Customer condition data processing method, device and equipment

Abstract

The invention provides a customer condition data processing method, device and equipment, and relates to the technical field of data processing, and the method comprises the steps: obtaining to-be-processed customer condition data and a customer condition library; determining a strategy library according to the customer condition library; performing matching processing on the to-be-processed customer condition data and data in a customer condition library to obtain matched data; in the strategy library, determining strategy data corresponding to the matched data; determining a customer condition processing scheme according to the matching data and the strategy data; and performing satisfaction evaluation on the customer condition processing scheme to obtain an evaluation result, and outputting the evaluation result. According to the scheme, online operation and automatic study and judgment of the customer information are realized, the customer information handling time is shortened, and the handling efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method, device and equipment for processing customer sentiment data. Background Art

[0002] In the handling of customer relations in the tobacco system, it is necessary to do a good job of customer awareness in advance, carry out customer relationship management work, and create a safe development environment; among them, customer sentiment refers to the personalized experience, subjective feelings and overall satisfaction generated by cigarette retail customers in the process of interaction with tobacco companies, which is based on the real experience of customers in the process of receiving services, including but not limited to product quality, service attitude, business environment, promotional activities and after-sales support; customer awareness refers to the early perception and proactive resolution of various needs and risks that customers may complain about, so as to "prevent illness before it occurs and prevent changes after illness occurs"; customer relationship management refers to a series of management and maintenance activities carried out to establish emotional connections and relationships between tobacco companies and cigarette retail customers during the service process; these activities are aimed at strengthening communication and interaction with customers, understanding and meeting customer needs and expectations, and resolving problems or disputes that customers may encounter. Customer sentiment awareness is an important means to perceive and proactively resolve customer needs in advance and effectively reduce customer complaints. Currently, customer sentiment awareness is mainly operated through manual records, paper circulation, and manual analysis and judgment. This method can only handle customer sentiment based on personal experience, with low processing efficiency and poor processing results. At the same time, with the in-depth advancement of customer service work, the amount of customer sentiment awareness information has increased significantly, and the workload of customer sentiment handling has increased sharply. The original "offline + manual analysis and judgment" operation mode can no longer meet the needs of fast and effective customer sentiment awareness. It is urgent to build a new set of customer sentiment awareness operation modes to realize the online operation and automatic analysis of customer sentiment information, shorten the customer sentiment awareness handling time, and improve the handling efficiency. Summary of the invention

[0003] The present invention provides a method, device and equipment for processing customer sentiment data, which solves the problems of long processing time, low processing efficiency, inability to automatically analyze customer sentiment and high labor cost in existing customer sentiment perception methods.

[0004] In order to solve the above technical problems, the technical solution of the present invention is as follows:

[0005] An embodiment of the present invention provides a method for processing customer sentiment data, which is applied to a customer sentiment processing system. The method includes:

[0006] Obtain the customer sentiment data to be processed and the customer sentiment database;

[0007] Determine a strategy library according to the customer sentiment library;

[0008] Matching the customer sentiment data to be processed with the data in the customer sentiment database to obtain matching data;

[0009] In the policy library, determining policy data corresponding to the matching data;

[0010] Determine a customer situation processing plan based on the matching data and the strategy data;

[0011] Conduct a satisfaction evaluation on the customer relationship handling solution, obtain the evaluation results, and output them.

[0012] Optionally, obtaining the customer information database includes:

[0013] Obtain initial customer data;

[0014] Performing data standardization processing on the initial customer sentiment data to obtain standard processed data;

[0015] Performing quantization processing on the standard processed data to obtain matrix processed data;

[0016] Performing cluster distribution processing on the matrix processed data to obtain a cluster distribution graph;

[0017] The cluster distribution diagram is subjected to target classification to obtain a customer sentiment database.

[0018] Optionally, determining a strategy library according to the customer sentiment library includes:

[0019] Obtain risk index values ​​and corresponding importance values ​​of all customer sentiment data in the customer sentiment database;

[0020] Determine the strategy library based on the risk index value and corresponding importance value of each customer situation.

