Customer experience information acquisition method and device, electronic equipment and computer program product

Abstract

The invention discloses a customer experience information acquisition method and device, electronic equipment and a computer program product, and the method comprises the steps: obtaining basic data of a customer, including portrait data and interaction data of the customer; processing the basic data by using the acquisition mode prediction model to obtain a prediction result of the acquisition mode, the prediction result being that the customer experience information is acquired in a prediction acquisition mode or is not acquired; if the prediction result is collection, customer experience information is collected in a prediction collection mode, and a first collection result is obtained; and if the prediction result is that the customer experience information is not acquired, acquiring the customer experience information by using a default acquisition mode to obtain a second acquisition result. According to the method, the client static portrait data and the dynamic service interaction data are combined to serve as model input, the factors influencing the information collection mode are comprehensively analyzed, multiple collection modes are fitted, the method is not limited to a traditional collection mode of randomly sending questionnaires any more, the requirements of different client groups are better met, and the collection efficiency is improved.

Description

Technical Field

[0001] The present application relates to the field of information collection technology, and in particular to a method, device, electronic device, and computer program product for collecting customer experience information. Background Art

[0002] With the impact of Internet finance, the social economy has entered the era of experience economy. Customer experience management has become the focus of enterprises and the core of improving enterprise competitiveness. All enterprises are building their own customer experience management system (CEMS). Customer experience is a set of multi-dimensional structures generated by the interaction between customers and enterprises, mainly referring to the customer's cognition, emotion, behavior, perception and social response to the company's products and services throughout the service process (including direct or indirect contact).

[0003] Most CEMS will send questionnaires to customers to survey customer experience information, but most customers are not willing to participate in experience information collection. The cost of distributing massive questionnaires has increased, but it has not brought valuable customer experience information feedback to the company. Instead, it has resulted in low efficiency and low questionnaire collection rate. Therefore, how to provide appropriate questionnaire information collection services to the appropriate customer groups at the right time and using the right customer experience information collection method is a problem that needs to be solved urgently. Summary of the invention

[0004] The embodiments of the present application provide a method, device, electronic device, and computer program product for collecting customer experience information to meet the needs of different customer groups and improve the efficiency of collecting customer experience information.

[0005] The present application embodiment adopts the following technical solutions:

[0006] In a first aspect, an embodiment of the present application provides a method for collecting customer experience information, the method for collecting customer experience information comprising:

[0007] Obtaining basic data of the customer, wherein the basic data of the customer includes the customer's portrait data and interaction data;

[0008] Processing the basic data of the customer using a preset collection method prediction model to obtain a prediction result of the customer experience information collection method, wherein the prediction result is whether the customer experience information is collected in the prediction collection method or not;

[0009] In the case where the prediction result is collecting customer experience information in a prediction collection manner, collecting the customer experience information in the prediction collection manner to obtain a first collection result of the customer experience information;

[0010] In the case that the prediction result does not collect the customer experience information, the customer experience information is collected using a default collection method to obtain a second collection result of the customer experience information.

[0011] Optionally, the using a preset collection method prediction model to process the basic data of the customer to obtain a prediction result of the customer experience information collection method includes:

[0012] Extracting features from the basic data of the customer to obtain customer feature coding information;

[0013] Preprocessing the customer feature coding information to obtain preprocessed customer feature coding information;

[0014] The pre-processed customer feature coding information is input into the preset collection method prediction model to obtain the prediction result of the customer experience information collection method.

[0015] Optionally, when the prediction result is to collect customer experience information in a prediction collection manner, collecting the customer experience information in the prediction collection manner to obtain a first collection result of the customer experience information includes:

[0016] In the case where the prediction result is to collect customer experience information by electronic questionnaire collection, determining a corresponding electronic questionnaire template according to the service transaction type in the interaction data;

[0017] Based on the transaction channel type and transaction result information in the interaction data, using the electronic questionnaire template to generate the customer's electronic questionnaire and send it to the customer;

[0018] The first collection result of the customer experience information is determined based on the customer's electronic questionnaire feedback.

[0019] Optionally, when the prediction result is to collect customer experience information in a prediction collection manner, collecting the customer experience information in the prediction collection manner to obtain a first collection result of the customer experience information includes:

[0020] In the case where the prediction result is to collect customer experience information by telephone return visit, generating a telephone return visit work order;

[0021] Collect the telephone return visit result information, and determine the first collection result of the customer experience information based on the telephone return visit result information.

[0022] Optionally, when the prediction result does not collect customer experience information, the customer experience information is collected by using a default collection method, and the second collection result of the customer experience information is obtained, including:

[0023] When the prediction result is that customer experience information is not collected, adding the customer to the group data set that does not collect customer experience information;

[0024] Randomly extract a plurality of target customers from the group data set that does not collect customer experience information;

[0025] Collecting experience information of multiple target customers using the default collection method to obtain a second collection result of the customer experience information;

[0026] After collecting the customer's experience information by using the default collection method to obtain a second collection result of the customer's experience information, the customer experience information collection method further includes:

[0027] The prediction result output by the preset collection method prediction model is verified according to the second collection result of the customer experience information.

