input an order number, and then a background inquires order data according to the order number to reply to a problem of the user. However, the order number is generally a string of long numbers generated randomly, the manual input expense of the user is high, and the manual input expense is easy to be mistaken, so that many users are unwilling to select intelligent customer service inquiry information and directly select artificial customer service, and the simple consultation that the ticket service platform hopes to be covered by the intelligent customer service is forced to be transferred to the artificial customer service for processing, so that a large amount of labor cost is consumed, the original intention of developing the intelligent customer service is violated, the experience of the user using the intelligent customer service is poor, and the complaint rate is high.
It is to be noted that the information disclosed in the above background section is only for enhancement of understanding of the background of the invention and therefore may include information that does not constitute prior art that is already known to a person of ordinary skill in the art.
Disclosure of Invention
In view of the above, the invention provides a method, a system, an electronic device and a storage medium for predicting a consultation order, which can predict the consultation order according to an incoming call number, are efficient and convenient, improve the utilization rate of intelligent customer service, save the cost of manual customer service, and improve the user experience.
One aspect of the present invention provides a method for predicting a consultation order, including: responding to an incoming call request of a client, and acquiring a related order according to an incoming call number; extracting a feature value of each consultation dimension according to the incoming call request and each associated order to form a feature value group of each associated order, and calculating the consultation probability of each associated order according to the feature value group of each associated order; and predicting one or more associated orders with the maximum consultation probability as alternative consultation orders, and sequentially broadcasting the alternative consultation orders to the client through AI customer service.
In some embodiments, each of the consulting dimensions has a plurality of values, and the calculating a consulting probability for each of the associated orders includes: calculating the actual consultation ratio of each value combination of each consultation dimension according to the actual consultation order of the existing incoming call stored in the database, and obtaining the consultation probability of each value combination at least according to the actual consultation ratio of each value combination; and acquiring the consultation probability of each associated order according to the corresponding value combination of the characteristic value group of each associated order.
In some embodiments, after calculating the actual consulting proportion of each value combination of each consulting dimension, the method further includes: calculating the number ratio of the orders completed by AI customer service in the actual consultation orders corresponding to each value combination; and acquiring the consultation probability of each value combination according to the actual consultation ratio and the order quantity ratio of each value combination.
In some embodiments, after the broadcasting to the client in sequence by the AI customer service, the method further includes: obtaining a current consultation order of the client, and judging whether the current consultation order is predicted to be the alternative consultation order; if yes, storing the current consultation order into the database, and updating the consultation probability of each value combination according to the characteristic value group of the current consultation order; if not, storing the current consultation order into the database, and adjusting the value of one or more consultation dimensions according to the characteristic value group of the current consultation order until the prediction accuracy of all the existing incoming calls exceeds a threshold value.
In some embodiments, the advisory dimensions include: order type, incoming call time and the existence of order notification in the preset time before the incoming call; the order type values include: the type of the air ticket order and the type of the hotel order; the values of the incoming call time comprise: before and after the order trip; the value of whether the order notification exists in the preset time before the incoming call comprises the following values: with order notification and no order notification.
In some embodiments, after calculating the consulting probability of each associated order, the method further includes: acquiring the order opening times, page browsing time and page nesting times of each browsed associated order in a preset time period before the incoming call request of the client; calculating the user preference weight of each browsed associated order according to the weights corresponding to the order opening times, the page browsing time and the page nesting times; and adjusting the consultation probability of each associated order according to the user preference weight of each browsed associated order.
In some embodiments, the order opening times of an associated order is the total number of times the self-order viewing top page enters the order page of the associated order; the page browsing time of a related order is the total browsing time of an order page of the related order; the page nesting times of a related order are the total times of entering order pages of other related orders by taking the order page of the related order as a root page; the weight corresponding to the page nesting times is larger than the weight corresponding to the order opening times and is larger than the weight corresponding to the page browsing time.
Another aspect of the present invention provides a forecasting system for a consultation order, including: the incoming call response module is used for responding to an incoming call request of the client and acquiring a correlation order according to the incoming call number; the probability calculation module is used for extracting a characteristic value of each consultation dimension according to the incoming call request and each associated order to form a characteristic value group of each associated order, and calculating the consultation probability of each associated order according to the characteristic value group of each associated order; and the prediction broadcasting module is used for predicting one or more associated orders with the highest consultation probability as alternative consultation orders and sequentially broadcasting the alternative consultation orders to the client through AI customer services.
Yet another aspect of the present invention provides an electronic device, comprising: a processor; a memory having executable instructions stored therein; wherein the executable instructions, when executed by the processor, implement the method for forecasting consultation orders of any of the above embodiments.
Yet another aspect of the present invention provides a computer-readable storage medium storing a program which, when executed by a processor, implements the consultation order prediction method according to any of the above-mentioned embodiments.