[0021] Optionally, obtain the risk index values ​​and corresponding importance values ​​of all customer sentiment data in the customer sentiment database, including:

[0022] Obtaining potential customer sentiment risk factors of customer sentiment data in the customer sentiment database;

[0023] According to the potential factors of customer sentiment risk, the risk index values ​​and corresponding importance values ​​of all customer sentiment data in the customer sentiment database are obtained.

[0024] Optionally, matching the customer sentiment data to be processed with the data in the customer sentiment database to obtain matching data includes:

[0025] Inputting the customer sentiment data to be processed into the customer sentiment database;

[0026] The customer sentiment database performs matching processing according to a preset customer sentiment matching degree;

[0027] When the customer sentiment data to be processed is greater than or equal to the preset customer sentiment matching degree, the data matching requirements are met and the matching data is output; when the customer sentiment data to be processed is less than the preset customer sentiment matching degree, a secondary analysis is performed on the customer sentiment data to be processed so that the customer sentiment data to be processed meets the data matching requirements and the matching data is output.

[0028] Optionally, in the policy library, determining the policy data corresponding to the matching data includes:

[0029] The matching data is mapped with the policy library through a target mapping relationship to determine the policy data corresponding to the matching data in the policy library.

[0030] Optionally, a satisfaction evaluation is performed on the customer relationship handling solution to obtain and output the evaluation results, including:

[0031] Obtain satisfaction evaluation data of customer relationship management solutions;

[0032] According to the satisfaction evaluation data and the satisfaction evaluation rules, a satisfaction score is obtained;

[0033] An evaluation result is output according to the satisfaction score, and the matching data in the customer sentiment database and the strategy data in the strategy database are dynamically adjusted in real time according to the evaluation result.

[0034] The present invention also provides a device for processing customer sentiment data, comprising:

[0035] The acquisition module is used to obtain the customer sentiment data to be processed and the customer sentiment database;

[0036] A processing module is used to determine a policy library based on the customer sentiment library; match the customer sentiment data to be processed with the data in the customer sentiment library to obtain matching data; determine the policy data corresponding to the matching data in the policy library; determine a customer sentiment processing plan based on the matching data and the policy data; conduct a satisfaction evaluation on the customer sentiment processing plan, obtain an evaluation result, and output it.

[0037] The present invention also provides a computing device, comprising: a processor, a memory, and a program or instruction stored in the memory and executable on the processor. When the program or instruction runs on a computer, the computer executes the above-mentioned data processing method applied to an audit system.

[0038] The present invention also provides a computer-readable storage medium storing instructions, which, when executed on a computer, enables the computer to execute the above-mentioned data processing method applied to an audit system.

[0039] The above solution of the present invention includes at least the following beneficial effects:

[0040] The method for processing customer sentiment data of the present invention obtains customer sentiment data to be processed and a customer sentiment database; determines a strategy database based on the customer sentiment database; matches the customer sentiment data to be processed with the data in the customer sentiment database to obtain matching data; determines strategy data corresponding to the matching data in the strategy database; determines a customer sentiment processing plan based on the matching data and the strategy data; and performs a satisfaction evaluation on the customer sentiment processing plan to obtain an evaluation result and output it. The method realizes the online operation and automatic judgment of customer sentiment information, shortens the time for processing customer sentiment awareness, and improves the efficiency of processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a flowchart of the method for processing customer sentiment data of the present invention;

[0042] Figure 2 It is a structural schematic diagram of the customer sentiment data processing device of the present invention. DETAILED DESCRIPTION

[0043] The exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present invention and to enable the scope of the present invention to be fully communicated to those skilled in the art.

[0044] like Figure 1 As shown, an embodiment of the present invention provides a method for processing customer sentiment data, including:

[0045] Step 11, obtaining the customer sentiment data to be processed and the customer sentiment database;

[0046] Step 12, determining a strategy library according to the customer sentiment library;

[0047] Step 13, matching the customer sentiment data to be processed with the data in the customer sentiment database to obtain matching data;

[0048] Step 14, determining the policy data corresponding to the matching data in the policy library;

[0049] Step 15, determining a customer situation processing plan based on the matching data and the strategy data;

[0050] Step 16, conduct a satisfaction evaluation on the customer relationship handling solution, obtain the evaluation result, and output it.

