Intelligent customer service system and method based on intention recognition

Abstract

The invention relates to the field of customer service processing, in particular to an intelligent customer service system and method based on intention recognition, and the system comprises a response evaluation module which is used for responding to a response evaluation condition to determine a response analysis strategy for a to-be-responded target; the execution analysis module is used for determining an execution analysis mode based on the processing execution difference index and the response quality difference index so as to determine an execution evaluation coefficient, and responding to a response setting condition so as to determine a setting mode of a response processing coefficient; the reference analysis module is used for responding to a target reference condition to determine a setting mode of a response processing coefficient of the second-class response target; and the service processing module is connected with the execution analysis module and the reference analysis module, and is used for periodically determining whether to schedule the target to be responded or not based on the node processing coefficient of each target service node, and the uniformity of a customer service processing task allocation result is improved.

Description

Technical Field

[0001] The present invention relates to the field of customer service processing, and in particular to an intelligent customer service system and method based on intent recognition. Background Art

[0002] Determining the inquiry intention of the customer service object based on intent recognition can provide effective guidance for subsequent customer service and task allocation, thereby ensuring the overall customer service processing efficiency. However, when facing electronic devices or other types of technical equipment, there are differences in the degree of cognition between different service objects, and the existing intelligent customer service solutions based on intent recognition often only determine the intention based on the information provided by the service object to perform processing task allocation, and fail to consider the differences in actual processing efficiency caused by the different cognition of the inquired device among the service objects, resulting in uneven task allocation in the actual customer service process. Therefore, how to determine targeted analysis methods based on the service object's cognition of the inquired device to ensure the accuracy of the estimated results of the processing difficulty for the service object is a problem that needs to be urgently solved by technical personnel in this field.

[0003] Chinese patent publication number CN112784039A discloses a method, device and storage medium for allocating online customer service, specifically obtaining the current user consultation question, and then inputting the user consultation question into a pre-trained intent prediction model to generate an intent classification label, wherein the intent prediction model is trained based on the user's order information, operation information and the intent classification label determined by the user's first user consultation question on the consultation page, and finally, based on the intent classification label, the type of consultation entrance is determined, and the user is assigned an online customer service corresponding to the consultation entrance. The above scheme has the following problems: It fails to consider the impact of the differences in the cognition of the consultation product between different users on the processing of the consultation task, which leads to poor uniformity of the task allocation results. Summary of the invention

[0004] To this end, the present invention provides an intelligent customer service system and method based on intent recognition, so as to overcome the problem that the prior art fails to consider the impact of differences in cognition of different users on the consulted products on the difficulty of customer service processing, thereby resulting in poor uniformity of task allocation results.

[0005] To achieve the above objectives, the present invention provides an intelligent customer service system based on intent recognition, comprising: A response evaluation module, which is used to respond to the response evaluation conditions to determine the response analysis strategy corresponding to each target to be responded to as the target execution analysis or information reference analysis; an execution analysis module connected to the response evaluation module, for determining an execution analysis method based on a processing execution difference index and a response quality difference index to obtain an execution evaluation coefficient, and for responding to a response setting condition to determine a setting method of the response processing coefficient to determine the execution evaluation coefficient based on an information association index and an associated reference execution index, or to determine the execution evaluation coefficient based on an information association index and an analysis interference index; A reference analysis module connected to the response evaluation module for responding to the target reference condition to determine the response processing coefficients of the second type of response targets in a setting manner based on the information pointing parameter and the pointing execution parameter, or the target execution coefficient and the information pointing parameter to determine the response processing coefficients of the second type of response targets; The service processing module is respectively connected to the execution analysis module and the reference analysis module, and is used to periodically determine whether to schedule the target to be responded to based on the node processing coefficient of each target service node.

[0006] Furthermore, if the response evaluation condition responded by the response evaluation module is that there is a type of response target, the determination execution analysis module performs target execution analysis on the type of response target, and the target execution analysis includes: The execution analysis module determines the execution analysis mode based on the processing execution difference index and the response quality difference index of a type of response target in response to the execution analysis condition; The execution analysis module determines, in response to the execution evaluation completion condition, a setting method of a response processing coefficient for a class of response targets based on the execution evaluation coefficient; The execution analysis condition is that the response evaluation module determines that the execution analysis module performs target execution analysis on any type of response target, and the execution evaluation completion condition is that the execution evaluation coefficient of a type of response target is completed and determined; The first type of response target is a target to be responded to whose expression standard index is greater than a preset expression standard index or whose reference processing execution coefficient is greater than a preset reference processing execution coefficient.

[0007] Further, the analysis setting condition of the execution analysis module response is that the execution stability coefficient is greater than the preset execution stability coefficient, then the execution evaluation coefficient of a type of response target is determined based on the information association index and the associated reference execution index; The execution evaluation coefficient is positively correlated with the information association index and the association reference execution index respectively, and the execution stability coefficient is determined according to the processing execution difference index of a class of response targets and the response quality difference index.

[0008] Further, if the analysis setting condition of the execution analysis module response is that the execution stability coefficient is less than or equal to the preset execution stability coefficient, it is determined that the execution evaluation coefficient of a type of response target is determined based on the information association index and the analysis interference index, and whether to adjust the execution evaluation coefficient based on the relevant execution parameters; The evaluation adjustment condition responded by the execution analysis module is that the relevant execution parameter is greater than the preset relevant execution parameter, then it is determined to increase the execution evaluation coefficient according to the relevant execution parameter.