Compared with the prior art, the invention has the beneficial effects that:
according to the incoming call number prediction consultation order, the consultation order is automatically broadcasted for the user to select, the user does not need to manually input the order number, the use experience of the user is improved, the utilization rate of intelligent customer service is improved, and the manual customer service cost is saved; the consultation probability of the associated order is obtained at least according to the actual consultation ratio calculation of the value combination of the corresponding consultation dimension, so that the method is convenient and quick, the response speed of the intelligent customer service can be improved, and the calculation resources are saved; the consultation probability of the associated order can be obtained by calculating according to the number ratio of the orders completed by the intelligent customer service, so that the prediction accuracy of the consultation orders butted by the intelligent customer service is improved; after each prediction, updating the database according to the current consultation order, adjusting and optimizing the prediction algorithm of the consultation order, and improving the prediction accuracy; the preference weight of the user to each associated order can be obtained through the browsing behavior of the user, and the consultation probability of each associated order is adjusted accordingly, so that the prediction accuracy of the consultation orders is further improved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention. It is obvious that the drawings described below are only some embodiments of the invention, and that for a person skilled in the art, other drawings can be derived from them without inventive effort.
FIG. 1 is a schematic diagram illustrating steps of a method for forecasting consultation orders according to an embodiment of the present invention;
FIG. 2 is a graph showing the distribution of incoming call quantity over incoming call time for an actual consultation order according to an embodiment of the present invention;
FIG. 3 is a schematic diagram showing steps of a forecast method of consulting orders in a further embodiment of the present invention;
FIG. 4 is a schematic diagram showing steps of a forecast method of consulting orders in a further embodiment of the present invention;
FIG. 5 is a block diagram of a forecast system for consulting orders in accordance with an embodiment of the present invention;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art.
The drawings are merely schematic illustrations of the invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus their repetitive description will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.
In addition, the flow shown in the drawings is only an exemplary illustration, and not necessarily includes all the steps. For example, some steps may be divided, some steps may be combined or partially combined, and the actual execution sequence may be changed according to the actual situation. It should be noted that features of the embodiments of the invention and of the different embodiments may be combined with each other without conflict.
The invention mainly aims to design a prediction algorithm of a consultation order by combining the order data (including the actual consultation order of the existing incoming call and the associated order of the incoming call number of the existing incoming call) of the existing incoming call stored in the database, predict the order which the user wants to consult according to the incoming call number of the user, realize that the user can inquire the order information which the user wants to consult without manually inputting the order number under most conditions, reduce the inquiry threshold of the user, reduce the labor cost of a ticket service platform and improve the satisfaction degree of the user.
The prediction algorithm of the consultation order is realized by the following steps during design: firstly, counting data and designing an algorithm: counting order data of all existing incoming calls, analyzing distribution conditions of relevant orders of all incoming call numbers in all dimensions, screening out consultation dimensions which have obvious influence on actual consultation orders of the existing incoming calls, and designing a calculation mode of order priority according to the consultation dimensions; secondly, compiling codes and building a system: the compiling algorithm realizes the prediction of consultation orders, so that most possible order data can be output when the incoming call number is input; thirdly, accessing the system, and optimizing the algorithm: and accessing the prediction algorithm of the consultation order into the intelligent customer service system, storing the corresponding relation between the incoming call number of the user and the actual consultation order into a database for calculating the accuracy rate, and analyzing and optimizing the prediction algorithm.
The prediction method of the consultation order is explained in detail below. Fig. 1 shows the main steps of a prediction method of a consultation order in an embodiment, and referring to fig. 1, the prediction method of a consultation order includes:
step S110, responding to the incoming call request of the client, and obtaining the associated order according to the incoming call number. The associated order of the incoming call number refers to all orders which are stored in the database within the valid period range and take the incoming call number as the mobile phone number of the contact person or the mobile phone number of the outgoing person.
And step S120, extracting the feature value of each consultation dimension according to the incoming call request and each associated order to form a feature value group of each associated order, and calculating the consultation probability of each associated order according to the feature value group of each associated order.
In one embodiment, the most relevant dimensions of the existing incoming call consultation order are order type, incoming call time, and whether the system sent a relevant notification to the user the previous hour of the incoming call, based on the existing data statistical analysis in the database. Therefore, in this embodiment, the consulting dimension includes: the order type, the incoming call time and the preset time before the incoming call are informed of the existence of the order. Each advisory dimension has multiple values. Specifically, the values of the order types include: an air ticket order type and a hotel order type (for example only, in other embodiments, the value of the order type may also include other order types such as a car and the like); the values of the incoming call time include: before and after the order trip; the value of whether the order notification exists in the preset time before the incoming call comprises the following steps: with order notification and no order notification. For an air ticket order, the travel time may refer to the departure time, and for a hotel order, the travel time may refer to the check-in time.