[0028] Optionally, the method for collecting customer experience information further includes:

[0029] If the prediction result is to collect customer experience information in a prediction collection method, after collecting the customer experience information in the prediction collection method and obtaining a first collection result of the customer experience information, the customer feature coding information, the prediction result of the customer experience information collection method, and the first collection result of the customer experience information are correspondingly stored in the information collection database;

[0030] If the prediction result is not to collect customer experience information, then after collecting the customer's experience information using the default collection method and obtaining a second collection result of the customer experience information, the customer feature coding information, the prediction result of the customer experience information collection method, and the second collection result of the customer experience information are stored correspondingly in the information collection database.

[0031] Optionally, the method for collecting customer experience information further includes:

[0032] When the production data in the information collection database meets the preset model update conditions, the preset collection mode prediction model is updated using the production data in the information collection database.

[0033] In a second aspect, an embodiment of the present application further provides a device for collecting customer experience information, the device for collecting customer experience information comprising:

[0034] An acquisition unit, used to acquire basic data of a customer, wherein the basic data of a customer includes a portrait data and interaction data of the customer;

[0035] A prediction unit, configured to process the basic data of the customer using a preset collection method prediction model to obtain a prediction result of the customer experience information collection method, wherein the prediction result is to collect the customer experience information in the prediction collection method or not to collect the customer experience information;

[0036] A first collection unit, configured to, when the prediction result is to collect customer experience information in a prediction collection manner, collect the customer experience information in the prediction collection manner to obtain a first collection result of the customer experience information;

[0037] The second collection unit is used to collect the customer's experience information by using a default collection method when the prediction result does not collect the customer's experience information, so as to obtain a second collection result of the customer's experience information.

[0038] In a third aspect, an embodiment of the present application further provides an electronic device, including:

[0039] Processor; and

[0040] A memory arranged to store computer executable instructions which, when executed, cause the processor to perform any of the methods described above.

[0041] In a fourth aspect, an embodiment of the present application further provides a computer program product, including a computer program or instructions, which, when executed by a processor, implements any of the aforementioned methods for collecting customer experience information.

[0042] At least one of the above-mentioned technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects: the customer experience information collection method of the embodiments of the present application first obtains the customer's basic data, and the customer's basic data includes the customer's portrait data and interaction data; then, the customer's basic data is processed using a preset collection method prediction model to obtain a prediction result of the customer experience information collection method, and the prediction result is to collect the customer experience information in a predictive collection method or not to collect the customer experience information; then, when the prediction result is to collect the customer experience information in a predictive collection method, the customer's experience information is collected in a predictive collection method to obtain a first collection result of the customer experience information; finally, when the prediction result is not to collect the customer experience information, the customer's experience information is collected using the default collection method to obtain a second collection result of the customer experience information. The method for collecting customer experience information in the embodiment of the present application combines static customer portrait data with dynamic business interaction data as the input of a preset collection method prediction model. It can comprehensively analyze the factors that affect the customer experience information collection method and fit a variety of customer experience information collection methods, thereby being able to output a variety of predicted collection methods and results without collection. It is no longer limited to the traditional collection method of randomly sending questionnaires, and is more in line with the needs of different customer groups. It improves the efficiency of collecting customer experience information. The overall solution is highly portable, flexible, and has a wide coverage. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0044] Figure 1 A flowchart of a method for collecting customer experience information in an embodiment of the present application;

[0045] Figure 2 This is a schematic diagram of a process for collecting customer experience information in an embodiment of the present application;

[0046] Figure 3 This is a schematic diagram of the structure of a device for collecting customer experience information in an embodiment of the present application;

[0047] Figure 4 This is a schematic diagram of the structure of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0049] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0050] In order to facilitate the understanding of the embodiments of the present application, several existing customer experience information collection solutions are first introduced:

[0051] Patent document CN202210168346.7 discloses an online questionnaire interaction method, including: obtaining the interaction data of the interviewee; generating a first exclusive information to be reached based on the interaction data, and sending the first exclusive information to be reached to the interviewee, wherein the first exclusive information to be reached is used to instruct the interviewee to access the interactive questionnaire; in response to the interviewee's operation of accessing the interactive questionnaire, assigning a value to at least one pre-set entry mark title based on the interaction data, and generating an interaction label of the interviewee based on the interaction data; generating the interactive questionnaire based on the interaction purpose, the interaction label, and the assigned entry mark title. This application has the effect of improving the recovery rate of online questionnaires.