[0009] Further, if the response setting condition responded by the execution analysis module is that the execution evaluation coefficient is greater than the preset execution evaluation coefficient, it is determined that the response processing coefficient of a type of response target is determined based on the execution evaluation coefficient and the associated reference execution index; The response setting condition responded by the execution analysis module is that the execution evaluation coefficient is less than or equal to the preset execution evaluation coefficient, and then the response processing coefficient of a type of response target is determined based on the execution evaluation coefficient and the execution stability coefficient.

[0010] Furthermore, if the response evaluation condition responded by the response evaluation module is that there are two types of response targets, the reference analysis module is determined to perform information reference analysis on the two types of response targets, and the information reference analysis includes: The reference analysis module responds to the reference analysis condition and determines the setting method of the response processing coefficient of the second type of response target based on the information reference index and the information overlap index of the second type of response target; The reference analysis condition is that the response evaluation module determines that the reference analysis module performs information reference analysis on any two types of response targets; The second type of response targets are targets to be responded to whose expression standard index is less than or equal to the preset expression standard index and whose reference processing execution coefficient is less than or equal to the preset reference processing execution coefficient.

[0011] Further, if the target reference condition responded by the reference analysis module is that the information reference index is greater than the preset information reference index or the information overlap index is greater than the preset information overlap index, the response processing coefficients of the second type of response targets are determined based on the information pointing parameter and the pointing execution parameter; The target reference condition responded by the reference analysis module is that the information reference index is less than or equal to the preset information reference index and the information overlap index is less than or equal to the preset information overlap index, then the response processing coefficient of the second type of response target is determined based on the target execution coefficient and the information pointing parameter.

[0012] Further, the service analysis module periodically responds to the node processing difference coefficient of the target scheduling condition to determine whether to perform task scheduling for the pending response target of the key service node; If the target scheduling condition responded by the service analysis module is that the node processing difference coefficient is greater than the preset node processing difference coefficient, it is determined to perform task scheduling for the scheduling response target of the key service node; The node processing difference coefficient is determined based on the node processing coefficient of each target service node.

[0013] Further, the service analysis module responds to the scheduling response coefficient of the scheduling setting condition to determine the scheduling response target of each key service node, and the scheduling response coefficient is determined according to the response processing coefficient and the analysis related index; If the dispatch setting condition responded by the service analysis module is that there is a dispatch response coefficient of a pending response target that is greater than a preset dispatch response coefficient, the pending response target is determined to be a dispatch response target; The service analysis module responds to the target scheduling condition and determines the transfer service node of each scheduling response target based on the analysis of the relevant index. The target scheduling condition is that each key service node completes the determination of the scheduling response target.

[0014] The present invention also provides a method applied to the intelligent customer service system based on intention recognition, comprising: The response analysis strategy for the target to be responded to is determined based on the expression standard index and the reference processing execution coefficient, which is to perform target execution analysis or information reference analysis on the target to be responded to; Under the target execution analysis, an execution analysis method of a type of response target is determined according to the processing execution difference index and the response quality difference index. The execution analysis method is to determine an execution evaluation coefficient of a type of response target based on the information association index and the association reference execution index, or the information association index and the analysis interference index. Under the condition of completion of the execution evaluation, the setting method of determining the response processing coefficient of a type of response target based on the execution evaluation coefficient is to determine the response processing coefficient of a type of response target based on the execution evaluation coefficient and the associated reference execution index, or, the execution evaluation coefficient and the execution stability coefficient; Under the information reference analysis, the setting method of determining the response processing coefficient of the second type of response target according to the information reference index and the information overlap index is to determine the response processing coefficient of the second type of response target based on the information pointing parameter and the pointing execution parameter, or the target execution coefficient and the information pointing parameter; Periodically determine whether to schedule tasks for the pending response targets of the target service node based on the node processing difference coefficient, determine the scheduling response targets of each key service node based on the scheduling response coefficient, and determine the transfer service node of each scheduling response target based on the analysis of the relevant index.

[0015] Compared with the prior art, the beneficial effect of the present invention lies in that the technical scheme of the present invention determines a targeted response analysis strategy according to the expression standard index of the target to be responded to and the reference processing execution coefficient, so that the analysis process of the target to be responded to takes into account the differences in the cognition of the problems faced by different targets to be responded to, thereby avoiding the influence of the cognitive situation on the response processing coefficient. The present invention improves the effectiveness of the determined response processing coefficient of each target to be responded to, thereby improving the uniformity of the customer service processing task allocation results.

[0016] Furthermore, the present invention characterizes the effectiveness of the problem description of the target to be responded to the problems it faces at present and in the past, as well as the ability to execute problem-solving measures, based on the expression standard index and the reference processing execution coefficient, so as to determine the degree of cognition of the inquiry items by different targets to be responded to, provide effective support for the subsequent determination of targeted response analysis strategies, and thus ensure the degree of adaptation of the set response analysis strategy to the actual analysis process.

[0017] Furthermore, in the present invention, for a class of response targets, an execution stability coefficient is determined based on the processing execution difference index and the response quality difference index of the class of response targets, and an execution analysis method is determined based on the execution stability coefficient. The execution analysis method is determined based on the execution stability coefficient to avoid differences in the processing records of the targets to be responded to with better cognitive conditions, thereby improving the accuracy of the determination results of the response processing coefficients for the class of response targets and ensuring the uniformity of the customer service processing task allocation results.

[0018] Furthermore, in the present invention, for the second-category response target, the setting method of the response processing coefficient of the second-category response target is determined according to the information reference index and the information overlap index, that is, the targeted setting method is determined based on the difficulty of inferring the root cause of the fault based on the initial service information of the second-category response target, so that the determination method of the response processing coefficient is more in line with the actual situation of the second-category response target. The present invention ensures the accuracy of the determined response processing coefficient.