[0051] In this embodiment, the method for processing customer sentiment data is applied to a customer sentiment processing system, which can collect, summarize, and input customer sentiment in the form of voice or text, and automatically provide a customer sentiment processing plan to the staff; by obtaining the customer sentiment data to be processed and the customer sentiment library; determining the strategy library according to the customer sentiment library; matching the customer sentiment data to be processed with the data in the customer sentiment library to obtain matching data; determining the strategy data corresponding to the matching data in the strategy library; determining the customer sentiment processing plan according to the matching data and the strategy data; and evaluating the satisfaction of the customer sentiment processing plan to obtain the evaluation result and output it. The online operation and automatic judgment of customer sentiment information are realized, the time for customer sentiment awareness and processing is shortened, and the efficiency of processing is improved.

[0052] In an optional embodiment of the present invention, obtaining the customer sentiment database in step 11 includes:

[0053] Step 111, obtaining initial customer sentiment data;

[0054] Step 112, performing data standardization processing on the initial customer sentiment data to obtain keyword entry data;

[0055] Step 113, quantizing the keyword data to obtain matrix processed data;

[0056] Step 114, performing cluster distribution processing on the matrix processed data to obtain a cluster distribution graph;

[0057] Step 115, target classification is performed on the cluster distribution diagram to determine the customer sentiment database.

[0058] In this embodiment, the initial customer sentiment data mainly refers to the personalized experience, subjective feelings and overall satisfaction customer sentiment data generated by cigarette retail customers in the process of interaction with tobacco enterprises, and specifically may include customer sentiment data on unsatisfied demand for ordering some cigarettes, customer sentiment data on retail customers expressing dissatisfaction or complaints, customer sentiment data on doubts about the disclosure and publicity of supply source information, customer sentiment data on unsatisfied demand for ordering some cigarettes, customer sentiment data on retail customers expressing dissatisfaction or complaints, and customer sentiment data on unsatisfied demand for ordering cigarettes for events (such as cigarettes for weddings, business use, construction sites, entertainment hotels, etc.);

[0059] Keyword extraction is performed on the initial customer sentiment data to obtain multiple keyword entries, and the customer sentiment information is classified and processed according to the real feelings of the retail customers through preset dimensions (such as demands / complaints, complaints / blames, expectations / desires) (for example, customer sentiment data in which retail customers express dissatisfaction or complaints are classified into the complaint category); then the classified data is cleaned to remove duplicate records, process missing values, correct errors and outliers, etc., to obtain standard processed data and eliminate interference from other irrelevant data;

[0060] Each term in the standard processing data is assigned a value and quantified, and then a calculation matrix is ​​established and the required matrix structure is determined to process the data. In this embodiment, a two-dimensional table matrix is ​​used, and rows and columns represent key term variables.

[0061] Perform cluster analysis on the data obtained from matrix processing, cluster the data through clustering algorithms such as K-means, hierarchical clustering, DBSCAN, etc., explain the characteristics of each cluster, and label the clusters as needed. Finally, obtain the cluster distribution map based on different business lines, such as marketing, monopoly, professional behavior, distribution, etc.

[0062] Analyze the cluster distribution map, design the structure of the graph database according to the clustering results, import the results of the cluster analysis into the graph database, and set corresponding attributes and relationships, such as serial number, customer information items, customer information content, collection method, collection subject, collection type, etc., to form a customer information database.

[0063] In an optional embodiment of the present invention, step 12 may include:

[0064] Step 121, obtaining the risk index values ​​and corresponding importance values ​​of all customer sentiment data in the customer sentiment database;

[0065] Step 122, determining a strategy library according to the risk index value and the corresponding importance value of each customer sentiment.

