CN112288446A - Method and device for calculating complaint and claim - Google Patents
Method and device for calculating complaint and claim Download PDFInfo
- Publication number
- CN112288446A CN112288446A CN202011172616.9A CN202011172616A CN112288446A CN 112288446 A CN112288446 A CN 112288446A CN 202011172616 A CN202011172616 A CN 202011172616A CN 112288446 A CN112288446 A CN 112288446A
- Authority
- CN
- China
- Prior art keywords
- complaint
- text
- type
- historical
- amount
- 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
- 238000000034 method Methods 0.000 title claims abstract description 65
- 238000012545 processing Methods 0.000 claims abstract description 36
- 238000007781 pre-processing Methods 0.000 claims abstract description 13
- 238000004364 calculation method Methods 0.000 claims description 31
- 230000008451 emotion Effects 0.000 claims description 23
- 230000011218 segmentation Effects 0.000 claims description 7
- 238000012217 deletion Methods 0.000 claims description 5
- 230000037430 deletion Effects 0.000 claims description 5
- 238000004891 communication Methods 0.000 abstract description 7
- 230000008569 process Effects 0.000 description 11
- 230000006870 function Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 238000004590 computer program Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 238000002372 labelling Methods 0.000 description 3
- 230000003993 interaction Effects 0.000 description 2
- 238000011002 quantification Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 206010049976 Impatience Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/284—Lexical analysis, e.g. tokenisation or collocates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G06Q50/60—
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The application provides a method and a device for calculating complaint claim, relates to the technical field of communication, and solves the problem of low complaint processing efficiency. The method comprises the following steps: obtaining a complaint text, and processing the complaint text by using a preset rule to obtain a target dispute amount; preprocessing the complaint text to obtain a word set of the complaint text, and inputting the word set of the complaint text into a first preset model to obtain a target corresponding relation; determining a target text type according to the target corresponding relation; and inputting the target text type and the target dispute amount into a second preset model to obtain the claim amount of the complaint text. Embodiments of the present application are applied to determine a result of a benefit of a complaint.
Description
Technical Field
The embodiment of the application relates to the technical field of communication, in particular to a method and a device for calculating complaint and claim.
Background
With the development of service diversity of telecommunication operators, users may encounter problems of unexpected charges, poor service quality, etc. in the process of enjoying services, thereby causing complaints. At this time, the telecom operator needs to determine a complaint handling scheme, even the procedure of reimbursement.
At present, when a user complaint is met and a refund is required, the user complaint is generally paid in a manually specified mode, and when the payment amount is calculated, the user complaint is usually determined according to personal experience or manual historical processing conditions. As a result, the processing efficiency is low when the traffic is relatively large.
Disclosure of Invention
The application provides a method and a device for calculating complaint claim, which solve the problem of low complaint processing efficiency.
In a first aspect, the present application provides a method for calculating a complaint, which is applied to a device for calculating a complaint, and includes: the calculation device of the complaint claim obtains the complaint text and processes the complaint text by using the preset rule to obtain the target dispute amount. And then, preprocessing the complaint text to obtain a word set of the complaint text, and inputting the word set of the complaint text into a first preset model to obtain a target corresponding relation. Then, the calculation device of the complaint claim determines the target text type according to the target correspondence. And finally, inputting the target text type and the target dispute amount into a second preset model to obtain the claim amount of the complaint text.
The target corresponding relation comprises a corresponding relation between words in a word set of the complaint text and the text type; the target text type is the text type with the highest Bayesian probability in the target corresponding relation.
In the above scheme, the calculation device for the complaint claims can obtain the target dispute amount according to the complaint text, determine the target text type of the complaint text by using the first preset model, and obtain the claim amount of the complaint text by using the second preset model. The method avoids the manual mode of determining the payment amount according to personal experience or manual inquiry of historical processing conditions. Thus, even if the traffic is relatively large, the calculation result of the paid amount can be obtained in time, and the efficiency of complaint processing is improved.
In a second aspect, the present application provides a complaint payment computing device comprising: the device comprises an acquisition module and a processing module. And the obtaining module is used for obtaining the complaint text and processing the complaint text by using a preset rule to obtain the target dispute amount. And the processing module is used for preprocessing the complaint text to obtain a word set of the complaint text, and inputting the word set of the complaint text into the first preset model to obtain the target corresponding relation. And the determining module is used for determining the type of the target text according to the target corresponding relation. And the processing module is also used for inputting the target text type and the target dispute amount into a second preset model to obtain the reimbursement amount of the complaint text.
The target corresponding relation comprises a corresponding relation between words in a word set of the complaint text and the text type; the target text type is the text type with the highest Bayesian probability in the target corresponding relation.
In a third aspect, the present application provides a computing device for complaint, comprising a processor, wherein when the computing device for complaint is operated, the processor executes computer-executable instructions to cause the computing device for complaint to perform the method for computing complaint as described above.