[0019] Furthermore, the present invention determines whether to perform task scheduling for the pending response target of the key service node based on the node processing difference coefficient between the target service nodes, and determines the scheduling response target and its corresponding transfer service node based on the response processing coefficient and analysis of the relevant index to ensure the uniformity of the processing intensity and time consumption of each target service node. The present invention improves the overall efficiency in the processing process of the pending response target. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a module connection diagram of the intelligent customer service system based on intent recognition of the present invention; Figure 2A flowchart of the method for performing analysis determined by the analysis module of the present invention in response to analysis setting conditions; Figure 3 A flow chart of the service analysis module of the present invention responding to a target scheduling condition to determine whether to perform task scheduling for a target to be responded to by a target service node; Figure 4 It is a schematic diagram of the intelligent customer service method based on intent recognition of the present invention. DETAILED DESCRIPTION

[0021] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0022] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0023] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0024] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0025] See also Figures 1 to 3 As shown, the present invention provides an intelligent customer service system based on intent recognition, comprising: A response evaluation module, which is used to respond to the response evaluation conditions to determine the response analysis strategy corresponding to each target to be responded to as the target execution analysis or information reference analysis; an execution analysis module connected to the response evaluation module, for determining an execution analysis method based on a processing execution difference index and a response quality difference index to obtain an execution evaluation coefficient, and for responding to a response setting condition to determine a setting method of the response processing coefficient to determine the execution evaluation coefficient based on an information association index and an associated reference execution index, or to determine the execution evaluation coefficient based on an information association index and an analysis interference index; A reference analysis module connected to the response evaluation module for responding to the target reference condition to determine the response processing coefficients of the second type of response targets in a setting manner based on the information pointing parameter and the pointing execution parameter, or the target execution coefficient and the information pointing parameter to determine the response processing coefficients of the second type of response targets; The service processing module is respectively connected to the execution analysis module and the reference analysis module, and is used to periodically determine whether to schedule the target to be responded to based on the node processing coefficient of each target service node.

[0026] The present invention is used to arrange and dispatch customer service for a certain category of goods. During the arrangement and dispatch process, the category of goods to be served is recorded as the target service category. If a service request from any buyer of goods is received, the buyer of the goods is recorded as the target to be responded to, and the target to be responded to is analyzed to determine its response processing coefficient. The response analysis strategy used is determined according to the expression standard index of the target to be responded to and the reference processing execution coefficient. There are also several target service nodes in the present invention to provide customer service for each target to be responded to. The target service category in the present invention includes but is not limited to: smart phones, smart wearable devices, smart home systems and laptop computers; Several service analysis records are applied in the present invention, and any service analysis record records the expression standard index, reference processing execution coefficient, execution stability coefficient, associated judgment quantity, relevant execution parameters, information reference index, information overlap index, node processing difference coefficient and scheduling response coefficient in at least one allocation process of processing tasks for pending responses, and each service analysis record corresponds to a qualified mark, which records whether the uniformity of the customer service processing task allocation result meets the user's requirements. It can be understood that the user can determine whether the uniformity of the customer service processing task allocation result meets the requirements based on self-set indicators. For example, the self-set indicators can be but are not limited to the service response difference parameter, which is the absolute value of the difference between the maximum and minimum values ​​of the remaining unprocessed pending responses of the target service node.

[0027] Specifically, the response evaluation condition responded by the response evaluation module is that there is a type of response target, then the determination execution analysis module performs target execution analysis on the type of response target, and the target execution analysis includes: The execution analysis module determines the execution analysis mode based on the processing execution difference index and the response quality difference index of a type of response target in response to the execution analysis condition; The execution analysis module determines, in response to the execution evaluation completion condition, a setting method of a response processing coefficient for a class of response targets based on the execution evaluation coefficient; The execution analysis condition is that the response evaluation module determines that the execution analysis module performs target execution analysis on any type of response target, and the execution evaluation completion condition is that the execution evaluation coefficient of a type of response target is completed and determined; The first type of response target is a target to be responded to whose expression standard index is greater than a preset expression standard index or whose reference processing execution coefficient is greater than a preset reference processing execution coefficient.

[0028] Among them, the present invention applies historical service records, which include records of each service process of each target service node, and the historical service records all include initial service information corresponding to each service process and the final problem location, and the expression standard index of the initial service information of the target to be answered in each service process in its historical service record is detected. The historical service record is a collection of several customer service processes for the target to be answered, and the target service categories corresponding to each service process in the historical service record are the same. The text information used to describe the service requirements of the target to be answered for the first time after sending the service request in each service process is recorded as the initial service information, and for a single initial service Information, the expression standard index is the number of professional phrases of the target service category in the initial service information, the reference processing execution coefficient is the average execution duration of the solution provided by the target to be responded to the target service node in each service process, for a single service process, the execution duration is the interval between the moment when the target service node provides the solution and the moment when the target to be responded ends the service process, how to determine the professional phrases of each target service category is easy to understand for those skilled in the art, for example, if the target service category is a smart home system, its corresponding professional phrases include but are not limited to: ZigBee protocol, gateway device, scene mode, automation rules and device linkage; If there is a target to be responded to whose expression standard index is greater than the preset expression standard index or whose reference processing execution coefficient is greater than the preset reference processing execution coefficient, it is determined to perform target execution analysis on the target to be responded to whose expression standard index is greater than the preset expression standard index or whose reference processing execution coefficient is greater than the preset reference processing execution coefficient. The values ​​of the preset expression standard index and the preset reference processing execution coefficient can be determined by the user according to the actual work scenario. For example, the user can set them according to the service analysis record. The higher the user's requirement for the uniformity of the customer service processing task allocation result, the smaller the value of the preset expression standard index and the smaller the value of the preset reference processing execution coefficient. A method for determining the value of the preset expression standard index is provided. The service analysis record for information reference analysis on the target to be responded to is recorded as an evaluation reference record. The maximum value of the expression standard index in the evaluation reference record that meets the user's requirement for the uniformity of the customer service processing task allocation result is recorded as the preset expression standard index. A method for determining the value of the preset reference processing execution coefficient is provided. The maximum value of the reference processing execution coefficient in the evaluation reference record that meets the user's requirement for the uniformity of the customer service processing task allocation result is recorded as the preset reference processing execution coefficient.