[0066] In this embodiment, according to the risk index value (PRN) of each customer situation in the customer situation database and the corresponding importance value (S), a handling rule is formulated in the strategy database, and a strategy database is constructed according to the handling rule and the handling countermeasure corresponding to each customer situation; wherein the handling countermeasure corresponding to each customer situation may specifically be, for example, when the customer situation is that the client's demand for ordering cigarettes for an event is not met (such as cigarettes for weddings, business use, construction site use, entertainment hotels, etc.), the corresponding handling countermeasure is to verify the event situation on site, and let the customer fill out an application form for cigarettes for the event, and re-supply the required cigarettes according to the application form for the customer whose situation is true;

[0067] The specific disposal rules can be: when PRN ≥ 200 or S ≥ 8, the disposal method is set as offline disposal, the disposal time limit is immediate disposal, and the disposal subject is the municipal bureau;

[0068] When 120≤PRN<200 or 6≤S<8, the disposal method is set as offline disposal, the disposal time limit is immediate disposal, and the disposal entity is the county or distribution center;

[0069] When 80≤PRN<120 or 4≤S<6, the disposal method is set as offline disposal, the disposal time limit is within 30 minutes, and the disposal entity is the service station or distribution department;

[0070] When PRN<80 and S<4, the handling method is formulated as online or offline handling, the handling time limit is within 60 minutes, and the handling subject is the front-line personnel;

[0071] When the RPN value and S value conditions conflict, the policy library rule condition takes the heavier one.

[0072] In an optional embodiment of the present invention, step 121 may include:

[0073] Step 1211, obtaining customer sentiment risk potential factors of customer sentiment data in the customer sentiment database;

[0074] Step 1212: Obtain risk index values ​​and corresponding importance values ​​of all customer relationship data in the customer relationship database according to the customer relationship risk potential factors.

[0075] In this embodiment, the customer data in the customer database is sorted out, and potential factors of customer risk that may exist are mined through fault tree analysis. The potential risk factors include equipment damage and aging, unsuccessful order settlement, unsatisfied ordering needs, unfair distribution of supply, changes in consumer groups, brand promotion, insufficient consumer guidance capabilities, market dynamic changes, etc.

[0076] The factors are evaluated by the consequence impact and severity (S), the cause and possibility of failure (O), the inspection method and detectability (D) of the potential risk factors, and the importance value (S) of the potential risk factors is calculated according to the importance value table;

[0077] Then multiply the consequence impact and severity (S), failure cause and possibility (O), inspection method and detectability (D) to obtain the risk index value (RPN) of each factor.

[0078] In an optional embodiment of the present invention, step 13 may include:

[0079] Step 131, inputting the customer sentiment data to be processed into the customer sentiment database;

[0080] Step 132, the customer sentiment database performs matching processing according to a preset customer sentiment matching degree;

[0081] Step 133, when the customer sentiment data to be processed is greater than or equal to the preset customer sentiment matching degree, the data matching requirement is met and the matching data is output; when the customer sentiment data to be processed is less than the preset customer sentiment matching degree, a secondary analysis is performed on the customer sentiment data to make the customer sentiment data to be processed meet the data matching requirement and the matching data is output.

[0082] In this embodiment, the data types of the customer sentiment data to be processed are classified, and the types mainly include true value, date, category, unique ID of input data item, time item, static input, known input, etc.; the customer sentiment data to be processed is preprocessed, text fields (such as description, name, etc.) are extracted, and they are converted into word embeddings or sequences; the linear transformation of the output of the time fusion decoder is used to generate quantile predictions:

[0083]

[0084] Among them, W q , b q is a linear coefficient used to specify the quantile q, which is optimized by the loss function to minimize the quantile and summed over all quantile outputs:

[0085] The loss function used is as follows:

[0086]

[0087] Among them, y is the actual value, is the predicted value, q is the quantile, t is the first moment time, τ is the second moment time, y t is the value at the first moment.