In a fourth aspect, the present application provides a computer-readable storage medium comprising instructions which, when executed on a computer, cause the computer to perform the method of calculating a complaint payment as described above.
In a fifth aspect, the present application provides a computer program product comprising instruction code for performing the method of calculating a complaint payment as described above.
It is understood that any one of the above-mentioned computing devices, computer-readable storage media or computer program products for complaint payment is provided to execute the above-mentioned methods, and therefore, the beneficial effects achieved by the above-mentioned methods and the corresponding solutions in the following embodiments can be referred to, and are not repeated herein.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a hardware structure diagram of a computing device for complaint payment according to an embodiment of the present application;
fig. 2 is a schematic flowchart of a method for calculating a complaint claim according to an embodiment of the present disclosure;
fig. 3 is a schematic flowchart of a method for establishing a first preset model according to an embodiment of the present application;
fig. 4 is a schematic flowchart of a method for establishing a second preset model according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of a computing device for complaint payment according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
In the embodiments of the present application, words such as "exemplary" or "for example" are used to mean serving as an example, instance, or illustration. Any embodiment or design described herein as "exemplary" or "e.g.," is not necessarily to be construed as preferred or advantageous over other embodiments or designs. Rather, use of the word "exemplary" or "such as" is intended to present concepts related in a concrete fashion.
In the following, the terms "first", "second" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the embodiments of the present application, "a plurality" means two or more unless otherwise specified.
The method for calculating the complaint and the claim is applied to the scene of complaint of the user. Specifically, as the diversity of services of telecommunication operators develops, users may encounter problems of unexpected charges, poor quality of service, etc. during the process of enjoying the services, thereby causing complaints. At this time, the telecom operator needs to determine a complaint handling scheme, even the procedure of reimbursement. At present, when a user complaint is met and a refund claim is required, the user complaint is generally paid in a manually specified mode, and when calculating the claim amount, the user complaint is usually determined according to personal experience or manual historical processing conditions. As a result, the processing efficiency is low when the traffic is relatively large.
In view of the above problems, the present application provides a method and an apparatus for calculating a complaint payment, where the method for calculating a complaint payment specifically includes: firstly, a complaint text of a user is obtained, and the complaint text is processed by using a preset rule to obtain a target dispute amount. And then, preprocessing the complaint text to obtain a word set of the complaint text, and inputting the word set of the complaint text into a first preset model to obtain a target corresponding relation. And then, determining the type of the target text according to the target corresponding relation. And finally, inputting the type of the target text and the target dispute amount into a second preset model to obtain the claim amount of the complaint text, and directly obtaining the claim amount according to the complaint text of the user, so that the complaint processing efficiency is improved.
In a specific implementation, a computing device for complaint payment has components as shown in FIG. 1. Fig. 1 is a computing apparatus for complaint payment provided by an embodiment of the present application, and the computing apparatus may include at least one processor 102, where the processor 102 is configured to execute application program code, so as to implement a method for computing a complaint payment in the present application.
The processor 102 may be a Central Processing Unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more ics for controlling the execution of programs in accordance with the present disclosure.
As shown in fig. 1, the computing device of the complaint payment may also include a memory 103. The memory 103 is used for storing application program codes for executing the scheme of the application, and the processor 102 controls the execution.
The memory 103 may be, but is not limited to, a read-only memory (ROM) or other type of static storage device that may store static information and instructions, a Random Access Memory (RAM) or other type of dynamic storage device that may store information and instructions, an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disk storage, optical disk storage (including compact disc, laser disc, optical disc, digital versatile disc, blu-ray disc, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer. The memory 103 may be separate and coupled to the processor 102 via the bus 104. Memory 103 may also be integrated with processor 102.
As shown in fig. 1, the computing device of the complaint payment may further include a communication interface 101, wherein the communication interface 101, the processor 102, and the memory 103 may be coupled to each other, for example, via a bus 104. The communication interface 101 is used for information interaction with other devices, for example, information interaction of a computing device supporting complaint payment with other devices.
It is noted that the equipment configuration shown in fig. 1 does not constitute a limitation of the computing device of the complaint, which may include more or less components than those shown in fig. 1, or some components in combination, or a different arrangement of components, in addition to the components shown in fig. 1.
The method for calculating the complaint provided by the embodiment of the present application is described below with reference to fig. 2 to 4 in conjunction with the apparatus for calculating the complaint shown in fig. 1.
Fig. 2 is a schematic flowchart of a method for calculating a complaint claim according to an embodiment of the present disclosure. Referring to fig. 2, the method for calculating the complaint payment includes the following steps.
201. The calculation device of the complaint claim obtains the complaint text, and processes the complaint text by using the preset rule to obtain the target dispute amount.