[0029] Specifically, if the analysis setting condition of the execution analysis module response is that the execution stability coefficient is greater than the preset execution stability coefficient, it is determined that the execution evaluation coefficient of a type of response target is determined based on the information association index and the associated reference execution index; The execution evaluation coefficient is positively correlated with the information association index and the association reference execution index respectively, and the execution stability coefficient is determined according to the processing execution difference index of a class of response targets and the response quality difference index.

[0030] Among them, for a single first-class response target, the execution stability coefficient = 1 / (response quality difference index + processing execution difference index), the response quality difference index , n is the number of service processes of this type of response target in the historical service records, yi is the expression standard index corresponding to the i-th service process of this type of response target in the historical service records, y0 is the average value of the expression standard index corresponding to each service process of this type of response target in the historical service records, and the processing execution difference index , di is the execution duration corresponding to the i-th service process of this type of response target in the historical service records, and d0 is the average execution duration corresponding to each service process of this type of response target in the historical service records; The value of the preset execution stability coefficient can be determined by the user according to the actual work scenario. For example, the user can set it according to the service analysis record. The higher the user's requirement for the uniformity of the customer service processing task allocation result, the larger the value of the preset execution stability coefficient. A method for determining the value of the preset execution stability coefficient is provided. The service analysis record for determining the execution evaluation coefficient of a class of response targets based on the information association index and the associated reference execution index is recorded as the execution reference record. The minimum value of the execution stability coefficient in the execution reference record that meets the user's requirement for the uniformity of the customer service processing task allocation result is recorded as the preset execution stability coefficient. If the execution stability coefficient of a type of response target is greater than the preset execution stability coefficient, it indicates that the overall cognition of the type of response target for the target processing category is good and always remains stable, that is, it indicates that the cognition of the type of response target is relatively comprehensive. Therefore, it is necessary to evaluate the processing difficulty of the initial service information that the type of response target currently needs to process, and determine the execution evaluation coefficient of the type of response target based on the information relevance index and the associated reference execution index. For a single type of response target, the execution evaluation coefficient = ln (information relevance index × associated reference execution index), the information relevance index is the number of associated problem locations corresponding to the professional phrases contained in the initial service information of the type of response target, and the associated reference execution index is the average execution processing time of each associated problem location corresponding to the professional phrases contained in the initial service information of the type of response target. For a single problem location of the target processing category, if the number of associated judgments of the problem location is greater than the preset number of associated judgments, the problem location is recorded as the associated problem location of the type of response target, and the number of associated judgments is the initial problem location involved in the problem location. The number of professional phrases contained in the initial service information and the initial service information of the response target of this type. If there is a service process in the historical service record whose final fault factor is the problem location, it is determined that the problem location involves the initial service information corresponding to the service process. For a single associated problem location, the execution processing time is the average processing time of each service process determined as the associated problem location after analysis in the historical service record. For a single service process, the processing time is the interval between the time when the service request of the corresponding target to be responded is received and the end time of the service process. The problem location is the possible fault factor of the target processing category. How to determine the corresponding fault factor of the target processing category is easy for technicians in this field to understand. For example, if the target processing category is a smart home system, the problem location includes but is not limited to: power adapter damage, loose power cord or poor contact, internal power module failure, motherboard failure, memory failure, system file damage, network connection interruption, signal interference or attenuation, actuator failure, firmware version mismatch, and temperature is too high or too low. The value of the preset number of associated determinations can be determined by the user according to the actual work scenario. For example, the user can set it according to the service analysis record. The higher the user's requirement for the uniformity of the customer service processing task allocation result, the larger the value of the preset number of associated determinations. A method for determining the value of the preset number of associated determinations is provided, and the average value of the number of associated determinations for each associated problem location in the service analysis record that meets the user's requirement for the uniformity of the customer service processing task allocation result is recorded as the preset number of associated determinations.

[0031] Specifically, if the analysis setting condition of the execution analysis module response is that the execution stability coefficient is less than or equal to the preset execution stability coefficient, it is determined to determine the execution evaluation coefficient of a type of response target based on the information association index and the analysis interference index, and whether to adjust the execution evaluation coefficient based on the relevant execution parameters; The evaluation adjustment condition responded by the execution analysis module is that the relevant execution parameter is greater than the preset relevant execution parameter, then it is determined to increase the execution evaluation coefficient according to the relevant execution parameter.