[0052] Patent document CN201810776626.X discloses an intelligent questionnaire survey method, including: obtaining questionnaire characteristic information; obtaining audience group characteristic information; breaking down the questionnaire into question groups based on the questionnaire characteristic information and the audience group characteristic information, and distributing them to audience groups matching the question groups. The method, system, electronic device and computer-readable medium can save the cost of questionnaire surveys, improve the questionnaire recovery rate, and improve the pertinence, flexibility and / or accuracy of questionnaire surveys.

[0053] Patent document CN202011439600.X discloses a questionnaire structuring method, including: obtaining a preset data framework, generating a corresponding entity library based on the preset data framework; obtaining the questionnaire content; performing structured processing on the questionnaire content based on the entity library and the preset data framework to obtain structured questionnaire content; processing the structured questionnaire content according to preset fusion rules to obtain a processed questionnaire. By first creating an entity library in the medical field before processing the medical questionnaire, and performing structured processing on the questionnaire content based on the entity library, the questionnaire content is converted into content that can be recognized and processed by a machine, allowing the machine to automatically analyze and process the recognized questionnaire content, providing doctors with more readable questionnaire content, and no longer requiring doctors to manually process the questionnaire content or view questionnaire content with poor readability, thereby improving doctors' work efficiency and user experience.

[0054] Patent document CN202211279743.8 provides a personalized electronic questionnaire construction method, including: step S1: inputting markup language and questionnaire raw data in the original text editing interface and editing the markup language and questionnaire raw data; step S2: after receiving the preview instruction, identifying and parsing the currently edited markup language and questionnaire raw data to obtain the parsing result; step S3: according to the parsing result, displaying the questionnaire effect in the preview display interface; step S4: editing the basic information about the questionnaire to complete the creation of the basic questionnaire; step S5: automatically and accurately controlling the display or hiding of the remaining questions and their options in the basic questionnaire according to the respondent's answer to the current question, thereby constructing a personalized electronic questionnaire suitable for different respondents. The present invention displays personalized questions and options of the questions according to the content of the respondent's answer sheet, constructs a personalized questionnaire, graphically presents the questionnaire results, and can fully retrieve the questionnaire data.

[0055] It can be seen that the existing questionnaire information collection scheme still has the following major problems:

[0056] 1) Most questionnaire information collection solutions adopt a reactive approach, distributing massive questionnaires to all customer groups, resulting in low questionnaire response rates and increased information collection costs for the company.

[0057] 2) Most questionnaire information collection systems are limited to electronic questionnaires, and there is no channel to provide differentiated services to high-value customers. In addition, the questions in electronic questionnaires are fixed and single.

[0058] Based on this, the present application embodiment provides a method for collecting customer experience information, such as Figure 1 As shown, a flow chart of a method for collecting customer experience information in an embodiment of the present application is provided, and the method for collecting customer experience information at least includes the following steps S110 to S140:

[0059] Step S110, obtaining the basic data of the customer, wherein the basic data of the customer includes the customer's portrait data and interaction data.

[0060] When collecting customer experience information, the embodiment of the present application needs to first obtain the multi-dimensional basic data of the customer, mainly including the customer's own portrait data and interaction data. The portrait data is a model that depicts user needs based on customer data, for example, it may include customer basic attribute information, customer product holding information, customer transaction behavior information, customer channel opening information, etc. Each major category may also include several sub-factors, for example, the basic attribute information may include customer gender, customer age group, customer occupation, customer account nature, risk level rating, customer account opening time, etc.

[0061] Customer interaction data refers to the historical data of the entire process of interaction between the customer and the company from the time the customer comes into contact with the product or service until the time the customer enjoys the service. For example, it may include data such as the service transaction type, transaction channel type, and transaction results.

[0062] Of course, the specific dimensions of data to be set can be flexibly selected by those skilled in the art based on actual application scenarios, and no specific limitation is made here.

[0063] Step S120, using a preset collection method prediction model to process the basic data of the customer to obtain a prediction result of the customer experience information collection method, wherein the prediction result is to collect the customer experience information in the prediction collection method or not to collect the customer experience information.

[0064] The embodiment of the present application uses a deep learning algorithm to pre-train a collection method prediction model, and the collection method prediction model can predict the corresponding collection method based on the input customer feature data. The specific method of training the collection method prediction model can be flexibly implemented by those skilled in the art in combination with existing deep learning algorithms, and is not specifically limited here.

[0065] The obtained customer basic data is encoded into feature data and input into a pre-trained collection method prediction model, so as to obtain the prediction result of the customer experience information collection method output by the model. The prediction result may be collecting customer experience information in a certain prediction collection method, or not collecting customer experience information.

[0066] Step S130, when the prediction result is to collect customer experience information in a prediction collection manner, collect the customer experience information in the prediction collection manner to obtain a first collection result of the customer experience information.

[0067] If the model prediction result is to collect the customer's experience information in a predictive collection manner, it means that collecting the customer experience information in this collection manner will have a better information recovery rate. Therefore, the predictive collection manner can be executed to collect the customer's experience information and judge the collection result of the customer experience information, that is, whether the customer experience information is successfully collected.