Specifically, the manner of obtaining the complaint text may be to obtain and identify audio information to obtain the complaint text. Wherein the audio information comprises voice information of the complaint of the user. For example, when a user calls a complaint telephone to complain, audio information of the complaint telephone is acquired, and the audio information is identified by using a relevant voice recognition model to obtain a complaint text.
The method for obtaining the complaint text can also be directly obtaining the complaint document fed back by the user to obtain the complaint text. For example, a user logs in a related website, writes a complaint document for complaint, and directly obtains the complaint document written by the user to obtain a complaint text.
After obtaining the complaint text, the computing device of the complaint payment processes the complaint text using preset rules to obtain a target dispute amount. The preset rule is a regular expression.
Specifically, terms related to the amount in the complaint text are extracted through the regular expression, such as "deduct more XX elements", "accept more XX blocks", "XX elements are not lost", and the like. And then extracting the number in the dialect related to the amount to obtain the target dispute amount. And when the words related to the amount are not extracted through the regular expression in the complaint text, determining that the target dispute amount is 0.
202. The calculation device of the complaint claim preprocesses the complaint text to obtain a word set of the complaint text.
Specifically, the pretreatment comprises at least one of the following operations: word segmentation operation and stop word deletion operation. For example, a computing device for complaint claims uses a word segmentation tool to segment a complaint text and delete stop words, resulting in a set of words for the complaint text.
203. The calculation device of the complaint claim inputs the word set of the complaint text into the first preset model to obtain the target corresponding relation.
The target corresponding relation comprises a corresponding relation between words in a word set of the complaint text and the text type.
Optionally, before the complaint text is input into the first preset model, the first preset model needs to be established, and specifically, fig. 3 provides a schematic flow diagram of an establishing method of the first preset model. Referring to fig. 3, the method for establishing the first predetermined model includes the following steps 301 to 302.
301. A computing device of a complaint claim obtains a set of words corresponding to each text type.
First, a computing device of a complaint payment obtains at least one historical complaint text. Wherein the at least one historical complaint text includes a text type. One historical complaint text corresponds to one text type.
Specifically, the related management personnel label the text type of each historical complaint text in at least one historical complaint text, one historical complaint text corresponds to one text type, and the calculation device for complaint claims acquires the at least one historical complaint text comprising the text type.
Then, the calculation device for complaint claims executes a first operation on each historical complaint text to obtain a word set corresponding to each text type.
Specifically, the first operation is: the calculation device for complaint claims firstly preprocesses the first historical complaint text to obtain a word set of the first historical complaint text. The first historical complaint text is any one of the at least one historical complaint text.
More specifically, the pretreatment comprises at least one of the following operations: word segmentation operation and stop word deletion operation. For example, a computing device of a complaint claim uses a word segmentation tool to segment a first historical complaint text and delete stop words.
Then, the calculation device for complaint claims determines a word set corresponding to the text type of the first historical complaint text according to the number of the first words in the word set of the first historical complaint text, the number of the acquired historical complaint texts, and the number of the acquired historical complaint texts containing the first words. The first word is any word in the word set of the first historical complaint text.
Further specifically, first, according to the number of the first words and the number of words in the word set of the first historical complaint text, the probability that the first words occupy the text type corresponding to the first historical complaint text is calculated.
The probability that the first words occupy the text type corresponding to the first historical complaint text meets a formula:
TFwthe probability that the first word occupies the text type corresponding to the first historical complaint text is represented, w represents the number of the first word, and c represents the number of words in the word set of the first historical complaint text.
And then, calculating the reverse file frequency according to the number of the obtained historical complaint texts and the number of the obtained historical complaint texts containing the first words.
Wherein, the reverse file frequency satisfies the formula:
IDFwthe reverse file frequency is represented, m represents the number of the obtained historical complaint texts, and n represents the number of the obtained historical complaint texts containing the first words.
And then, calculating the probability of the first word according to the probability that the first word occupies the text type corresponding to the first historical complaint text and the reverse file frequency.
Wherein the probability of the first term satisfies the formula: pw＝TFw×IDFw，PwRepresenting the probability of the first word, TFwMeans the probability that the first word occupies the text type corresponding to the first historical complaint text, IDFwRepresenting the inverse file frequency.
And finally, determining a first word set with the highest probability under the first historical complaint text as a word set corresponding to the text type of the first historical complaint text.
302. The calculation device for complaint claims establishes a first preset model according to each text type, the word set corresponding to each text type and the words in each word set.
Specifically, the calculation device for complaint and claim payment generates the corresponding relationship among the text type, the word set corresponding to the text type and the words in the word set according to each text type, the word set corresponding to each text type and the words in each word set, and stores the corresponding relationship to obtain the first preset model.
In this way, when the computing device of the complaint claim inputs the word set of the complaint text into the first preset model, the first preset model outputs the target correspondence between the words in the word set of the complaint text and the text type according to the correspondence.