[0032] Among them, if the execution stability coefficient of a type of response target is less than or equal to the preset execution stability coefficient, it means that although the overall cognition of the target processing category of the type of response target is good, the type of response target has a one-sided unclear cognition, which will interfere with the processing process and information expression. Therefore, it is necessary to further analyze the current initial service information of the type of response target to determine the cognition of the type of response target for the initial service information currently provided to determine the execution evaluation coefficient of the type of response target, determine the execution evaluation coefficient of the type of response target based on the information correlation index and the analysis interference index, and determine whether it is necessary to adjust the execution evaluation coefficient according to the relevant execution parameters; For a type of response target whose single execution stability coefficient is less than or equal to the preset execution stability coefficient, the initially determined execution evaluation coefficient of the type of response target = ln (information association index × analysis interference index), the analysis interference index = the number of interference problem locations of the type of response target / the number of associated problem locations of the type of response target, the interference problem location is the associated problem location with the number of associated judgments greater than the preset interference index, the relevant execution parameter = the number of relevant execution phrases of the type of response target / the information association index of the type of response target, the execution duration is greater than the average execution duration corresponding to each service process in the historical service record of the type of response target The professional phrases involved in the initial service information of the service process are recorded as relevant execution phrases. If the relevant execution parameters of the response target of this type are greater than the preset relevant execution parameters, the execution evaluation coefficient initially determined is increased and adjusted according to the relevant execution parameters. The increase value of the execution evaluation coefficient initially determined is positively correlated with the relevant execution parameters. The setting method of the response coefficient of the response target of this type is determined according to the execution evaluation coefficient after the increase adjustment. If the relevant execution parameters of the response target of this type are less than or equal to the preset relevant execution parameters, the execution evaluation coefficient initially determined is not adjusted, that is, the setting method of the response coefficient of the response target of this type is determined according to the execution evaluation coefficient initially determined. The values ​​of the preset interference index and the preset related execution parameters can be determined by the user according to the actual work scenario. For example, the user can set them according to the service analysis record. The higher the user's requirement for the uniformity of the customer service processing task allocation result, the larger the value of the preset interference index and the smaller the value of the preset related execution parameter. A method for determining the value of the preset interference index is provided, and the minimum value of the associated determination number of each interference problem location in the service analysis record that meets the user's requirement for the uniformity of the customer service processing task allocation result is recorded as the preset interference index. A method for determining the value of the preset related execution parameters is provided, and the service analysis record that is adjusted to increase the execution evaluation coefficient according to the relevant execution parameters is recorded as an adjustment reference record. The minimum value of the relevant execution parameters of a type of response target in the adjustment reference record that meets the user's requirement for the uniformity of the customer service processing task allocation result is recorded as the preset related execution parameter.

[0033] Specifically, the response setting condition of the execution analysis module response is that the execution evaluation coefficient is greater than the preset execution evaluation coefficient, then the response processing coefficient of a type of response target is determined based on the execution evaluation coefficient and the associated reference execution index; The response setting condition responded by the execution analysis module is that the execution evaluation coefficient is less than or equal to the preset execution evaluation coefficient, and then the response processing coefficient of a type of response target is determined based on the execution evaluation coefficient and the execution stability coefficient.

[0034] Among them, for a single type of response target, if the execution evaluation coefficient of the type of response target is greater than the preset execution evaluation coefficient, the response processing coefficient of the type of response target is determined based on the execution evaluation coefficient and the associated reference execution index, and the response processing coefficient = ln (execution evaluation coefficient × associated reference execution index); if the execution evaluation coefficient of the type of response target is less than or equal to the preset execution evaluation coefficient, the response processing coefficient of the type of response target is determined based on the execution evaluation coefficient and the execution stability coefficient, and the response processing coefficient = ln (execution evaluation coefficient / execution stability coefficient).

[0035] Specifically, the response evaluation condition responded by the response evaluation module is that there are two types of response targets, then the determination reference analysis module performs information reference analysis on the two types of response targets, and the information reference analysis includes: The reference analysis module responds to the reference analysis condition and determines the setting method of the response processing coefficient of the second type of response target based on the information reference index and the information overlap index of the second type of response target; The reference analysis condition is that the response evaluation module determines that the reference analysis module performs information reference analysis on any two types of response targets; The second type of response targets are targets to be responded to whose expression standard index is less than or equal to the preset expression standard index and whose reference processing execution coefficient is less than or equal to the preset reference processing execution coefficient.

[0036] Among them, if there is a target to be responded to whose expression standard index is less than or equal to the preset expression standard index and the reference processing execution coefficient is less than or equal to the preset reference processing execution coefficient, then information reference analysis is performed on the target to be responded to whose expression standard index is less than or equal to the preset expression standard index and the reference processing execution coefficient is less than or equal to the preset reference processing execution coefficient. For a single second-category response target, the information reference index is the number of analysis keywords contained in the initial service information of the second-category response target, and the information overlap index = the number of overlapping keywords of the second-category response target / the information reference index of the second-category response target. For a single analysis keyword, if the overlap index of the analysis keyword is greater than the preset overlap index, the analysis keyword is determined to be an overlapping keyword, and the overlap index is the problem positioning involved by the analysis keyword and other analysis keywords contained in the initial service information of the second-category response target. The value of the preset overlap index can be determined by the user according to the actual work scenario. For example, the user can set it according to the service analysis record. The higher the user's requirement for the uniformity of the customer service processing task allocation result, the larger the value of the preset overlap index. A method for setting the value of the preset overlap index is provided. The average value of the overlap index of each overlapping keyword in the service analysis record that meets the user's requirement for the uniformity of the customer service processing task allocation result is recorded as the preset overlap index. The user can set the analysis keyword according to the actual work scenario. The analysis keyword is a phrase that can be used to determine the problem location of the initial service information. How to set the analysis keyword according to the actual work scenario is easy for technicians in this field to understand. For example, if the target processing category is a smart home system, the analysis keywords include but are not limited to: the power indicator light is not on, cannot connect, the Wi-Fi signal is weak, the response is slow, and cannot be controlled; The values ​​of the preset information reference index and the preset information overlap index can be determined by the user according to the actual work scenario. For example, the user can set them according to the service analysis record. A method for setting the value of the preset information reference index is provided, and the service analysis record for determining the response processing coefficient of the second type of response target based on the target execution coefficient and the information pointing parameter is recorded as the setting reference record. The maximum value of the information reference index in the setting reference record that meets the user's requirements for the uniformity of the customer service processing task allocation results is recorded as the preset information reference index. A method for setting the value of the preset information overlap index is provided, and the maximum value of the information overlap index in the setting reference record that meets the user's requirements for the uniformity of the customer service processing task allocation results is recorded as the preset information overlap index.