In the above listed consulting dimension, the incoming call time is a continuous random variable, and when the influence of the incoming call time on the actual consulting order is counted according to the actual consulting order of the existing incoming call, a distribution curve of the incoming call number of the actual consulting order along with the incoming call time as shown in fig. 2 is obtained by taking four hours as a dividing point. The actual consultation orders include hotel orders 210 and airline orders 220, and each n in the incoming call data may represent any suitable number, such as 100, 500, 1000, and so forth. As can be seen from fig. 2, the number of the actual consultation orders significantly changes before the trip 200a and after the trip 200b, so that the incoming call time value is divided into the order before the trip and the order after the trip.
In other embodiments, the incoming call time may be divided into other values, as long as the value division can significantly affect the distribution of the actual consultation order. Additionally, in other embodiments, the consulting dimension may also include other dimensions related to orders and/or related to incoming calls, and will not be further described herein.
Calculating the consultation probability of each associated order, comprising: calculating the actual consultation ratio of each value combination of each consultation dimension according to the actual consultation order of the existing incoming call stored in the database, and obtaining the consultation probability of each value combination at least according to the actual consultation ratio of each value combination; and acquiring the consultation probability of each associated order according to the value combination corresponding to the characteristic value set of each associated order.
An existing incoming call may be selected for a suitable historical period, such as the last half year. According to the actual consultation orders of each available incoming call, the distribution quantity of the actual consultation orders under different value combinations of each consultation dimension can be obtained, and the actual consultation ratio of each value combination is calculated according to the distribution quantity. In one embodiment, the actual consulting occupation ratio of each value combination is calculated according to the consulting dimensions and the values thereof, as shown in table 1 below.
Table 1: actual consult order-consult dimension proportion distribution table:
according to the actual consultation occupation ratio of each value combination obtained in the table 1, the consultation probability of each value combination can be obtained. For example, the actual consultation ratio of each value combination can be directly used as the consultation probability of each value combination, for example, the consultation probability of an air ticket order for which an order notification is sent within one hour before the incoming call before the trip is 19%.
In other embodiments, the consultation probability of each value combination can be obtained by combining other influence factors. For example, in one embodiment, after calculating the actual consulting proportion of each value combination of each consulting dimension, the method further includes: calculating the number ratio of the orders completed by the AI customer service in the actual consultation orders corresponding to each value combination; and acquiring the consultation probability of each value combination according to the actual consultation ratio and the order quantity ratio of each value combination. The actual consultation orders corresponding to each value combination comprise orders completed by intelligent customer service and orders transferred to manual customer service. By adding the number of the orders completed by the intelligent customer service to the calculation of the consultation probability of each value combination, the value combination more suitable for interaction between the intelligent customer service and the user can be more accurately calculated, and the prediction accuracy of the consultation orders docked by the intelligent customer service is improved.
Specifically, when the consulting probability of each value combination is calculated, the actual consulting proportion of each value combination can be multiplied by the number proportion of the orders completed by the intelligent customer service to serve as the consulting probability of each value combination. For example, for the air ticket order in which the order notification is sent within one hour before the incoming call before the trip, the consulting probability is calculated to be 16% by combining the actual consulting proportion and the order quantity proportion.
And step S130, predicting one or more associated orders with the highest consultation probability as alternative consultation orders, and sequentially broadcasting the alternative consultation orders to the client through AI customer services.
The number of alternative consultation orders can be set as desired. For example, the first three related orders with the largest consultation probability are selected as alternative consultation orders, and are sequentially broadcasted to the client according to the sequence from large consultation probability to small consultation probability, so that the user can select the order which the user actually wants to consult.
During specific implementation, the system for predicting the consultation orders can be accessed to the intelligent customer service system, so that when the intelligent customer service system receives an incoming call of a user, the system for predicting the consultation orders can be used for rapidly predicting the orders which the user may want to consult, and automatically broadcasting the orders to the user for selection.
In some cases, the associated orders obtained according to the incoming call number only include one or two cases with extremely small quantity, and the one or two associated orders with extremely small quantity can be directly broadcasted without the step of calculating the consultation probability of each associated order.
The broadcast may be a brief description of basic order information, for example, basic order information including travel time, travel location, and the like, so that the user can quickly locate a specific order.
By the method for predicting the consultation orders, the consultation orders can be predicted according to the incoming call numbers, the consultation orders can be automatically broadcasted for the user to select, the user does not need to manually input the order numbers, the use experience of the user is improved, the utilization rate of intelligent customer service is improved, and the cost of manual customer service is saved; the consultation probability of the associated order is obtained at least according to the actual consultation ratio calculation of the value combination of the corresponding consultation dimension, so that the method is convenient and quick, does not need complex algorithm logic, can improve the response speed of the intelligent customer service, and saves calculation resources; the consultation probability of the associated orders can be obtained through calculation according to the number ratio of the orders completed by the intelligent customer service, and the prediction accuracy of the consultation orders connected by the intelligent customer service is improved.