204. And the calculation device for the complaint claim determines the target text type according to the target corresponding relation.
And the target text type is the text type with the highest Bayesian probability in the target corresponding relation.
Specifically, a second operation is executed on each text type in the target corresponding relation to obtain the Bayesian probability of each text type in the target corresponding relation; and then, determining the text type with the highest Bayesian probability in the target corresponding relation as the target text type.
More specifically, the second operation includes: and calculating the probability of the first text type according to the number of the words corresponding to the first text type and the number of the words in the word set of the complaint text.
The first text type is any text type in the target corresponding relation. The probability of the first text type satisfies the formula:
probability, N, of representing a first text typecRepresenting the number of words, N, corresponding to the first text typedocThe number of words in the set of words representing the complaint text.
And calculating the probability of the second word according to the number of the second word in the first text type and the number of the word corresponding to the first text type.
And the second word is any word in the word set of the complaint text. The probability of the second term satisfies the formula:
denotes the probability, count (w), of the second wordiAnd c) represents the number of second words in the first text type, count (w)jAnd c) represents the number of words corresponding to the first text type.
A Bayesian probability of the first text type is calculated based on the probability of the first text type and the probability of the second word.
Wherein the Bayesian probability of the first text type satisfies a formula:
a bayesian probability representing a first text type,
a probability of representing the first text type is indicated,
representing the probability of the second word.
And finally, after the Bayesian probability of each text type in the target corresponding relation is obtained, the text type with the highest Bayesian probability is determined as the target text type.
205. And the calculation device of the complaint claim inputs the target text type and the target dispute amount into the second preset model to obtain the claim amount of the complaint text.
Optionally, before inputting the target text type and the target dispute amount into the second preset model, the second preset model needs to be established, and specifically, fig. 4 provides a flowchart of a method for establishing the second preset model. Referring to fig. 4, the method for establishing the second predetermined model includes the following steps 401 to 402.
401. And obtaining the text type, the historical dispute amount and the historical reimbursement amount of each historical complaint text in at least one historical complaint text.
Specifically, the related management personnel carries out text type labeling, historical dispute amount labeling and historical benefits amount labeling on each historical complaint text in at least one historical complaint text. Wherein, one text type, one historical dispute amount and one historical compensation amount correspond to one historical complaint text. Thereafter, the computing device of the complaint claim obtains at least one historical complaint text, a text type, a historical dispute amount, and a historical payout amount for each historical complaint text.
402. And establishing a second preset model according to the text type, the historical dispute amount and the historical claims amount of each historical complaint text.
Wherein the text type includes an emotion type and a complaint type.
Specifically, the calculation device for complaint claims performs curve fitting on the emotion type, the complaint type and the historical dispute amount of at least one historical complaint text by using a least square method to obtain a least square fitting curve equation. And then calculating to obtain a function value of the least square fitting curve equation. Then, the calculation means of the complaint claims calculates the sum of squares of the difference values between the value of each of the historical claims and the function value, and obtains the weight of the corresponding emotion type, the weight of the complaint type, the weight of the dispute amount, and the compensation parameter when the sum of squares is minimum. And finally, establishing a second preset model according to the weight of the emotion type, the weight of the complaint type, the weight of the dispute amount and the compensation parameter.
More specifically, the second predetermined model satisfies the formula y ═ w1×x1+w2×x2+w3×x3+ b. Wherein y represents a reimbursement amount for a complaint, and x1Type of emotion, x, indicating a complaint2Type of complaint, x, indicating a complaint3Indicating a dispute amount, w, of a complaint1Weight, w, representing the type of emotion2Weight, w, indicating the type of complaint3Representing the weight of the amount of the dispute, b representing a compensation parameter, b > 0.
For the quantification of the complaint type and emotion type, a commonly used quantification method may be used. For example, the relevant manager makes relevant settings for the emotion classification, calmness is 1, anger is 2, impatience is 3, anger is 4, and rage is 5. For another example, the relevant manager ranks the complaints from low severity to high severity, and the signal is poor at 1, the network is disconnected at 2, the abnormal shutdown is 3, and the multi-deduction fee is 4.
Thus, when the calculation means of the complaint payment inputs the target text type and the target dispute amount into the second preset model, the second preset model substitutes the emotion type, the complaint type and the target dispute amount in the target text type into the above formula, and outputs the calculated result as the payment amount.
Optionally, after the computing device of the complaint claim outputs the claim amount, the relevant manager soothes and pays the customer service based on the claim amount, so as to solve the complaint problem.
In the above scheme, the calculation device for the complaint claims can obtain the target dispute amount according to the complaint text, determine the target text type of the complaint text by using the first preset model, and obtain the claim amount of the complaint text by using the second preset model. The method avoids the manual mode of determining the payment amount according to personal experience or manual inquiry of historical processing conditions. Thus, even if the traffic is relatively large, the calculation result of the paid amount can be obtained in time, and the efficiency of complaint processing is improved.