[0037] Specifically, if the target reference condition responded by the reference analysis module is that the information reference index is greater than the preset information reference index or the information overlap index is greater than the preset information overlap index, the response processing coefficients of the second type of response targets are determined based on the information pointing parameter and the pointing execution parameter; The target reference condition responded by the reference analysis module is that the information reference index is less than or equal to the preset information reference index and the information overlap index is less than or equal to the preset information overlap index, then the response processing coefficient of the second type of response target is determined based on the target execution coefficient and the information pointing parameter.

[0038] Among them, for a single second-category response target, if the information reference index of the second-category response target is greater than the preset information reference index or the information overlap index is greater than the preset information overlap index, it indicates that the initial service information of the second-category response target contains relatively rich content for inferring the root cause of the fault corresponding to the second-category response target or the information content therein overlaps with the direction of the root cause of the fault, which further indicates that the root cause of the fault of the second-category response target can be determined relatively easily. At this time, the response processing coefficient is determined according to the information pointing parameter and the pointing execution parameter of the second-category response target, and the response processing coefficient = ln (information pointing parameter × pointing execution parameter) execution parameter), the information pointing parameter is the sum of the information reference index and the information overlap index of the two types of response targets, the pointing execution parameter is the execution processing time of the pointing problem positioning of the two types of response targets, for a single pointing problem positioning, the execution processing time is the average processing time of each service process determined as the pointing problem positioning after analysis in the historical service records, the pointing problem positioning is the problem positioning involved in the overlapping keywords of the two types of response targets, if the initial service information of any service process in the historical service record contains any overlapping keywords, then the fault positioning corresponding to the service process is determined to be the pointing problem positioning; For a single Class II response target, if the information reference index of the Class II response target is less than or equal to the preset information reference index and the information overlap index is less than or equal to the preset information overlap index, it indicates that the content contained in the Class II response target is less directed to the root cause of the fault. At this time, the response processing coefficient is determined based on the target execution coefficient and information pointing parameter of the Class II response target. The response processing coefficient = ln (target execution coefficient × information pointing parameter). The target execution coefficient is the sum of the expression standard index of the Class II response target and the reference processing execution coefficient.

[0039] Specifically, the service analysis module periodically responds to the node processing difference coefficient of the target scheduling condition to determine whether to perform task scheduling for the pending response target of the key service node; If the target scheduling condition responded by the service analysis module is that the node processing difference coefficient is greater than the preset node processing difference coefficient, it is determined to perform task scheduling for the scheduling response target of the key service node; The node processing difference coefficient is determined based on the node processing coefficient of each target service node.

[0040] Among them, a cyclic response scheduling cycle is applied in the present invention, and the duration of the response scheduling cycle can be determined by the user. The higher the user's requirements for the uniformity of the customer service processing task allocation result, the shorter the duration of the response scheduling cycle. A response scheduling cycle duration is provided, and the response scheduling cycle is 15 minutes. At the end of each response scheduling cycle, it is determined whether to schedule the scheduling response target of the key service node according to the node processing difference coefficient. If the node processing difference coefficient is greater than the preset node processing difference coefficient, it is determined that the task scheduling is performed for the scheduling response target of the key service node. If the node processing difference coefficient is less than or equal to the preset node processing difference coefficient, it is determined that the task scheduling is not performed for the scheduling response target of the key service node. The node handles the coefficient of variance , m is the number of target service nodes, kt is the cumulative response processing coefficient of the tth target service node, k0 is the average value of the cumulative response processing coefficients of each target service node, for a single target service node, the cumulative response processing coefficient is the sum of the response processing coefficients of each pending response target that the target service node needs to process at the current moment, the value of the preset node processing difference coefficient can be determined by the user according to the actual work scenario, for example, the user can set it according to the service analysis record, the higher the user's requirement for the uniformity of the customer service processing task allocation result, the smaller the value of the preset node processing difference coefficient, and a method for determining the value of the preset node processing difference coefficient is provided, the service analysis record for task scheduling for the pending response target of the target service node is recorded as a scheduling reference record, and the minimum value of the node processing difference coefficient in the scheduling reference record that meets the user's requirement for the uniformity of the customer service processing task allocation result is recorded as the preset node processing difference coefficient.

[0041] Specifically, the service analysis module responds to the scheduling response coefficient of the scheduling setting condition to determine the scheduling response target of each key service node, and the scheduling response coefficient is determined according to the response processing coefficient and the analysis related index; If the dispatch setting condition responded by the service analysis module is that there is a dispatch response coefficient of a pending response target that is greater than a preset dispatch response coefficient, the pending response target is determined to be a dispatch response target; The service analysis module responds to the target scheduling condition and determines the transfer service node of each scheduling response target based on the analysis of the relevant index. The target scheduling condition is that each key service node completes the determination of the scheduling response target.