[0068] Step S140, when the prediction result does not collect customer experience information, collect customer experience information using a default collection method to obtain a second collection result of the customer experience information.

[0069] If the model prediction result is not to collect the customer's experience information, considering that the prediction effect of the model cannot be completely accurate, in order to collect as much customer experience information as possible while ensuring the recovery rate, the embodiment of the present application can also adopt the default collection method and strategy to collect the customer's experience information, and judge the collection result of the customer experience information, that is, whether the customer experience information is successfully collected. The collection result obtained in this case can be used as one of the bases for reverse verification of whether the model prediction is accurate.

[0070] The method for collecting customer experience information in the embodiment of the present application combines static customer portrait data with dynamic business interaction data as the input of a preset collection method prediction model. It can comprehensively analyze the factors that affect the customer experience information collection method and fit a variety of customer experience information collection methods, thereby being able to output a variety of predicted collection methods and results without collection. It is no longer limited to the traditional collection method of randomly sending questionnaires, and is more in line with the needs of different customer groups. It improves the efficiency of collecting customer experience information. The overall solution is highly portable, flexible, and has a wide coverage.

[0071] In some embodiments of the present application, the use of a preset collection method prediction model to process the customer's basic data to obtain a prediction result of the customer experience information collection method includes: extracting features from the customer's basic data to obtain customer feature coding information; preprocessing the customer feature coding information to obtain preprocessed customer feature coding information; and inputting the preprocessed customer feature coding information into the preset collection method prediction model to obtain a prediction result of the customer experience information collection method.

[0072] Before inputting the basic customer data into the model for processing, the customer's portrait data and interaction data can be feature encoded to extract the multi-dimensional features in the customer portrait data and the multi-dimensional features in the customer interaction data. These multi-dimensional feature data are used together as the model input.

[0073] In deep neural networks, gradient vanishing and gradient exploding are common problems. Data normalization can alleviate these problems, allowing gradients to propagate within a reasonable range, helping to improve the training effect of the model, saving training time, and improving the efficiency of the model. Therefore, the embodiment of the present application further normalizes all the feature data after the above encoding, that is, maps the input parameter to the interval [0,1] according to the following formula.

[0074]

[0075] Among them, x is the original feature data, x min is the minimum value in the original feature data, x max is the maximum value of the original feature data, and y is the target value after normalization. Feature data is mainly divided into discrete data and continuous data. Discrete data, such as customer level, 0 represents ordinary level, 0.25 represents gold card, 0.5 represents platinum, 0.75 represents diamond, and 1 represents private bank. Continuous data, such as customer age, is directly calculated by the above formula.

[0076] In some embodiments of the present application, the preset acquisition mode prediction model is trained in the following manner:

[0077] 1) Structural design of deep neural network model: The deep neural network DNN model has a total of 5 layers, including an input layer, three hidden layers, and an output layer. The input layer contains 17 neurons, the first two hidden layers contain 128 neurons, the third hidden layer contains 32 neurons, and the output layer contains 3 neurons.

[0078] 2) Definition of model output layer: The output layer contains multiple feature dimensions, which represent not collecting customer experience information, collecting customer experience information in some collection methods such as electronic questionnaires or telephone follow-up, etc.

[0079] 3) Activation function definition: In the embodiment of the present application, for example, the ReLu function can be selected as the activation function of the hidden layer to maximize the screening ability of neurons and quickly converge the model, as shown in the following formula:

[0080] f(x)=max(0,x), (2)

[0081] Among them, x is the input of nonlinear change. The output layer fits the customer experience information, which belongs to the multi-classification problem. Therefore, the SoftMax function can be used as the output layer activation function. As shown in the following formula:

[0082]

[0083] Among them, x is the input of the output layer. The option with the highest output probability is the way to fit customer experience information.

[0084] 4) Definition of loss function: The loss function is a measure of the difference between the output calculated by the training sample and the actual output of the training sample. Assume that the l-1th layer contains m neurons and the lth layer contains n neurons, that is, the jth neuron in the lth layer is The generalized calculation formula is:

[0085]

[0086] Among them, the linear relationship coefficient Defined as the linear coefficient from the kth neuron in the l-1th layer to the jth neuron in the lth layer, the input layer w parameter is 1; the offset coefficient represents the offset of the jth neuron in the lth layer, and the output layer offset is 0. Using the matrix method, the output Y of the lth layer is l for:

[0087] Y l =f(Z l )=f(W l X l-1 +B l ), (5)

[0088] Among them, X l-1 is the m×1 input vector of the l-1th layer, Z l Y is the n×1 unactivated linear output of the lth layer, l is the n×1 output vector of the lth layer, W l is an n×m matrix, B l is the n×1 offset vector of the lth layer. The loss function of the output layer Lth layer is defined as:

[0089]

[0090] Among them, Y L is the output vector with feature dimension n_out, and ||S|| 2 is the L2 norm of S. Solve for W L , B L The gradient is:

[0091]

[0092] Here, the symbol ⊙ represents the hadamard product.