In one embodiment, the consulting preference weight of the user to each associated order can be obtained through the browsing behavior before the user sends the incoming call request, so that the consulting probability of each associated order is adjusted, and the predicting accuracy of the consulting order is further improved.
Fig. 3 shows a prediction method of consultation orders in another embodiment, and referring to fig. 3, on the basis of the prediction method in fig. 1, the prediction method of this embodiment further includes, after calculating a consultation probability of each associated order: step S310, acquiring order opening times, page browsing time and page nesting times of each browsed associated order in a preset time period before an incoming call request of a client; step S320, calculating the user preference weight of each browsed associated order according to the weights corresponding to the order opening times, the page browsing time and the page nesting times; step S330, according to the user preference weight of each browsed associated order, the consultation probability of each associated order is adjusted.
The order opening frequency of a related order is the total frequency of entering the order page of the related order from the order view home page within a preset time period, for example, within 1 hour before the incoming call request, and the viewing frequency of the related order by the user can be reflected. The page browsing time of a related order is the total browsing time of the order page of the related order in a preset time period. The page nesting times of a related order are the total times of entering order pages of other related orders in a preset time period by taking the order page of the related order as a root page.
Regarding the page nesting times, for example, the user views the home page from the order and enters the order page of the related order P11, and the order page of the related order P11 is the root page; after browsing the order page of the associated order P11 (for example, browsing for more than 5 seconds), the user enters another order page of the associated order P22 through a link displayed on the order page of the associated order P11, and then the page nesting time +1 of the associated order P11 is recorded as 2; then, the user may return to the order page of the associated order P11 and enter the order page of the associated order P33 through another link displayed on the order page of the associated order P11, or through a nested sub-page of the order page of the associated order P11, such as a link displayed on the order page of the associated order P22, and then the page nesting number +1 of the associated order P11 is recorded as 3; and by analogy, the page nesting times of each browsed associated order are counted, so that the consultation intention degree of the user to each browsed associated order is reflected.
The weight corresponding to the page nesting times is larger than the weight corresponding to the order opening times and larger than the weight corresponding to the page browsing time. When calculating the user preference weight of each browsed associated order, the order opening times, the page browsing time and the page nesting times of each browsed associated order may be weighted to obtain the user preference weight of each browsed associated order. Therefore, the consultation probability of the associated orders is adjusted according to the preference weight of the user, so that the consultation probability of each associated order not only accords with the universality rule of all orders, but also considers the user consultation requirement degree of each order, and the prediction accuracy of the consultation orders is improved.
In one embodiment, after the predicted alternative consultation orders are broadcasted to the user, the database is updated according to the consultation orders actually selected by the user, the prediction algorithm of the optimized consultation orders is adjusted, and the prediction accuracy is improved.
Fig. 4 shows a prediction method of a consultation order in another embodiment, and referring to fig. 4, based on the prediction method shown in fig. 1 or fig. 3, taking the prediction method shown in fig. 1 as an example, the prediction method of this embodiment further includes: step S410, obtaining a current consultation order of the client, and judging whether the current consultation order is predicted to be an alternative consultation order; step S420, if yes, storing the current consultation order into a database, and updating the consultation probability of each value combination according to the characteristic value group of the current consultation order; and step S430, if not, storing the current consultation order into a database, and adjusting the value of one or more consultation dimensions according to the characteristic value group of the current consultation order until the prediction accuracy of all the existing incoming calls exceeds a threshold value.
The current consultation order, that is, the order actually selected by the client for consultation, may be one of the alternative consultation orders, or may be other related orders that are not reported. In specific implementation, after the AI customer service broadcasts the complete selection consultation order, a voice prompt of 'please input order numbers if other orders need to be consulted' can be added, so that the user can input order numbers of other related orders which are not predicted as alternative consultation orders.
If the current consultation order is predicted to be the alternative consultation order, the prediction algorithm is accurate, so that the proportion condition of the actual consultation order of each value combination is updated according to the characteristic value group of the current consultation order, and the prediction algorithm of the consultation order is optimized along with the continuous increase of the existing calls. If the current consultation order is not predicted as the alternative consultation order, the prediction algorithm is deviated, and adjustment is needed.
When the prediction algorithm is adjusted, the values of one or more consulting dimensions may be adjusted, for example, the values of the incoming time are divided into: and calculating the consultation probability of each value combination of each consultation dimension again according to different value combinations of each regulated consultation dimension based on the actual consultation ratio and the order quantity ratio from 2 hours before the trip to 2 hours after the trip, wherein the value intervals are earlier than 2 hours before the trip and later than 2 hours after the trip.