[0042] Among them, the key service node is a target service node whose cumulative response processing coefficient is greater than the balanced processing coefficient, and the balanced processing coefficient is the average value of the cumulative response processing coefficients of each target service node. For a single key service node, the scheduling response coefficient of each pending response target of the key service node is determined according to the response processing coefficient and the analysis related index. The scheduling setting condition responded by the service analysis module is that there is a pending response target whose scheduling response coefficient is greater than the preset scheduling response coefficient, then the pending response target whose scheduling response coefficient is greater than the preset scheduling response coefficient is determined to be the scheduling response target. For a single pending response target, the scheduling response coefficient = the response processing coefficient of the pending response target / the analysis related index of the pending response target, and the analysis related index is the pending response target. The number of overlapping professional phrases in the initial service information, for any professional phrase contained in the initial service information of the target to be answered, if the number of the target to be answered whose initial service information contains the professional phrase in the key service node is greater than the preset overlapping number, the professional phrase is recorded as an overlapping professional phrase, for a single scheduling answer target, the transfer priority coefficient of each service node to be transferred is determined according to the analysis related index, the service node to be transferred is the target service node whose cumulative answer processing coefficient is less than or equal to the balance processing coefficient, the transfer priority coefficient is positively correlated with the analysis related index, the service node to be transferred with the largest transfer priority coefficient is recorded as the transfer service node of the scheduling answer target, that is, the scheduling answer target is transferred to the transfer service node to complete the customer service; The values ​​of the preset overlap number and the preset scheduling response coefficient can be determined by the user according to the actual work scenario. For example, the user can set them according to the service analysis record. The higher the user's requirement for the uniformity of the customer service processing task allocation result, the larger the value of the preset overlap number and the smaller the value of the preset scheduling response coefficient. A value of the preset overlap number is provided, and the value of the preset overlap number is 50% of the number of targets to be responded to in the target service node. A method for determining the value of the preset scheduling response coefficient is provided, and the average value of the scheduling response coefficient of the scheduling response target in the service analysis record that meets the user's requirement for the uniformity of the customer service processing task allocation result is recorded as the preset scheduling response coefficient.

[0043] See also Figure 4 As shown, it is a schematic diagram of an intelligent customer service method based on intent recognition of the present invention. The present invention also provides an intelligent customer service method based on intent recognition, including: The response analysis strategy for the target to be responded to is determined based on the expression standard index and the reference processing execution coefficient, which is to perform target execution analysis or information reference analysis on the target to be responded to; Under the target execution analysis, an execution analysis method of a type of response target is determined according to the processing execution difference index and the response quality difference index. The execution analysis method is to determine an execution evaluation coefficient of a type of response target based on the information association index and the association reference execution index, or the information association index and the analysis interference index. Under the condition of completion of the execution evaluation, the setting method of determining the response processing coefficient of a type of response target based on the execution evaluation coefficient is to determine the response processing coefficient of a type of response target based on the execution evaluation coefficient and the associated reference execution index, or, the execution evaluation coefficient and the execution stability coefficient; Under the information reference analysis, the setting method of determining the response processing coefficient of the second type of response target according to the information reference index and the information overlap index is to determine the response processing coefficient of the second type of response target based on the information pointing parameter and the pointing execution parameter, or the target execution coefficient and the information pointing parameter; Periodically determine whether to schedule tasks for the pending response targets of the target service node based on the node processing difference coefficient, determine the scheduling response targets of each key service node based on the scheduling response coefficient, and determine the transfer service node of each scheduling response target based on the analysis of the relevant index.

[0044] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0045] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An intelligent customer service system based on intent recognition, characterized in that: include: A response evaluation module, which is used to respond to the response evaluation conditions to determine the response analysis strategy corresponding to each target to be responded to as the target execution analysis or information reference analysis; an execution analysis module connected to the response evaluation module, for determining an execution analysis method based on a processing execution difference index and a response quality difference index to obtain an execution evaluation coefficient, and for responding to a response setting condition to determine a setting method of the response processing coefficient to determine the execution evaluation coefficient based on an information association index and an associated reference execution index, or to determine the execution evaluation coefficient based on an information association index and an analysis interference index; A reference analysis module connected to the response evaluation module for responding to the target reference condition to determine the response processing coefficients of the second type of response targets in a setting manner based on the information pointing parameter and the pointing execution parameter, or the target execution coefficient and the information pointing parameter to determine the response processing coefficients of the second type of response targets; The service processing module is respectively connected to the execution analysis module and the reference analysis module, and is used to periodically determine whether to schedule the target to be responded to based on the node processing coefficient of each target service node.

2. The intelligent customer service system based on intention recognition according to claim 1 is characterized in that: The response evaluation condition responded by the response evaluation module is that there is a type of response target, then the determination execution analysis module performs target execution analysis on the type of response target, and the target execution analysis includes: The execution analysis module determines the execution analysis mode based on the processing execution difference index and the response quality difference index of a type of response target in response to the execution analysis condition; The execution analysis module determines, in response to the execution evaluation completion condition, a setting method of a response processing coefficient for a class of response targets based on the execution evaluation coefficient; The execution analysis condition is that the response evaluation module determines that the execution analysis module performs target execution analysis on any type of response target, and the execution evaluation completion condition is that the execution evaluation coefficient of a type of response target is completed and determined; The first type of response target is a target to be responded to whose expression standard index is greater than a preset expression standard index or whose reference processing execution coefficient is greater than a preset reference processing execution coefficient.