[0088] Through the customer information processing model, static variables are used as input, and the unknown (future) dynamic variables are predicted through the known dynamic variables input; the closer the time to be predicted is to the known data time, the smaller the loss and the higher the prediction accuracy; further, the mean square error function is used to calculate the gap between the predicted value and the standard value to measure the gap between the two;

[0089] The formula for mean square error is as follows:

[0090]

[0091] Where X obs Indicates the actual standard value, X model It represents the predicted value of the model output. The smaller the value is, the closer the predicted value is to the actual value.

[0092] Through continuous iteration, the model can continuously predict the best matching countermeasures and relationship with the processing team for each retailer when generating customer relationships. In order to improve the accuracy of the model, in actual use, a certain amount of high-quality customer relationship processing data can be regularly sampled directly to compare the accuracy of the model predictions. The model can also be further optimized and adjusted using the directly sampled data, thereby continuously improving the model's prediction capabilities.

[0093] According to the matching situation of the customer sentiment database, in the customer sentiment analysis, if the customer sentiment matching degree is low, the disposal strategy automatically recommended by the system will not meet the needs of effective customer disposal. At this time, based on the customer sentiment matching similarity, the system automatically forwards the customer sentiment to the customer sentiment special team of the municipal bureau (company). The customer sentiment special team will maintain the customer sentiment content, disposal strategy, and risk index in the customer sentiment database, and then the system will make a secondary judgment and output the matching data.

[0094] In an optional embodiment of the present invention, step 14 may include:

[0095] Mapping the matching data with the policy library through a target mapping relationship to determine the policy data corresponding to the matching data in the policy library;

[0096] In this embodiment, the customer situation description is determined as a common attribute associated with the customer situation database and the policy database, a unique ID is set, and a mapping relationship between the customer situation database and the policy database is constructed; the mapping relationship is used to determine the corresponding strategy, including the customer situation handling subject, handling time, handling measures, etc.

[0097] In an optional embodiment of the present invention, step 16 may include:

[0098] Step 161, obtaining satisfaction evaluation data of the customer relationship processing solution;

[0099] Step 162, obtaining a satisfaction score according to the satisfaction evaluation data and satisfaction evaluation rules;

[0100] Step 163: output an evaluation result according to the satisfaction score, and dynamically adjust the matching data in the customer sentiment database and the strategy data in the strategy database in real time according to the evaluation result.

[0101] In this embodiment, after processing according to the customer sentiment data, the satisfaction evaluation index of the customer feedback is received, and the satisfaction evaluation includes very satisfied, satisfied, average, dissatisfied, and very dissatisfied, and the satisfaction evaluation index is assigned a value, and the very satisfied is assigned a value of 5, the satisfied is assigned a value of 4, the average is assigned a value of 3, the dissatisfied is assigned a value of 2, and the very dissatisfied is assigned a value of 1;

[0102] By formula:

[0103] Calculate and obtain the satisfaction evaluation results;

[0104] Then, the weight of each factor is calculated through the critic weight method to determine the weight of each factor in the customer satisfaction evaluation, providing strong support for subsequent decision-making and optimization;

[0105] When calculating the weight, the variability and conflict indicators are multiplied and normalized to obtain the final weight;

[0106] Based on the final weight, and in accordance with the evaluation results of each customer relationship handling and changes in relevant policies, the customer relationship descriptions and customer relationship handling strategies in the customer relationship database and strategy database are adjusted dynamically in real time to ensure the timeliness of customer relationship handling to the greatest extent.

[0107] like Figure 2 As shown, an embodiment of the present invention further provides a customer sentiment data processing device 20, comprising:

[0108] An acquisition module 21 is used to acquire customer sentiment data to be processed and a customer sentiment database;

[0109] The processing module 22 is used to determine the policy library based on the customer sentiment library; match the customer sentiment data to be processed with the data in the customer sentiment library to obtain matching data; determine the policy data corresponding to the matching data in the policy library; determine the customer sentiment processing plan based on the matching data and the policy data; conduct a satisfaction evaluation on the customer sentiment processing plan, obtain the evaluation result, and output it.