In the embodiment of the present application, functional modules of the computing device for complaint payment may be divided according to the above method embodiment, for example, each functional module may be divided according to each function, or two or more functions may be integrated into one processing module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. It should be noted that, in the embodiment of the present application, the division of the module is schematic, and is only one logic function division, and there may be another division manner in actual implementation.
The method provided by the embodiment of the present application is described in detail above with reference to fig. 2 to 4. Hereinafter, a computing apparatus for complaint payment provided in the embodiment of the present application will be described in detail with reference to fig. 5. It should be understood that the description of the apparatus embodiments corresponds to the description of the method embodiments, and therefore, for brevity, details are not repeated here, since the details that are not described in detail may be referred to the above method embodiments.
Fig. 5 shows a schematic structural diagram of a computing device for complaint payment. The computing device of the complaint payment includes an acquisition module 51, a processing module 52, and a determination module 53.
The obtaining module 51 is configured to obtain the complaint text, and process the complaint text by using a preset rule to obtain the target dispute amount. For example, referring to fig. 2, the obtaining module 51 is configured to execute step 201. A processing module 52 configured to: and preprocessing the complaint text to obtain a word set of the complaint text. And inputting the word set of the complaint text into a first preset model to obtain a target corresponding relation. The target corresponding relation comprises a corresponding relation between words in a word set of the complaint text and the text type. For example, referring to FIG. 2, processing module 52 is configured to perform step 202 and step 203. And the determining module 53 is configured to determine the target text type according to the target correspondence. The target text type is the text type with the highest Bayesian probability in the target corresponding relation. For example, referring to FIG. 2, the determination module 53 is configured to perform step 204. The processing module 52 is further configured to: and inputting the target text type and the target dispute amount into a second preset model to obtain the claim amount of the complaint text. For example, referring to FIG. 2, the processing module 52 is further configured to perform step 204.
Optionally, the obtaining module 51 is specifically configured to: and acquiring and identifying the audio information to obtain a complaint text, or acquiring a complaint document of a user to obtain the complaint text. Wherein the audio information comprises voice information of the complaint of the user.
Optionally, the obtaining module 51 is further configured to obtain a word set corresponding to each text type. For example, referring to fig. 3, the obtaining module 51 is further configured to execute step 301. The processing module 52 is further configured to establish a first preset model according to each text type, the word set corresponding to each text type, and the words in each word set. For example, referring to FIG. 3, the processing module 52 is further configured to perform step 302.
Optionally, the obtaining module 51 is specifically configured to: at least one historical complaint text is obtained. Wherein the at least one historical complaint text includes a text type. One historical complaint text corresponds to one text type. And executing a first operation on each historical complaint text to obtain a word set corresponding to each text type. The first operation is: and preprocessing the first historical complaint text to obtain a word set of the first historical complaint text. Determining a word set corresponding to the text type of the first historical complaint text according to the number of the first words in the word set of the first historical complaint text, the number of the obtained historical complaint texts, and the number of the obtained historical complaint texts containing the first words. The first historical complaint text is any one of the at least one historical complaint text. The first word is any word in a set of words of the first historical complaint text.
Optionally, the pre-processing comprises at least one of: word segmentation operation and stop word deletion operation.
Optionally, the obtaining module 51 is further configured to obtain a text type, a historical dispute amount, and a historical reimbursement amount of each historical complaint text in at least one historical complaint text. For example, referring to fig. 4, the obtaining module 51 is further configured to execute step 401. The processing module 52 is further configured to establish a second preset model according to the text type, the historical dispute amount, and the historical reimbursement amount of each historical complaint text. For example, referring to FIG. 4, the processing module 52 is further configured to perform step 402.
Optionally, the text type includes an emotion type and a complaint type, and the processing module 52 is specifically configured to: and performing curve fitting on the emotion type, the complaint type and the historical dispute amount of the at least one historical complaint text by using a least square method to obtain a least square method fitting curve equation. And calculating to obtain a function value of the least square method fitting curve equation. And calculating the sum of squares of the difference value of each historical reimbursement amount and the function value, and acquiring the weight of the corresponding emotion type, the weight of the complaint type, the weight of the dispute amount and the compensation parameter when the sum of squares is minimum. And establishing a second preset model according to the weight of the emotion type, the weight of the complaint type, the weight of the dispute amount and the compensation parameter.
Optionally, the second predetermined model satisfies the formula y ═ w1×x1+w2×x2+w3×x3+ b. Wherein y represents a reimbursement amount for a complaint, and x1Type of emotion, x, indicating a complaint2Type of complaint, x, indicating a complaint3Indicating a dispute amount, w, of a complaint1Weight, w, representing the type of emotion2Weight, w, indicating the type of complaint3Representing the weight of the amount of the dispute, b representing a compensation parameter, b > 0.