[0093] 5) Optimization method: The embodiment of the present application can use the Adam (Adaptive momentum) optimizer, which is a stochastic optimization method for adaptive momentum. First, the exponential moving average of the gradient and the exponential moving average of the square of the gradient are calculated, and then the gradient mean and the gradient square mean need to be bias-corrected. Finally, the parameters are updated, and the initial learning rate is multiplied by the ratio of the gradient mean to the square root of the gradient variance. Specifically, it can be expressed as:

[0094] g t ←▽ θ J(θ t-1 )

[0095] m t ←β 1 m t-1 +(1-β 1 ) t

[0096]

[0097] m t ←m t / (1-β 1 t )

[0098] v t ←v t / (1-β 2 t )

[0099]

[0100] Among them, t is the number of steps to update; α is the learning rate, which is used to control the step size; θ is the parameter to be solved (updated); g t is the gradient obtained by derivation of the objective function; β 1 is the first-order moment attenuation coefficient, β 2 is the second-order moment attenuation coefficient; m t is the gradient g t Expectations, v t is the gradient g t 2 expectations.

[0101] 6) Model training method: Load the customer experience information collection method dataset, randomly select 90% of the samples for training set, and 10% of the samples for test set; split 10% from the training set as the validation set, with a batch size of 64 and a training cycle of 100 rounds. Train the model accuracy to more than 90%, and store the optimal model in the training round.

[0102] It should be noted that the above training process is only an exemplary explanation of the embodiment of the present application. The specific selection and definition of functions, parameter settings and training process, etc., can be flexibly adjusted by technical personnel in this field according to actual scenarios and needs, and no specific limitation is made here.

[0103] In some embodiments of the present application, when the prediction result is to collect customer experience information in a predictive collection manner, the customer experience information is collected in the predictive collection manner to obtain a first collection result of the customer experience information, including: when the prediction result is to collect customer experience information in an electronic questionnaire collection manner, determining a corresponding electronic questionnaire template according to the service transaction type in the interaction data; based on the transaction channel type and transaction result information in the interaction data, generating an electronic questionnaire for the customer using the electronic questionnaire template and sending it to the customer; and determining the first collection result of the customer experience information according to the customer's electronic questionnaire feedback.

[0104] The collection method defined in the embodiment of the present application includes a method of collecting customer experience information by electronic questionnaire collection. If the result of the model prediction is to collect customer experience information by electronic questionnaire collection, the corresponding transaction questionnaire template can be matched according to the service transaction type in the customer interaction data, and then the corresponding questions can be generated according to the transaction channel type and transaction results and other information, so as to quickly match the current user to form a targeted electronic questionnaire and send it to the customer. Then, the feedback of the customer's electronic questionnaire is judged, such as whether the customer's electronic questionnaire is collected within the specified time, and whether the customer's experience information is collected in the collected electronic questionnaire.

[0105] In some embodiments of the present application, when the prediction result is to collect customer experience information in a predictive collection manner, the customer's experience information is collected by using the predictive collection manner to obtain a first collection result of the customer experience information, including: when the prediction result is to collect customer experience information in a telephone follow-up collection manner, generating a telephone follow-up work order; collecting telephone follow-up result information, and determining the first collection result of the customer experience information based on the telephone follow-up result information.

[0106] The collection method defined in the embodiment of the present application also includes collecting customer experience information by telephone follow-up collection method. If the result of the model prediction is to collect customer experience information by telephone follow-up collection method, a corresponding telephone follow-up work order can be generated to facilitate the staff to conduct a telephone follow-up and collect the telephone follow-up result information, such as whether the follow-up was successful and the specific customer information collected during the follow-up.

[0107] In some embodiments of the present application, when the prediction result does not collect customer experience information, the customer's experience information is collected using a default collection method to obtain a second collection result of the customer experience information, including: when the prediction result is that customer experience information is not collected, adding the customer to a group data set that does not collect customer experience information; randomly extracting multiple target customers from the group data set that does not collect customer experience information; collecting experience information of multiple target customers using the default collection method to obtain a second collection result of the customer experience information; after collecting the customer's experience information using the default collection method to obtain the second collection result of the customer experience information, the customer experience information collection method also includes: verifying the prediction result output by the preset collection method prediction model according to the second collection result of the customer experience information.

[0108] If the result of the model prediction is that the customer experience information is not collected, the embodiment of the present application can add the customer to the group data set that does not collect the customer experience information, and then randomly collect the customer experience information from some customers in the customer group by sending electronic questionnaires. The specific number of questionnaires sent can be determined by the hyperparameter λ configured in the following formula:

[0109] m=λM, (9)

[0110] Among them, λ is a custom hyperparameter less than 1, and its size can be flexibly set according to business needs. M is the total number of questionnaires expected to be sent for this business, and m is the number of questionnaires randomly sent to the group that does not collect customer experience information.