[0110] Optionally, obtaining the customer information database includes:

[0111] Obtain initial customer data;

[0112] Performing data standardization processing on the initial customer sentiment data to obtain standard processed data;

[0113] Performing quantization processing on the standard processed data to obtain matrix processed data;

[0114] Performing cluster distribution processing on the matrix processed data to obtain a cluster distribution graph;

[0115] The cluster distribution diagram is subjected to target classification to obtain a customer sentiment database.

[0116] Optionally, determining a strategy library according to the customer sentiment library includes:

[0117] Obtain risk index values ​​and corresponding importance values ​​of all customer sentiment data in the customer sentiment database;

[0118] Determine the strategy library based on the risk index value and corresponding importance value of each customer situation.

[0119] Optionally, obtain the risk index values ​​and corresponding importance values ​​of all customer sentiment data in the customer sentiment database, including:

[0120] Obtaining potential customer sentiment risk factors of customer sentiment data in the customer sentiment database;

[0121] According to the potential factors of customer sentiment risk, the risk index values ​​and corresponding importance values ​​of all customer sentiment data in the customer sentiment database are obtained.

[0122] Optionally, matching the customer sentiment data to be processed with the data in the customer sentiment database to obtain matching data includes:

[0123] Inputting the customer sentiment data to be processed into the customer sentiment database;

[0124] The customer sentiment database performs matching processing according to a preset customer sentiment matching degree;

[0125] When the customer sentiment data to be processed is greater than or equal to the preset customer sentiment matching degree, the data matching requirements are met and the matching data is output; when the customer sentiment data to be processed is less than the preset customer sentiment matching degree, a secondary analysis is performed on the customer sentiment data to be processed so that the customer sentiment data to be processed meets the data matching requirements and the matching data is output.

[0126] Optionally, in the policy library, determining the policy data corresponding to the matching data includes:

[0127] The matching data is mapped with the policy library through a target mapping relationship to determine the policy data corresponding to the matching data in the policy library.

[0128] Optionally, a satisfaction evaluation is performed on the customer relationship handling solution to obtain and output the evaluation results, including:

[0129] Obtain satisfaction evaluation data of customer relationship management solutions;

[0130] According to the satisfaction evaluation data and the satisfaction evaluation rules, a satisfaction score is obtained;

[0131] The evaluation result is outputted according to the satisfaction score, and the matching data in the customer database and the policy data in the policy database are dynamically adjusted in real time according to the evaluation result. It should be noted that the device is a device corresponding to the data processing method applied to the audit system, and all implementation methods in the above method are applicable to the embodiments of the device and can achieve the same technical effect.

[0132] An embodiment of the present invention also provides a computing device, comprising: a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the steps of the data processing method as described for application to an audit system.

[0133] The embodiment of the present invention further provides a computer-readable storage medium, including instructions, which, when executed on a computer, enable the computer to execute the data processing method applied to an audit system as described above. All implementations in the above method embodiments are applicable to this embodiment and can achieve the same technical effect.

[0134] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0135] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0136] In the embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0137] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0138] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0139] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, ROM, RAM, magnetic disks, or optical disks.

[0140] In addition, it should be noted that in the apparatus and method of the present invention, it is obvious that each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. Moreover, the steps of performing the above-mentioned series of processing can naturally be performed in chronological order according to the order of description, but it is not necessary to perform them in chronological order, and some steps can be performed in parallel or independently of each other. For those of ordinary skill in the art, it is understood that all or any steps or components of the method and apparatus of the present invention can be implemented in any computing device (including processors, storage media, etc.) or a network of computing devices in hardware, firmware, software or a combination thereof, which can be achieved by those of ordinary skill in the art using their basic programming skills after reading the description of the present invention.

[0141] Therefore, the purpose of the present invention can also be achieved by running a program or a group of programs on any computing device. The computing device can be a well-known general device. Therefore, the purpose of the present invention can also be achieved by simply providing a program product containing a program code that implements the method or device. That is to say, such a program product also constitutes the present invention, and the storage medium storing such a program product also constitutes the present invention. Obviously, the storage medium can be any well-known storage medium or any storage medium developed in the future. It should also be pointed out that in the device and method of the present invention, it is obvious that each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. In addition, the steps of performing the above-mentioned series of processing can naturally be performed in chronological order according to the order of description, but it is not necessary to perform them in chronological order. Some steps can be performed in parallel or independently of each other.