Optionally, the preset rule is a regular expression matching rule.
Another embodiment of the present application further provides a computer-readable storage medium, which stores instructions that, when executed on a computing device of a complaint, perform the steps in the computing method of a complaint according to the embodiment shown in fig. 2-4.
In another embodiment of the present application, there is also provided a computer program product comprising computer executable instructions stored in a computer readable storage medium; the processor of the computing device of the complaint payment can read the computer-executable instructions from the computer-readable storage medium, and execution of the computer-executable instructions by the processor causes the computing device of the complaint payment to perform the steps in the method of computing the complaint payment of the embodiment as shown in fig. 2-4.
All relevant contents of each step related to the above method embodiment may be referred to the functional description of the corresponding functional module, and the function thereof is not described herein again.
It should be understood that, in the various embodiments of the present application, the sequence numbers of the above-mentioned processes do not mean the execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.
Those of ordinary skill in the art would appreciate that the various illustrative modules, elements, and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus, and method may be implemented in other ways. For example, the device embodiments described above are merely illustrative, e.g., multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
Units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (20)
1. A method of calculating a complaint payment, comprising:
obtaining a complaint text, and processing the complaint text by using a preset rule to obtain a target dispute amount;
preprocessing the complaint text to obtain a word set of the complaint text;
inputting the word set of the complaint text into a first preset model to obtain a target corresponding relation; the target corresponding relation comprises a corresponding relation between words in a word set of the complaint text and text types;
determining a target text type according to the target corresponding relation; the target text type is the text type with the highest Bayesian probability in the target corresponding relation;
and inputting the target text type and the target dispute amount into a second preset model to obtain the payment amount of the complaint text.
2. The computing method of claim 1, wherein obtaining the complaint text comprises:
acquiring and identifying audio information to obtain the complaint text; the audio information comprises voice information of the complaints of the user;
alternatively, the first and second electrodes may be,
and obtaining a complaint document of the user to obtain the complaint text.
3. The computing method of claim 1, wherein prior to entering the set of words of the complaint text into a first preset model, the computing method further comprises:
acquiring a word set corresponding to each text type;
and establishing the first preset model according to each text type, the word set corresponding to each text type and the words in each word set.
4. The computing method of claim 3, wherein the obtaining a set of words corresponding to each text type comprises:
obtaining at least one historical complaint text; wherein the at least one historical complaint text comprises a text type; one historical complaint text corresponds to one text type;
executing a first operation on each historical complaint text to obtain a word set corresponding to each text type;
the first operation is: preprocessing a first historical complaint text to obtain a word set of the first historical complaint text; determining a word set corresponding to the text type of the first historical complaint text according to the number of first words in the word set of the first historical complaint text, the number of acquired historical complaint texts, and the number of acquired historical complaint texts containing the first words; wherein the first historical complaint text is any one of the at least one historical complaint text; the first word is any word in the set of words of the first historical complaint text.
5. The calculation method according to claim 1 or 4,
the pre-processing comprises at least one of the following operations: word segmentation operation and stop word deletion operation.
6. The computing method of claim 1, wherein prior to entering the target text type and the target dispute amount into a second pre-set model, the computing method further comprises:
acquiring the text type, the historical dispute amount and the historical reimbursement amount of each historical complaint text in at least one historical complaint text;
and establishing a second preset model according to the text type of each historical complaint text, the historical dispute amount and the historical claims amount.
7. The computing method of claim 6, wherein the text types include an emotion type and a complaint type, and wherein the establishing a second preset model according to the text type, the historical dispute amount, and the historical payout amount of each historical complaint text comprises:
performing curve fitting on the emotion type, the complaint type and the historical dispute amount of the at least one historical complaint text by using a least square method to obtain a least square method fitting curve equation; calculating to obtain a function value of the least square method fitting curve equation;
calculating the sum of squares of the difference value between each historical reimbursement amount and the function value, and acquiring the weight of the corresponding emotion type, the weight of the complaint type, the weight of the dispute amount and the compensation parameter when the sum of squares is minimum;
and establishing a second preset model according to the weight of the emotion type, the weight of the complaint type, the weight of the dispute amount and the compensation parameter.
8. The calculation method according to claim 7, wherein the second predetermined model satisfies the formula y-w1×x1+w2×x2+w3×x3+ b; wherein y represents a reimbursement amount for a complaint, and x1Type of emotion, x, representing said one complaint2A complaint type, x, representing said one complaint3A dispute amount, w, representing said one complaint1Weight, w, representing the type of emotion2A weight, w, representing the type of complaint3A weight representing the amount of said dispute, b representing said compensation parameter, b > 0.