And judging whether the actual consultation order of each existing incoming call in the database is predicted to be the alternative consultation order of the existing incoming call or not by utilizing all the existing incoming calls (including the newly stored incoming call request and the current consultation order) after the consultation probability of each value combination of each consultation dimension is recalculated until the prediction accuracy of all the existing incoming calls exceeds the threshold, if so, recording the prediction accuracy as 1, and otherwise, recording the prediction accuracy as 0. And finally, obtaining the prediction accuracy of all the existing incoming calls according to the ratio of the sum of the prediction accuracy of all the existing incoming calls to the number of all the existing incoming calls. The threshold value can be set according to needs, and in a preferred embodiment, the threshold value is the prediction accuracy rate of the last adjustment, so that each adjustment of the prediction algorithm can be further optimized.
Therefore, by adopting the prediction method of the consultation orders, when the user is in incoming call consultation, a plurality of orders which the user most possibly wants to inquire can be predicted according to the number of the incoming calls, and the content which the user wants to consult can be quickly positioned; meanwhile, the predicted order data are analyzed, the algorithm is continuously optimized, the accuracy is improved, and the consultation cost of the user and the manpower operation cost of the ticket service platform are reduced.
The embodiment of the invention also provides a prediction system of the consultation order, which can be used for realizing the prediction method of the consultation order described in any embodiment. The features and principles of the prediction method described in any of the above embodiments may be applied to the following prediction system embodiments. In the following embodiment of the forecasting system, the features and principles of the forecasting algorithm already set forth with respect to the consultation orders are not repeated.
FIG. 5 illustrates the major modules of a forecast system of consultation orders in an embodiment, and referring to FIG. 5, a forecast system 500 of consultation orders includes: an incoming call response module 510, configured to respond to an incoming call request of a client, and obtain an associated order according to an incoming call number; a probability calculation module 520, configured to extract a feature value of each consultation dimension according to the incoming call request and each associated order, form a feature value group of each associated order, and calculate a consultation probability of each associated order according to the feature value group of each associated order; and the prediction broadcasting module 530 is configured to predict one or more associated orders with the highest consultation probability as alternative consultation orders, and sequentially broadcast the alternative consultation orders to the client through the AI customer service.
Further, the forecasting system 500 for consulting orders may further include modules for implementing other process steps of the above-mentioned embodiments of forecasting methods, and specific principles of the modules may refer to the description of the above-mentioned embodiments of forecasting methods, and will not be repeated here.
As described above, the prediction system of the consultation order can predict the consultation order according to the incoming call number, automatically broadcast the consultation order for the user to select, does not need the user to manually input the order number, improves the use experience of the user, improves the utilization rate of intelligent customer service, and saves the cost of manual customer service; the consultation probability of the associated order is obtained at least according to the actual consultation ratio calculation of the value combination of the corresponding consultation dimension, so that the method is convenient and quick, the response speed of the intelligent customer service can be improved, and the calculation resources are saved; the consultation probability of the associated order can be obtained by calculating according to the number ratio of the orders completed by the intelligent customer service, so that the prediction accuracy of the consultation orders butted by the intelligent customer service is improved; after each prediction, updating the database according to the current consultation order, adjusting and optimizing the prediction algorithm of the consultation order, and improving the prediction accuracy; the preference weight of the user to each associated order can be obtained through the browsing behavior of the user, and the consultation probability of each associated order is adjusted accordingly, so that the prediction accuracy of the consultation orders is further improved.
The embodiment of the present invention further provides an electronic device, which includes a processor and a memory, where the memory stores executable instructions, and when the executable instructions are executed by the processor, the method for predicting a consultation order described in any of the above embodiments is implemented.
As described above, the electronic device of the invention can predict the consultation order according to the incoming call number, automatically broadcast the consultation order for the user to select, does not need the user to manually input the order number, improves the use experience of the user, improves the utilization rate of the intelligent customer service, and saves the cost of manual customer service; the consultation probability of the associated order is obtained at least according to the actual consultation ratio calculation of the value combination of the corresponding consultation dimension, so that the method is convenient and quick, the response speed of the intelligent customer service can be improved, and the calculation resources are saved; the consultation probability of the associated order can be obtained by calculating according to the number ratio of the orders completed by the intelligent customer service, so that the prediction accuracy of the consultation orders butted by the intelligent customer service is improved; after each prediction, updating the database according to the current consultation order, adjusting and optimizing the prediction algorithm of the consultation order, and improving the prediction accuracy; the preference weight of the user to each associated order can be obtained through the browsing behavior of the user, and the consultation probability of each associated order is adjusted accordingly, so that the prediction accuracy of the consultation orders is further improved.
Fig. 6 is a schematic structural diagram of an electronic device in an embodiment of the present invention, and it should be understood that fig. 6 only schematically illustrates various modules, and these modules may be virtual software modules or actual hardware modules, and the combination, the splitting, and the addition of the remaining modules of these modules are within the scope of the present invention.