[0111] In some embodiments of the present application, the method for collecting customer experience information also includes: if the prediction result is to collect customer experience information in a predictive collection manner, then after collecting the customer's experience information using the predictive collection manner and obtaining a first collection result of the customer experience information, the customer feature coding information, the prediction result of the customer experience information collection manner, and the first collection result of the customer experience information are stored correspondingly in an information collection database; if the prediction result is not to collect customer experience information, then after collecting the customer's experience information using the default collection manner and obtaining a second collection result of the customer experience information, the customer feature coding information, the prediction result of the customer experience information collection manner, and the second collection result of the customer experience information are stored correspondingly in the information collection database.

[0112] Whether the customer experience information is collected by electronic questionnaire collection or telephone return visit information collection, the characteristic coding information of the customer input into the model, the predicted results of the collection method output by the model, and the actual information collection results can be stored in the information collection database accordingly. The information collection results can be identified by a code, for example, 0 indicates successful information collection and 1 indicates failed information collection. The data stored in the information collection database is the production data obtained after the model is actually run in the production environment, so it can serve as the basis for subsequent model iteration and update.

[0113] In some embodiments of the present application, the method for collecting customer experience information further includes: when the production data in the information collection database meets the preset model update conditions, using the production data in the information collection database to update the preset collection method prediction model.

[0114] As production data runs, the information collection database will store and accumulate a large amount of real, high-value production data. The embodiment of the present application can regularly collect high-value production data from the information collection database as a new data set according to the configuration parameters, retrain and iteratively optimize the existing prediction model, and realize self-optimization of the model, so that the prediction information collection results are more and more accurate.

[0115] To facilitate the understanding of the above embodiments, Figure 2 As shown, a schematic diagram of the collection process of customer experience information in an embodiment of the present application is provided. First, customer portrait data and interaction data are obtained; then, the customer portrait data and interaction data are preprocessed by feature encoding and normalization; the preprocessed customer feature data is used as the input of the collection method prediction model, and is input into the collection method prediction model for processing to obtain the prediction result of the collection method prediction model.

[0116] Determine the type of prediction result. If the prediction result is that customer experience information is not collected, use random sampling verification to verify whether the model prediction result is correct. If the prediction result is that customer experience information is collected by electronic questionnaire collection, quickly match the questionnaire template library and customer interaction data to generate an electronic questionnaire and send it to the customer. If customer experience information is collected by non-electronic questionnaire collection methods such as telephone return visits, implement this collection method to collect customer experience information.

[0117] Finally, the collection results of customer experience information are collected and stored in the information collection database together with the customer feature data input by the model and the collection method prediction results output by the model. As the production data stored in the information collection database continues to accumulate, the production data stored in the information collection database is used as new sample data to iteratively update the prediction model to achieve continuous self-optimization of the model.

[0118] In summary, the key points and technical effects of the method for collecting customer experience information of this application mainly include:

[0119] 1) This application proposes a customer experience information collection system analysis method based on a data-driven approach using a deep learning algorithm. By extracting customer portrait model features and interaction data features as model inputs, the customer's static portrait model data is combined with dynamic business interaction data to comprehensively analyze and extract factors that affect the customer experience information collection method. The customer experience information collection method is set to electronic questionnaires, telephone return visits and other collection methods, as well as a method of not collecting information. It is no longer limited to the method of randomly sending questionnaires, which is more in line with the needs of different customer groups and has the advantages of strong portability, strong flexibility and wide coverage.

[0120] 2) The questionnaire information collection system framework proposed in this application collects high-value information collection production data in a data-driven manner, and then reuses the production data as sample data for iterative updates of the model to achieve continuous self-optimization of the model, which has the advantages of iterative upgrades and strong intelligence.

[0121] The present application embodiment also provides a device 300 for collecting customer experience information, such as Figure 3 As shown, a schematic diagram of the structure of a device for collecting customer experience information in an embodiment of the present application is provided. The device 300 for collecting customer experience information includes: an acquisition unit 310, a prediction unit 320, a first collection unit 330, and a second collection unit 340, wherein:

[0122] An acquisition unit 310 is used to acquire basic data of a customer, wherein the basic data of a customer includes a portrait data and interaction data of the customer;

[0123] The prediction unit 320 is used to process the basic data of the customer using a preset collection method prediction model to obtain a prediction result of the customer experience information collection method, wherein the prediction result is to collect the customer experience information in the prediction collection method or not to collect the customer experience information;

[0124] A first collection unit 330 is configured to, when the prediction result is to collect customer experience information in a prediction collection manner, collect the customer experience information in the prediction collection manner to obtain a first collection result of the customer experience information;

[0125] The second collection unit 340 is used to collect the customer's experience information by using a default collection method when the prediction result does not collect the customer's experience information, so as to obtain a second collection result of the customer's experience information.