9. The computing method according to claim 1,
the preset rule is a regular expression matching rule.
10. A computing device for complaint payment, comprising:
the obtaining module is used for obtaining the complaint text and processing the complaint text by using a preset rule to obtain a target dispute amount;
a processing module to:
preprocessing the complaint text to obtain a word set of the complaint text;
inputting the word set of the complaint text into a first preset model to obtain a target corresponding relation; the target corresponding relation comprises a corresponding relation between words in a word set of the complaint text and text types;
the determining module is used for determining the type of the target text according to the target corresponding relation; the target text type is the text type with the highest Bayesian probability in the target corresponding relation;
the processing module is further configured to: and inputting the target text type and the target dispute amount into a second preset model to obtain the payment amount of the complaint text.
11. The computing device of claim 10, wherein the obtaining module is specifically configured to:
acquiring and identifying audio information to obtain the complaint text; the audio information comprises voice information of the complaints of the user;
alternatively, the first and second electrodes may be,
and obtaining a complaint document of the user to obtain the complaint text.
12. The computing device of claim 10,
the acquisition module is further used for acquiring a word set corresponding to each text type;
the processing module is further configured to establish the first preset model according to each text type, the word set corresponding to each text type, and the words in each word set.
13. The computing device of claim 12, wherein the obtaining module is specifically configured to:
obtaining at least one historical complaint text; wherein the at least one historical complaint text comprises a text type; one historical complaint text corresponds to one text type;
executing a first operation on each historical complaint text to obtain a word set corresponding to each text type;
the first operation is: preprocessing a first historical complaint text to obtain a word set of the first historical complaint text; determining a word set corresponding to the text type of the first historical complaint text according to the number of first words in the word set of the first historical complaint text, the number of acquired historical complaint texts, and the number of acquired historical complaint texts containing the first words; wherein the first historical complaint text is any one of the at least one historical complaint text; the first word is any word in the set of words of the first historical complaint text.
14. The computing device of claim 10 or 13,
the pre-processing comprises at least one of the following operations: word segmentation operation and stop word deletion operation.
15. The computing device of claim 10,
the obtaining module is further configured to obtain a text type, a historical dispute amount, and a historical reimbursement amount of each historical complaint text in at least one historical complaint text;
and the processing module is also used for establishing a second preset model according to the text type of each historical complaint text, the historical dispute amount and the historical reimbursement amount.
16. The computing device of claim 15, wherein the text types include an emotion type and a complaint type, and wherein the processing module is specifically configured to:
performing curve fitting on the emotion type, the complaint type and the historical dispute amount of the at least one historical complaint text by using a least square method to obtain a least square method fitting curve equation; calculating to obtain a function value of the least square method fitting curve equation;
calculating the sum of squares of the difference value between each historical reimbursement amount and the function value, and acquiring the weight of the corresponding emotion type, the weight of the complaint type, the weight of the dispute amount and the compensation parameter when the sum of squares is minimum;
and establishing a second preset model according to the weight of the emotion type, the weight of the complaint type, the weight of the dispute amount and the compensation parameter.
17. The computing device of claim 16,
the second predetermined model satisfies the formula y ═ w1×x1+w2×x2+w3×x3+ b; wherein y represents a reimbursement amount for a complaint, and x1Type of emotion, x, representing said one complaint2A complaint type, x, representing said one complaint3A dispute amount, w, representing said one complaint1Weight, w, representing the type of emotion2A weight, w, representing the type of complaint3A weight representing the amount of said dispute, b representing said compensation parameter, b > 0.
18. The computing device of claim 10,
the preset rule is a regular expression matching rule.
19. A device for computing a complaint, comprising a processor that executes computer-executable instructions to cause the device for computing a complaint to perform the method of computing a complaint as claimed in any one of claims 1-9 when the device for computing a complaint is run.