As shown in fig. 6, the electronic device 600 is embodied in the form of a general purpose computing device. The components of the electronic device 600 include, but are not limited to: at least one processing unit 610, at least one memory unit 620, a bus 630 connecting the different platform components (including the memory unit 620 and the processing unit 610), a display unit 640, etc.
Wherein the storage unit stores program code executable by the processing unit 610 to cause the processing unit 610 to perform the steps of the method for forecasting consultation orders described in any of the above embodiments. For example, processing unit 610 may perform the steps shown in fig. 1.
The storage unit 620 may include readable media in the form of volatile memory units, such as a random access memory unit (RAM)6201 and/or a cache memory unit 6202, and may further include a read-only memory unit (ROM) 6203.
The memory unit 620 may also include programs/utilities 6204 including one or more program modules 6205, such program modules 6205 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.
The electronic device 600 may also communicate with one or more external devices 700, and the external devices 700 may be one or more of a keyboard, a pointing device, a bluetooth device, and the like. The external devices 700 enable a user to interactively communicate with the electronic device 600. The electronic device 600 may also be capable of communicating with one or more other computing devices, including routers, modems. Such communication may occur via an input/output (I/O) interface 650. Also, the electronic device 600 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network such as the Internet) via the network adapter 660. The network adapter 660 may communicate with other modules of the electronic device 600 via the bus 630. It should be appreciated that although not shown in the figures, other hardware and/or software modules may be used in conjunction with the electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms, to name a few.
The embodiment of the present invention further provides a computer-readable storage medium for storing a program, and when the program is executed, the method for predicting a consultation order described in any of the above embodiments is implemented. In some possible embodiments, the various aspects of the invention may also be implemented in the form of a program product comprising program code for causing a terminal device to perform the method for predicting a consultation order as described in any of the above embodiments, when the program product is run on the terminal device.
As described above, the computer-readable storage medium of the present invention can predict a consultation order according to an incoming call number, automatically broadcast for a user to select, without the user manually inputting an order number, thereby improving the user experience, improving the usage rate of intelligent customer service, and saving the cost of manual customer service; the consultation probability of the associated order is obtained at least according to the actual consultation ratio calculation of the value combination of the corresponding consultation dimension, so that the method is convenient and quick, the response speed of the intelligent customer service can be improved, and the calculation resources are saved; the consultation probability of the associated order can be obtained by calculating according to the number ratio of the orders completed by the intelligent customer service, so that the prediction accuracy of the consultation orders butted by the intelligent customer service is improved; after each prediction, updating the database according to the current consultation order, adjusting and optimizing the prediction algorithm of the consultation order, and improving the prediction accuracy; the preference weight of the user to each associated order can be obtained through the browsing behavior of the user, and the consultation probability of each associated order is adjusted accordingly, so that the prediction accuracy of the consultation orders is further improved.
The program product may employ a portable compact disc read only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited in this respect, and may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of readable storage media include, but are not limited to: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
A readable storage medium may include a propagated data signal with readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable storage medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device, such as through the internet using an internet service provider.
The foregoing is a more detailed description of the invention in connection with specific preferred embodiments and it is not intended that the invention be limited to these specific details. For those skilled in the art to which the invention pertains, several simple deductions or substitutions can be made without departing from the spirit of the invention, and all shall be considered as belonging to the protection scope of the invention.
Claims (10)
1. A method for forecasting a consultation order, comprising:
responding to an incoming call request of a client, and acquiring a related order according to an incoming call number;
extracting a feature value of each consultation dimension according to the incoming call request and each associated order to form a feature value group of each associated order, and calculating the consultation probability of each associated order according to the feature value group of each associated order;
and predicting one or more associated orders with the maximum consultation probability as alternative consultation orders, and sequentially broadcasting the alternative consultation orders to the client through AI customer service.
2. The prediction method of claim 1, wherein each of the consulting dimensions has a plurality of values, and wherein the calculating a consulting probability for each of the associated orders comprises:
calculating the actual consultation ratio of each value combination of each consultation dimension according to the actual consultation order of the existing incoming call stored in the database, and obtaining the consultation probability of each value combination at least according to the actual consultation ratio of each value combination;
and acquiring the consultation probability of each associated order according to the corresponding value combination of the characteristic value group of each associated order.
3. The prediction method of claim 2, wherein after calculating the actual consulting proportion for each combination of values of the consulting dimensions, the method further comprises:
calculating the number ratio of the orders completed by AI customer service in the actual consultation orders corresponding to each value combination; and
and acquiring the consultation probability of each value combination according to the actual consultation ratio and the order quantity ratio of each value combination.