[0126] In some embodiments of the present application, the prediction unit 320 is specifically used to: extract features from the basic data of the customer to obtain customer feature coding information; preprocess the customer feature coding information to obtain preprocessed customer feature coding information; input the preprocessed customer feature coding information into the preset collection method prediction model to obtain a prediction result of the customer experience information collection method.

[0127] In some embodiments of the present application, the first collection unit 330 is specifically used to: when the prediction result is to collect customer experience information by electronic questionnaire collection, determine the corresponding electronic questionnaire template according to the service transaction type in the interaction data; based on the transaction channel type and transaction result information in the interaction data, use the electronic questionnaire template to generate the customer's electronic questionnaire and send it to the customer; determine the first collection result of the customer experience information according to the customer's electronic questionnaire feedback.

[0128] In some embodiments of the present application, the first collection unit 330 is specifically used to: generate a telephone callback work order when the prediction result is to collect customer experience information by telephone callback collection; collect telephone callback result information, and determine the first collection result of the customer experience information based on the telephone callback result information.

[0129] In some embodiments of the present application, the second collection unit 340 is specifically used to: when the prediction result is not to collect customer experience information, add the customer to the group data set that does not collect customer experience information; randomly extract multiple target customers from the group data set that does not collect customer experience information; use the default collection method to collect experience information of multiple target customers to obtain a second collection result of customer experience information; after collecting the customer's experience information using the default collection method to obtain the second collection result of the customer experience information, the customer experience information collection method also includes: verifying the prediction result output by the preset collection method prediction model according to the second collection result of the customer experience information.

[0130] In some embodiments of the present application, the customer experience information collection device 300 also includes: a storage unit, which is used for, if the prediction result is to collect customer experience information in a predictive collection method, then after collecting the customer's experience information by using the predictive collection method and obtaining a first collection result of the customer experience information, storing the customer feature coding information, the prediction result of the customer experience information collection method, and the first collection result of the customer experience information in a corresponding manner in an information collection database; if the prediction result is not to collect customer experience information, then after collecting the customer's experience information by using the default collection method and obtaining a second collection result of the customer experience information, storing the customer feature coding information, the prediction result of the customer experience information collection method, and the second collection result of the customer experience information in a corresponding manner in the information collection database.

[0131] In some embodiments of the present application, the customer experience information collection device 300 also includes: an updating unit, which is used to update the preset collection method prediction model using the production data in the information collection database when the production data in the information collection database meets the preset model update conditions.

[0132] It can be understood that the above-mentioned customer experience information collection device can implement each step of the customer experience information collection method provided in the above-mentioned embodiment, and the relevant explanations about the customer experience information collection method are applicable to the customer experience information collection device, which will not be repeated here.

[0133] Figure 4 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. Figure 4 At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. The memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage. Of course, the electronic device may also include hardware required for other services.

[0134] The processor, network interface and memory can be interconnected through an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0135] The memory is used to store the program. Specifically, the program may include a program code, and the program code includes a computer operation instruction. The memory may include a memory and a non-volatile memory, and provides instructions and data to the processor.

[0136] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a customer experience information collection device at the logical level. The processor executes the program stored in the memory and is specifically used to perform the following operations:

[0137] Obtaining basic data of the customer, wherein the basic data of the customer includes the customer's portrait data and interaction data;

[0138] Processing the basic data of the customer using a preset collection method prediction model to obtain a prediction result of the customer experience information collection method, wherein the prediction result is whether the customer experience information is collected in the prediction collection method or not;

[0139] In the case where the prediction result is collecting customer experience information in a prediction collection manner, collecting the customer experience information in the prediction collection manner to obtain a first collection result of the customer experience information;

[0140] In the case that the prediction result does not collect the customer experience information, the customer experience information is collected using a default collection method to obtain a second collection result of the customer experience information.

[0141] The above application Figure 1The method performed by the customer experience information collection device disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or an instruction in the form of software. The above processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as being executed by a hardware decoding processor, or executed by a combination of hardware and software modules in a decoding processor. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0142] The embodiment of the present application further proposes a computer program product, including a computer program or an instruction, which, when executed by a processor, implements any of the aforementioned customer experience information collection methods, and is specifically used to execute:

[0143] Obtaining basic data of the customer, wherein the basic data of the customer includes the customer's portrait data and interaction data;

[0144] Processing the basic data of the customer using a preset collection method prediction model to obtain a prediction result of the customer experience information collection method, wherein the prediction result is whether the customer experience information is collected in the prediction collection method or not;

[0145] In the case where the prediction result is collecting customer experience information in a prediction collection manner, collecting the customer experience information in the prediction collection manner to obtain a first collection result of the customer experience information;

[0146] In the case that the prediction result does not collect the customer experience information, the customer experience information is collected using a default collection method to obtain a second collection result of the customer experience information.