20. A computer-readable storage medium comprising instructions that, when executed on a computer, cause the computer to perform a method of calculating a complaint claim as defined in any one of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011172616.9A CN112288446B (en) | 2020-10-28 | 2020-10-28 | Calculation method and device for complaint and claim payment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011172616.9A CN112288446B (en) | 2020-10-28 | 2020-10-28 | Calculation method and device for complaint and claim payment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112288446A true CN112288446A (en) | 2021-01-29 |
| CN112288446B CN112288446B (en) | 2023-06-06 |
Family
ID=74373662
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011172616.9A Active CN112288446B (en) | 2020-10-28 | 2020-10-28 | Calculation method and device for complaint and claim payment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112288446B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112925911A (en) * | 2021-02-25 | 2021-06-08 | 平安普惠企业管理有限公司 | Complaint classification method based on multi-modal data and related equipment thereof |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070027725A1 (en) * | 2005-07-29 | 2007-02-01 | Erwin Dirnberger | Insurance claim management |
| CN109376226A (en) * | 2018-11-08 | 2019-02-22 | 合肥工业大学 | Complain disaggregated model, construction method, system, classification method and the system of text |
| CN109684475A (en) * | 2018-11-21 | 2019-04-26 | 斑马网络技术有限公司 | Processing method, device, equipment and the storage medium of complaint |
| CN110347840A (en) * | 2019-07-18 | 2019-10-18 | 携程计算机技术（上海）有限公司 | Complain prediction technique, system, equipment and the storage medium of text categories |
| CN110457159A (en) * | 2019-08-21 | 2019-11-15 | 深圳前海微众银行股份有限公司 | A kind of method, apparatus, calculating equipment and the storage medium of processing batch tasks |
| CN110990559A (en) * | 2018-09-29 | 2020-04-10 | 北京国双科技有限公司 | Method and apparatus for classifying text, storage medium, and processor |
| CN111553711A (en) * | 2020-04-13 | 2020-08-18 | 携程计算机技术（上海）有限公司 | Method, system, electronic device and medium for configuring order claim scheme |
-
2020
- 2020-10-28 CN CN202011172616.9A patent/CN112288446B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070027725A1 (en) * | 2005-07-29 | 2007-02-01 | Erwin Dirnberger | Insurance claim management |
| CN110990559A (en) * | 2018-09-29 | 2020-04-10 | 北京国双科技有限公司 | Method and apparatus for classifying text, storage medium, and processor |
| CN109376226A (en) * | 2018-11-08 | 2019-02-22 | 合肥工业大学 | Complain disaggregated model, construction method, system, classification method and the system of text |
| CN109684475A (en) * | 2018-11-21 | 2019-04-26 | 斑马网络技术有限公司 | Processing method, device, equipment and the storage medium of complaint |
| CN110347840A (en) * | 2019-07-18 | 2019-10-18 | 携程计算机技术（上海）有限公司 | Complain prediction technique, system, equipment and the storage medium of text categories |
| CN110457159A (en) * | 2019-08-21 | 2019-11-15 | 深圳前海微众银行股份有限公司 | A kind of method, apparatus, calculating equipment and the storage medium of processing batch tasks |
| CN111553711A (en) * | 2020-04-13 | 2020-08-18 | 携程计算机技术（上海）有限公司 | Method, system, electronic device and medium for configuring order claim scheme |
Non-Patent Citations (2)
| Title |
|---|
| XUEFEI MAO 等: "An adaptive weighted least square support vector regression for hysteresis in piezoelectric actuators", 《SENSORS AND ACTUATORS A:PHYSICAL》, pages 423 - 429 * |
| 李国;张春杰;张志远;: "一种基于加权LDA模型的文本聚类方法", 中国民航大学学报, no. 02, pages 46 - 51 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112925911A (en) * | 2021-02-25 | 2021-06-08 | 平安普惠企业管理有限公司 | Complaint classification method based on multi-modal data and related equipment thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112288446B (en) | 2023-06-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110704519A (en) | Business document conversion method and device, storage medium and computer equipment | |
| JP6533048B2 (en) | Compliance check system and compliance check program | |
| CN111914057A (en) | Method and device for detecting and filtering sensitive words of customer service system | |
| CN112003989A (en) | Agent matching method and device, electronic equipment and computer storage medium | |
| CN111092999A (en) | Data request processing method and device | |
| CN112288446A (en) | Method and device for calculating complaint and claim | |
| CN107330709B (en) | Method and device for determining target object | |
| CN114330249A (en) | Information editing method, device, equipment and storage medium | |
| CN114169313A (en) | Priority determination method and device, electronic equipment and storage medium | |
| CN113407610A (en) | Information extraction method and device, electronic equipment and readable storage medium | |
| CN113706223B (en) | Data processing method and device | |
| CN115205163B (en) | Method, device and equipment for processing identification image and storage medium | |
| CN111105238A (en) | Transaction risk control method and device | |
| CN107172311B (en) | Service evaluation method and terminal equipment | |
| CN110600056A (en) | Voice quality inspection method and device | |
| CN115760404A (en) | Stock reduction scheme generation method, system, terminal and storage medium | |
| CN115563942A (en) | Contract generation method and device, electronic equipment and computer readable medium | |
| CN111090787A (en) | Message processing method, device, system and storage medium | |
| CN114529210A (en) | Evaluation method and device based on virtual reality | |
| CN115391343A (en) | Bill data processing method and device, electronic equipment and storage medium | |
| CN116933189A (en) | Data detection method and device | |
| CN111526184B (en) | Business auditing method and device | |
| CN108509258A (en) | Recall method, apparatus, computer equipment and the storage medium of task | |
| CN113344064A (en) | Event processing method and device | |
| CN112241915A (en) | Loan product generation 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 |