4. The prediction method according to claim 2, wherein after the broadcasting to the client in sequence by the AI customer service, further comprising:
obtaining a current consultation order of the client, and judging whether the current consultation order is predicted to be the alternative consultation order;
if yes, storing the current consultation order into the database, and updating the consultation probability of each value combination according to the characteristic value group of the current consultation order;
if not, storing the current consultation order into the database, and adjusting the value of one or more consultation dimensions according to the characteristic value group of the current consultation order until the prediction accuracy of all the existing incoming calls exceeds a threshold value.
5. The prediction method of claim 2, wherein the consulting dimension comprises: order type, incoming call time and the existence of order notification in the preset time before the incoming call;
the order type values include: the type of the air ticket order and the type of the hotel order;
the values of the incoming call time comprise: before and after the order trip;
the value of whether the order notification exists in the preset time before the incoming call comprises the following values: with order notification and no order notification.
6. The forecasting method of claim 1, wherein after calculating the probability of consultation for each of the associated orders, further comprising:
acquiring the order opening times, page browsing time and page nesting times of each browsed associated order in a preset time period before the incoming call request of the client;
calculating the user preference weight of each browsed associated order according to the weights corresponding to the order opening times, the page browsing time and the page nesting times;
and adjusting the consultation probability of each associated order according to the user preference weight of each browsed associated order.
7. The forecasting method of claim 6, wherein the number of orders opened for an associated order is the total number of times the order view home page entered the order page for the associated order;
the page browsing time of a related order is the total browsing time of an order page of the related order;
the page nesting times of a related order are the total times of entering order pages of other related orders by taking the order page of the related order as a root page;
the weight corresponding to the page nesting times is larger than the weight corresponding to the order opening times and is larger than the weight corresponding to the page browsing time.
8. A forecasting system for a consultation order, comprising:
the incoming call response module is used for responding to an incoming call request of the client and acquiring a correlation order according to the incoming call number;
the probability calculation module is used for extracting a characteristic value of each consultation dimension according to the incoming call request and each associated order to form a characteristic value group of each associated order, and calculating the consultation probability of each associated order according to the characteristic value group of each associated order;
and the prediction broadcasting module is used for predicting one or more associated orders with the highest consultation probability as alternative consultation orders and sequentially broadcasting the alternative consultation orders to the client through AI customer services.
9. An electronic device, comprising:
a processor;
a memory having executable instructions stored therein;
wherein the executable instructions, when executed by the processor, implement the method of forecasting of a consultation order of any of claims 1-7.
10. A computer-readable storage medium storing a program, wherein the program when executed by a processor implements the consultation order prediction method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110762430.7A CN113469710B (en) | 2021-07-06 | 2021-07-06 | Consultation order prediction method, system, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110762430.7A CN113469710B (en) | 2021-07-06 | 2021-07-06 | Consultation order prediction method, system, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113469710A true CN113469710A (en) | 2021-10-01 |
| CN113469710B CN113469710B (en) | 2022-10-11 |
Family
ID=77878527
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110762430.7A Active CN113469710B (en) | 2021-07-06 | 2021-07-06 | Consultation order prediction method, system, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113469710B (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009054979A2 (en) * | 2007-10-24 | 2009-04-30 | Uat, Inc. | System and method for assigning responsibility for trade order execution |
| CN105657201A (en) * | 2016-01-26 | 2016-06-08 | 北京京东尚科信息技术有限公司 | Method and system for processing call based on decision tree model |
| CN107844862A (en) * | 2017-11-14 | 2018-03-27 | 泰康保险集团股份有限公司 | Order failure prediction method, apparatus, medium and electronic equipment |
| CN108537644A (en) * | 2018-04-23 | 2018-09-14 | 吉林亿联银行股份有限公司 | A kind of method and apparatus of customer service recommended products |
| CN108564244A (en) * | 2018-02-26 | 2018-09-21 | 新智数字科技有限公司 | Order processing method, apparatus, equipment and semiconductor readable storage medium storing program for executing |
| CN108874823A (en) * | 2017-05-12 | 2018-11-23 | 阿里巴巴集团控股有限公司 | The implementation method and device of intelligent customer service |