[0147] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0148] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0149] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0150] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0151] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0152] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0153] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0154] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0155] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0156] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for collecting customer experience information, characterized in that: The method for collecting customer experience information includes: Obtaining basic data of the customer, wherein the basic data of the customer includes the customer's portrait data and interaction data; Processing the basic data of the customer using a preset collection method prediction model to obtain a prediction result of the customer experience information collection method, wherein the prediction result is to collect the customer experience information in the prediction collection method or not to collect the customer experience information; In the case where the prediction result is collecting customer experience information in a prediction collection manner, collecting the customer experience information in the prediction collection manner to obtain a first collection result of the customer experience information; In the case that the prediction result does not collect the customer experience information, the customer experience information is collected using a default collection method to obtain a second collection result of the customer experience information.

2. The method for collecting customer experience information according to claim 1, characterized in that: The method of processing the basic data of the customer using the preset collection method prediction model to obtain the prediction result of the customer experience information collection method includes: Extracting features from the basic data of the customer to obtain customer feature coding information; Preprocessing the customer feature coding information to obtain preprocessed customer feature coding information; The pre-processed customer feature coding information is input into the preset collection method prediction model to obtain the prediction result of the customer experience information collection method.

3. The method for collecting customer experience information according to claim 1, characterized in that: When the prediction result is to collect customer experience information in a prediction collection manner, collecting the customer experience information in the prediction collection manner to obtain a first collection result of the customer experience information includes: In the case where the prediction result is to collect customer experience information by electronic questionnaire collection, determining a corresponding electronic questionnaire template according to the service transaction type in the interaction data; Based on the transaction channel type and transaction result information in the interaction data, using the electronic questionnaire template to generate the customer's electronic questionnaire and send it to the customer; The first collection result of the customer experience information is determined based on the customer's electronic questionnaire feedback.

4. The method for collecting customer experience information according to claim 1, characterized in that: When the prediction result is to collect customer experience information in a prediction collection manner, collecting the customer experience information in the prediction collection manner to obtain a first collection result of the customer experience information includes: In the case where the prediction result is to collect customer experience information by telephone return visit, generating a telephone return visit work order; Collect the telephone return visit result information, and determine the first collection result of the customer experience information based on the telephone return visit result information.

5. The method for collecting customer experience information according to claim 1, characterized in that: In the case where the prediction result does not collect the customer experience information, the customer experience information is collected by using a default collection method, and the second collection result of the customer experience information is obtained, including: When the prediction result is that customer experience information is not collected, adding the customer to the group data set that does not collect customer experience information; Randomly extract a plurality of target customers from the group data set that does not collect customer experience information; Collecting experience information of multiple target customers using the default collection method to obtain a second collection result of the customer experience information; After collecting the customer's experience information by using the default collection method to obtain a second collection result of the customer's experience information, the customer experience information collection method further includes: The prediction result output by the preset collection method prediction model is verified according to the second collection result of the customer experience information.

6. The method for collecting customer experience information according to claim 2, characterized in that: The method for collecting customer experience information also includes: If the prediction result is to collect customer experience information in a prediction collection method, after collecting the customer experience information in the prediction collection method and obtaining a first collection result of the customer experience information, the customer feature coding information, the prediction result of the customer experience information collection method, and the first collection result of the customer experience information are correspondingly stored in the information collection database; If the prediction result is not to collect customer experience information, then after collecting the customer's experience information using the default collection method and obtaining a second collection result of the customer experience information, the customer feature coding information, the prediction result of the customer experience information collection method, and the second collection result of the customer experience information are stored correspondingly in the information collection database.

7. The method for collecting customer experience information according to claim 1, characterized in that: The method for collecting customer experience information also includes: When the production data in the information collection database meets the preset model update conditions, the preset collection mode prediction model is updated using the production data in the information collection database.

8. A device for collecting customer experience information, characterized in that: The customer experience information collection device comprises: An acquisition unit, used to acquire basic data of a customer, wherein the basic data of a customer includes a portrait data and interaction data of the customer; A prediction unit, configured to process the basic data of the customer using a preset collection method prediction model to obtain a prediction result of the customer experience information collection method, wherein the prediction result is to collect the customer experience information in the prediction collection method or not to collect the customer experience information; A first collection unit, configured to, when the prediction result is to collect customer experience information in a prediction collection manner, collect the customer experience information in the prediction collection manner to obtain a first collection result of the customer experience information; The second collection unit is used to collect the customer's experience information by using a default collection method when the prediction result does not collect the customer's experience information, so as to obtain a second collection result of the customer's experience information.

9. An electronic device, comprising: processor; as well as A memory arranged to store computer executable instructions, wherein when the executable instructions are executed, the processor executes the method for collecting customer experience information according to any one of claims 1 to 7.

10. A computer program product, comprising a computer program or instructions, wherein when the computer program or instructions are executed by a processor, the method for collecting customer experience information according to any one of claims 1 to 7 is implemented.

Images