[0142] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for processing customer sentiment data, characterized in that: Applied to customer relationship processing system, including: Obtain the customer sentiment data to be processed and the customer sentiment database; Determine a strategy library according to the customer sentiment library; Matching the customer sentiment data to be processed with the data in the customer sentiment database to obtain matching data; In the policy library, determining policy data corresponding to the matching data; Determine a customer situation processing plan based on the matching data and the strategy data; Conduct a satisfaction evaluation on the customer relationship handling solution, obtain the evaluation results, and output them.

2. The method for processing customer sentiment data according to claim 1, characterized in that: Obtaining customer information database includes: Obtain initial customer data; Performing data standardization processing on the initial customer sentiment data to obtain standard processed data; Performing quantization processing on the standard processed data to obtain matrix processed data; Performing cluster distribution processing on the matrix processed data to obtain a cluster distribution graph; The cluster distribution diagram is subjected to target classification to obtain a customer sentiment database.

3. The method for processing customer sentiment data according to claim 1, characterized in that: Determine a strategy library according to the customer sentiment library, including: Obtain risk index values ​​and corresponding importance values ​​of all customer sentiment data in the customer sentiment database; Determine the strategy library based on the risk index value and corresponding importance value of each customer situation.

4. The method for processing customer sentiment data according to claim 3, characterized in that: Obtain the risk index values ​​and corresponding importance values ​​of all customer sentiment data in the customer sentiment database, including: Obtaining potential customer sentiment risk factors of customer sentiment data in the customer sentiment database; According to the potential factors of customer sentiment risk, the risk index values ​​and corresponding importance values ​​of all customer sentiment data in the customer sentiment database are obtained.

5. The method for processing customer sentiment data according to claim 1, characterized in that: Matching the customer sentiment data to be processed with the data in the customer sentiment database to obtain matching data includes: Inputting the customer sentiment data to be processed into the customer sentiment database; The customer sentiment database performs matching processing according to a preset customer sentiment matching degree; When the customer sentiment data to be processed is greater than or equal to the preset customer sentiment matching degree, the data matching requirements are met and the matching data is output; when the customer sentiment data to be processed is less than the preset customer sentiment matching degree, a secondary analysis is performed on the customer sentiment data to be processed so that the customer sentiment data to be processed meets the data matching requirements and the matching data is output.

6. The method for processing customer sentiment data according to claim 5, characterized in that: In the policy library, determining the policy data corresponding to the matching data includes: The matching data is mapped with the policy library through a target mapping relationship to determine the policy data corresponding to the matching data in the policy library.

7. The method for processing customer sentiment data according to claim 1, characterized in that: Conduct a satisfaction evaluation on the customer relationship handling solution, obtain the evaluation results, and output them, including: Obtain satisfaction evaluation data of customer relationship management solutions; According to the satisfaction evaluation data and the satisfaction evaluation rules, a satisfaction score is obtained; An evaluation result is output according to the satisfaction score, and the matching data in the customer sentiment database and the strategy data in the strategy database are dynamically adjusted in real time according to the evaluation result.

8. A device for processing customer sentiment data, characterized in that: include: The acquisition module is used to obtain the customer sentiment data to be processed and the customer sentiment database; A processing module, used for determining a strategy library according to the customer sentiment library; The customer sentiment data to be processed is matched with the data in the customer sentiment database to obtain matching data; in the strategy database, the strategy data corresponding to the matching data is determined; according to the matching data and the strategy data, a customer sentiment processing plan is determined; and a satisfaction evaluation is performed on the customer sentiment processing plan to obtain an evaluation result and output it.

9. A computing device, characterized in that include: A processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein when the program or instruction is executed on a computer, the computer executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are executed on a computer, the computer is caused to execute the method according to any one of claims 1 to 7.

Images