3. The intelligent customer service system based on intention recognition according to claim 2 is characterized in that: If the analysis setting condition of the execution analysis module response is that the execution stability coefficient is greater than the preset execution stability coefficient, it is determined that an execution evaluation coefficient of a type of response target is determined based on the information association index and the associated reference execution index; The execution evaluation coefficient is positively correlated with the information association index and the association reference execution index respectively, and the execution stability coefficient is determined according to the processing execution difference index of a class of response targets and the response quality difference index.

4. The intelligent customer service system based on intention recognition according to claim 3 is characterized in that: If the analysis setting condition of the execution analysis module response is that the execution stability coefficient is less than or equal to the preset execution stability coefficient, it is determined that the execution evaluation coefficient of a type of response target is determined based on the information association index and the analysis interference index, and whether to adjust the execution evaluation coefficient based on the relevant execution parameters; The evaluation adjustment condition responded by the execution analysis module is that the relevant execution parameter is greater than the preset relevant execution parameter, then it is determined to increase the execution evaluation coefficient according to the relevant execution parameter.

5. The intelligent customer service system based on intention recognition according to claim 4 is characterized in that: If the response setting condition responded by the execution analysis module is that the execution evaluation coefficient is greater than the preset execution evaluation coefficient, it is determined that the response processing coefficient of a type of response target is determined based on the execution evaluation coefficient and the associated reference execution index; The response setting condition responded by the execution analysis module is that the execution evaluation coefficient is less than or equal to the preset execution evaluation coefficient, and then the response processing coefficient of a type of response target is determined based on the execution evaluation coefficient and the execution stability coefficient.

6. The intelligent customer service system based on intention recognition according to claim 5 is characterized in that: The response evaluation condition responded by the response evaluation module is that there are two types of response targets, then the reference analysis module is determined to perform information reference analysis on the two types of response targets, and the information reference analysis includes: The reference analysis module responds to the reference analysis condition and determines the setting method of the response processing coefficient of the second type of response target based on the information reference index and the information overlap index of the second type of response target; The reference analysis condition is that the response evaluation module determines that the reference analysis module performs information reference analysis on any two types of response targets; The second type of response targets are targets to be responded to whose expression standard index is less than or equal to the preset expression standard index and whose reference processing execution coefficient is less than or equal to the preset reference processing execution coefficient.

7. The intelligent customer service system based on intention recognition according to claim 6 is characterized in that: If the target reference condition responded by the reference analysis module is that the information reference index is greater than the preset information reference index or the information overlap index is greater than the preset information overlap index, the response processing coefficient of the second type of response target is determined based on the information pointing parameter and the pointing execution parameter; The target reference condition responded by the reference analysis module is that the information reference index is less than or equal to the preset information reference index and the information overlap index is less than or equal to the preset information overlap index, then the response processing coefficient of the second type of response target is determined based on the target execution coefficient and the information pointing parameter.

8. The intelligent customer service system based on intention recognition according to claim 7 is characterized in that: The service analysis module periodically responds to the node processing difference coefficient of the target scheduling condition to determine whether to perform task scheduling for the pending response target of the key service node; If the target scheduling condition responded by the service analysis module is that the node processing difference coefficient is greater than the preset node processing difference coefficient, it is determined to perform task scheduling for the scheduling response target of the key service node; The node processing difference coefficient is determined based on the node processing coefficient of each target service node.

9. The intelligent customer service system based on intention recognition according to claim 8, characterized in that: The service analysis module responds to the scheduling response coefficient of the scheduling setting condition to determine the scheduling response target of each key service node, wherein the scheduling response coefficient is determined according to the response processing coefficient and the analysis related index; If the dispatch setting condition responded by the service analysis module is that there is a dispatch response coefficient of a pending response target that is greater than a preset dispatch response coefficient, the pending response target is determined to be a dispatch response target; The service analysis module responds to the target scheduling condition and determines the transfer service node of each scheduling response target based on the analysis of the relevant index. The target scheduling condition is that each key service node completes the determination of the scheduling response target.

10. An intelligent customer service method applied to the intelligent customer service system based on intention recognition as claimed in any one of claims 1 to 9, characterized in that: include: The response analysis strategy for the target to be responded to is determined based on the expression standard index and the reference processing execution coefficient, which is to perform target execution analysis or information reference analysis on the target to be responded to; Under the target execution analysis, an execution analysis method of a type of response target is determined according to the processing execution difference index and the response quality difference index. The execution analysis method is to determine an execution evaluation coefficient of a type of response target based on the information association index and the association reference execution index, or the information association index and the analysis interference index. Under the condition of completion of the execution evaluation, the setting method of determining the response processing coefficient of a type of response target based on the execution evaluation coefficient is to determine the response processing coefficient of a type of response target based on the execution evaluation coefficient and the associated reference execution index, or, the execution evaluation coefficient and the execution stability coefficient; Under the information reference analysis, the setting method of determining the response processing coefficient of the second type of response target according to the information reference index and the information overlap index is to determine the response processing coefficient of the second type of response target based on the information pointing parameter and the pointing execution parameter, or the target execution coefficient and the information pointing parameter; Periodically determine whether to schedule tasks for the pending response targets of the target service node based on the node processing difference coefficient, determine the scheduling response targets of each key service node based on the scheduling response coefficient, and determine the transfer service node of each scheduling response target based on the analysis of the relevant index.

Images