| CN109492837A (en) * | 2018-12-29 | 2019-03-19 | 携程旅游网络技术（上海）有限公司 | Air ticket order insures method for pushing, device, electronic equipment, storage medium |
| CN109636378A (en) * | 2018-10-31 | 2019-04-16 | 阿里巴巴集团控股有限公司 | Account recognition methods and device, electronic equipment |
| CN109783632A (en) * | 2019-02-15 | 2019-05-21 | 腾讯科技（深圳）有限公司 | Customer service information-pushing method, device, computer equipment and storage medium |
| CN110110881A (en) * | 2019-03-21 | 2019-08-09 | 贵州电网有限责任公司 | Power customer requirement forecasting analysis method and system |
| CN110599192A (en) * | 2018-05-23 | 2019-12-20 | 阿里巴巴集团控股有限公司 | User order positioning method, device and system |
| CN112561112A (en) * | 2019-09-10 | 2021-03-26 | 北京三快在线科技有限公司 | Order distribution method and device, computer readable storage medium and electronic equipment |
| CN112819263A (en) * | 2019-10-31 | 2021-05-18 | 北京沃东天骏信息技术有限公司 | Method and device for dispatching customer service |
-
2021
- 2021-07-06 CN CN202110762430.7A patent/CN113469710B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2009054979A2 (en) * | 2007-10-24 | 2009-04-30 | Uat, Inc. | System and method for assigning responsibility for trade order execution |
| CN105657201A (en) * | 2016-01-26 | 2016-06-08 | 北京京东尚科信息技术有限公司 | Method and system for processing call based on decision tree model |
| CN108874823A (en) * | 2017-05-12 | 2018-11-23 | 阿里巴巴集团控股有限公司 | The implementation method and device of intelligent customer service |
| CN107844862A (en) * | 2017-11-14 | 2018-03-27 | 泰康保险集团股份有限公司 | Order failure prediction method, apparatus, medium and electronic equipment |
| CN108564244A (en) * | 2018-02-26 | 2018-09-21 | 新智数字科技有限公司 | Order processing method, apparatus, equipment and semiconductor readable storage medium storing program for executing |
| CN108537644A (en) * | 2018-04-23 | 2018-09-14 | 吉林亿联银行股份有限公司 | A kind of method and apparatus of customer service recommended products |
| CN110599192A (en) * | 2018-05-23 | 2019-12-20 | 阿里巴巴集团控股有限公司 | User order positioning method, device and system |
| CN109636378A (en) * | 2018-10-31 | 2019-04-16 | 阿里巴巴集团控股有限公司 | Account recognition methods and device, electronic equipment |
| CN109492837A (en) * | 2018-12-29 | 2019-03-19 | 携程旅游网络技术（上海）有限公司 | Air ticket order insures method for pushing, device, electronic equipment, storage medium |
| CN109783632A (en) * | 2019-02-15 | 2019-05-21 | 腾讯科技（深圳）有限公司 | Customer service information-pushing method, device, computer equipment and storage medium |
| CN110110881A (en) * | 2019-03-21 | 2019-08-09 | 贵州电网有限责任公司 | Power customer requirement forecasting analysis method and system |
| CN112561112A (en) * | 2019-09-10 | 2021-03-26 | 北京三快在线科技有限公司 | Order distribution method and device, computer readable storage medium and electronic equipment |
| CN112819263A (en) * | 2019-10-31 | 2021-05-18 | 北京沃东天骏信息技术有限公司 | Method and device for dispatching customer service |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113469710B (en) | 2022-10-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109377329B (en) | House resource recommendation method and device, storage medium and electronic equipment | |
| CN110555640B (en) | Route planning method and device | |
| CN108683818B (en) | Method, system, equipment and storage medium for distributing seats in call center | |
| CN109033342B (en) | Service providing method and device applied to service system and service model | |
| CN111611514B (en) | Page display method and device based on user login information and electronic equipment | |
| US20200134361A1 (en) | Data processing method and apparatus | |
| CN112015562A (en) | Resource allocation method and device based on transfer learning and electronic equipment | |
| US8392392B1 (en) | Voice request broker | |
| CN111598713B (en) | Cluster recognition method and device based on similarity weight updating and electronic equipment | |
| CN113971243A (en) | Data processing method, system, equipment and storage medium applied to questionnaire survey | |
| CN112015977A (en) | Customized information pushing method and device and electronic equipment | |
| CN109040000B (en) | User identification method and system based on IP address | |
| CN108965619B (en) | Call processing method, call center, electronic device, and storage medium | |
| CN109086429B (en) | IVR voice navigation method, system, equipment and storage medium | |
| CN111044062B (en) | Path planning and recommending method and device | |
| CN113469710B (en) | Consultation order prediction method, system, electronic equipment and storage medium | |
| CN113379229A (en) | Resource scheduling method and device | |
| CN116414955B (en) | Intelligent queuing method, device, equipment and medium based on client intention and intention | |
| CN115758169A (en) | Intelligent matching method, system, equipment and storage medium for network service platform | |
| CN110796543A (en) | Method and device for obtaining customized information based on relational network and electronic equipment | |
| CN115858937A (en) | Cloud computer recommendation method and system applied to mobile office | |
| CN112015978B (en) | Custom information sending method and device and electronic equipment | |
| CN115619142A (en) | Method, device, equipment and computer readable medium for matching data | |
| KR20080037172A (en) | Method for furnishing phone number search ranking and/or economic trend index using database of phone number and system for the same | |
| CN113780703B (en) | Index adjustment method and device |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |