Insurance renewal behavior prediction method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides an insurance renewal behavior prediction method and device, electronic equipment and a storage medium, and belongs to the technical field of artificial intelligence. The method comprises the following steps: acquiring insurance speech terms, clustering the insurance speech terms to obtain speech expression features and speech categories of the speech expression features, acquiring sample insurance renewal prompt dialogue statements, performing feature extraction on the sample insurance renewal prompt dialogue statements to obtain object insurance renewal objection features, and determining the object insurance renewal objection features according to the object insurance renewal objection features. Performing insurance renewal behavior prediction according to the object insurance renewal objection feature to obtain an object insurance renewal category, screening the verbal skill category according to the verbal skill expression feature and the object insurance renewal objection feature to obtain a target category, and performing model construction according to the target category, the object insurance renewal category and a preset object feature to obtain a target insurance renewal prediction model, and insurance renewal behavior prediction is performed on the target insurance renewal prompt dialogue statement through the target insurance renewal prediction model, so that the accuracy of insurance renewal behavior prediction can be improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, is applicable to the field of financial technology, and in particular to a renewal behavior prediction method and device, electronic device and storage medium. Background Art

[0002] In the insurance industry, renewing premiums is an important part of maintaining the validity of policies and providing continuous protection. Insurance companies usually remind users to renew their policies by phone, and the phone recording data contains detailed interaction information between customers and insurance companies. In related technologies, keyword matching is used to extract keywords from phone recording data, and predict users' renewal behavior based on keywords. However, this method cannot accurately identify users' renewal intentions. For example, if the phrase "Are you not paying anymore?" appears in the phone recording data, the keyword matching method will match this phrase as non-renewal, resulting in low accuracy in predicting renewal behavior. Summary of the invention

[0003] The main purpose of the embodiments of the present application is to propose a renewal behavior prediction method and device, an electronic device and a storage medium, aiming to improve the accuracy of renewal behavior prediction.

[0004] To achieve the above-mentioned purpose, a first aspect of an embodiment of the present application proposes a renewal behavior prediction method, the method comprising:

[0005] Get insurance jargon phrases;

[0006] Clustering the insurance speech sentences to obtain speech expression features and speech categories of the speech expression features;

[0007] Get sample renewal reminder dialogue statements;

[0008] Extract features from the sample renewal prompt dialogue sentences to obtain renewal objection features of the object;

[0009] Predicting the renewal behavior of the object according to the renewal objection characteristics of the object, and obtaining the renewal category of the object; the renewal category of the object is used to indicate renewal or non-renewal;

[0010] The speech category is screened according to the speech expression characteristics and the renewal objection characteristics of the object to obtain a target category;

[0011] A model is constructed according to the target category, the object renewal category and preset object features to obtain a target renewal prediction model; the preset object features are features of the preset renewal object obtained in advance;

[0012] The target renewal prediction model is used to predict the renewal behavior of the preset target renewal prompt dialogue sentence.

[0013] In some embodiments, the model is constructed according to the target category, the object renewal category and the preset object features to obtain the target renewal prediction model, including:

[0014] Constructing a decision tree according to the target category, the object renewal category, and the preset object features to obtain a first decision tree;

[0015] Predicting the renewal behavior of the target category and the preset object features by using the first decision tree to obtain a predicted renewal category;

[0016] Obtaining the renewal prediction weight of the first decision tree;

[0017] Calculate a reference sample gradient according to the object renewal category, the predicted renewal category, and the renewal prediction weight;

[0018] Constructing a decision tree according to the reference sample gradient, the target category, the object renewal category, and the preset object feature to obtain a second decision tree;

[0019] The target renewal prediction model is determined according to the first decision tree and the second decision tree.

[0020] In some embodiments, constructing a decision tree according to the target category, the object renewal category, and the preset object feature to obtain a first decision tree includes:

[0021] Performing feature screening on the target category and the preset object features to obtain original features;

[0022] Discretizing the original features to obtain discrete sub-features;

[0023] Calculating a feature gain of the discrete sub-feature according to the object renewal category;

[0024] Selecting the discrete sub-feature with the largest feature gain as a reference sub-feature;

[0025] Node construction is performed according to the reference sub-features to obtain a decision node;

[0026] The first decision tree is constructed according to the decision nodes.

[0027] In some embodiments, the calculating the feature gain of the discrete sub-feature according to the object renewal category includes:

[0028] Determine a reference renewal category according to the renewal category of the object;

[0029] Screening the renewal category of the object according to the discrete sub-features to obtain candidate renewal categories and the number of the candidate renewal categories;

[0030] determining an original sample gradient according to the reference renewal category, the candidate renewal category, and the number of categories of the candidate renewal category;

[0031] The feature gain of the discrete sub-feature is calculated according to the original sample gradient.

[0032] In some embodiments, the step of calculating the feature gain of the discrete sub-feature according to the original sample gradient includes:

[0033] Performing feature splitting on the discrete sub-feature to obtain a first sub-feature and a second sub-feature;

[0034] Calculate a first sub-gain of the first sub-feature according to the original sample gradient;

[0035] Calculating a second sub-gain of the second sub-feature according to the original sample gradient;

[0036] The first sub-gain and the second sub-gain are summed to obtain a feature gain of the discrete sub-feature.

[0037] In some embodiments, obtaining the renewal prediction weight of the first decision tree includes:

[0038] Calculate the loss according to the target renewal category and the predicted renewal category to obtain target loss data;

[0039] Determine first-order moment data and second-order moment data according to the target loss data;

[0040] The renewal prediction weight of the first decision tree is calculated based on the first-order moment data and the second-order moment data.

[0041] In some embodiments, clustering the insurance speech sentences to obtain speech expression features and speech categories of the speech expression features includes:

[0042] Performing sentence vectorization processing on the insurance speech phrase to obtain an insurance speech phrase vector;

[0043] Calculating the distance between the insurance speech vector and a preset cluster center to obtain a speech distance;

[0044] Clustering the insurance speech vectors according to the speech distance to obtain insurance speech clusters;

[0045] Performing average calculation on the insurance speech clusters to obtain the speech expression features;

[0046] Determine the speech category of the speech expression feature based on the insurance speech cluster.

[0047] To achieve the above-mentioned purpose, a second aspect of an embodiment of the present application provides a renewal behavior prediction device, the device comprising:

[0048] A speech sentence acquisition module, which acquires insurance speech sentences;

[0049] A clustering module, used for clustering the insurance speech sentences to obtain speech expression features and speech categories of the speech expression features;

[0050] A dialogue sentence acquisition module is used to obtain sample renewal prompt dialogue sentences;

[0051] A feature extraction module, used to extract features from the sample renewal prompt dialogue sentences to obtain renewal objection features of the object;

[0052] An original renewal behavior prediction module, used to predict the renewal behavior of the object according to the renewal objection characteristics of the object, and obtain the object renewal category; the object renewal category is used to indicate renewal or non-renewal;

[0053] A screening module, used to screen the speech category according to the speech expression characteristics and the renewal objection characteristics of the object, to obtain a target category;

[0054] A construction module, configured to construct a model according to the target category, the object renewal category and preset object features to obtain a target renewal prediction model; the preset object features are features of the preset renewal object obtained in advance;

[0055] The target renewal behavior prediction module is used to predict the renewal behavior of the preset target renewal prompt dialogue sentence through the target renewal prediction model.

[0056] To achieve the above objectives, a third aspect of an embodiment of the present application proposes an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the method described in the first aspect is implemented.

[0057] To achieve the above-mentioned purpose, the fourth aspect of an embodiment of the present application proposes a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method described in the first aspect is implemented.

[0058] The renewal behavior prediction method, renewal behavior prediction device, electronic device and computer-readable storage medium proposed in the embodiments of the present application obtain insurance speech sentences, cluster the insurance speech sentences, classify the insurance speech sentences with similar semantics into one category, obtain speech expression features and speech categories of speech expression features, so as to construct labels for insurance speech sentences. Sample renewal prompt dialogue sentences are obtained to predict renewal behavior. In the prediction of renewal behavior, the object objection can reflect the renewal tendency, behavior pattern and potential demand of the renewal object. The sample renewal prompt dialogue sentences are feature extracted to obtain features related to the object objection and obtain the object renewal objection features. In order to obtain the real renewal label required for model construction, the renewal behavior is predicted according to the object renewal objection features to obtain the object renewal category. In order to accurately identify the renewal intention, the dialogue category is screened according to the speech expression features and the object renewal objection features to screen out the renewal intention that matches the object renewal objection features from the pre-built label system to obtain the target category. In order to improve the accuracy of renewal behavior prediction, the target category is used as a new feature in the model construction process. The model is constructed according to the target category, object renewal category and preset object features to obtain a model with better prediction performance, and a target renewal prediction model is obtained. The target renewal prediction model is used to predict the renewal behavior of the preset target renewal prompt dialogue sentence, so as to accurately identify the renewal intention implied in the target renewal prompt dialogue sentence, thereby improving the accuracy of renewal behavior prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 is a flow chart of a renewal behavior prediction method provided in an embodiment of the present application;

[0060] Figure 2 yes Figure 1 Flow chart of step S120 in FIG.

[0061] Figure 3 yes Figure 1 Flowchart of step S170 in FIG.

[0062] Figure 4 yes Figure 3 Flow chart of step S310 in FIG.

[0063] Figure 5 yes Figure 4 Flow chart of step S430 in FIG.

[0064] Figure 6 yes Figure 5 Flow chart of step S540 in FIG.

[0065] Figure 7 yes Figure 3 Flow chart of step S330 in FIG.

[0066] Figure 8 is a structural schematic diagram of a renewal behavior prediction device provided in an embodiment of the present application;

[0067] Fig. 9 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0068] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0069] It should be noted that, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0070] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0071] In the insurance industry, renewing premiums is an important part of maintaining the validity of policies and providing continuous protection. Insurance companies usually remind users to renew their policies by phone, and the phone recording data contains detailed interaction information between customers and insurance companies. In related technologies, keyword matching is used to extract keywords from phone recording data, and users' renewal behavior is predicted based on keywords. However, this method cannot accurately predict users' renewal behavior. For example, if the phrase "Are you not paying anymore?" appears in the phone recording data, the keyword matching method will match this phrase as non-renewal, resulting in a low accuracy in the prediction of renewal behavior.

[0072] Based on this, the embodiments of the present application provide a renewal behavior prediction method, a renewal behavior prediction device, an electronic device and a computer-readable storage medium, aiming to improve the accuracy of renewal behavior prediction.

[0073] The renewal behavior prediction method, renewal behavior prediction device, electronic device and computer-readable storage medium provided in the embodiments of the present application are specifically illustrated through the following embodiments. First, the renewal behavior prediction method in the embodiments of the present application is described.

[0074] The renewal behavior prediction method provided in the embodiment of the present application relates to the field of artificial intelligence technology. The renewal behavior prediction method provided in the embodiment of the present application can be applied to a terminal, can be applied to a server side, or can be software running in a terminal or a server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or can be configured as a server cluster or a distributed system composed of multiple physical servers, and can also be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements the renewal behavior prediction method, etc., but is not limited to the above forms.

[0075] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0076] Figure 1 It is an optional flow chart of the renewal behavior prediction method provided in the embodiment of the present application, which may include but is not limited to steps S110 to S180.

[0077] Step S110, obtaining insurance terminology sentences;

[0078] Step S120, clustering insurance speech sentences to obtain speech expression features and speech categories of the speech expression features;

[0079] Step S130, obtaining a sample renewal prompt dialogue statement;

[0080] Step S140, extracting features from the sample renewal prompt dialogue sentences to obtain renewal objection features;

[0081] Step S150, predicting the renewal behavior of the object according to the renewal objection characteristics, and obtaining the renewal category of the object; the renewal category of the object is used to indicate whether to renew or not renew;

[0082] Step S160, filtering the dialogue categories according to the expression features of the dialogue and the renewal objection features of the object, and obtaining the target category;

[0083] Step S170, constructing a model according to the target category, the object renewal category and the preset object features to obtain a target renewal prediction model; the preset object features are the features of the preset renewal object obtained in advance;

[0084] Step S180, predicting the renewal behavior of the preset target renewal prompt dialogue sentence through the target renewal prediction model.

[0085] In the steps S110 to S180 shown in the embodiment of the present application, a label system is pre-constructed to extract customer objection speech, and speech labels with similar meanings to customer objection speech are extracted from the label system to accurately identify renewal intention. The speech labels are used as new features to participate in model construction to improve the accuracy of the model in predicting renewal behavior.

[0086] In step S110 of some embodiments, all possible questions or expressions that may appear in the insurance scenario are obtained to obtain insurance language sentences. Insurance language sentences can be used to convey the user's demand for insurance products. Insurance language sentences can be "this insurance product is useless", "the price of this insurance product is too high", etc.

[0087] See also Figure 2 In some embodiments, step S120 may include but is not limited to steps S210 to S250:

[0088] Step S210, performing sentence vectorization processing on the insurance speech sentence to obtain the insurance speech vector;

[0089] Step S220, calculating the distance between the insurance speech vector and the preset cluster center to obtain the speech distance;

[0090] Step S230, clustering the insurance speech vectors according to the speech distance to obtain insurance speech clusters;

[0091] Step S240, average calculation is performed on the insurance speech clusters to obtain speech expression features;

[0092] Step S250, determining the speech category of the speech expression feature according to the insurance speech cluster.

[0093] In step S210 of some embodiments, the insurance sales talk sentences are subjected to sentence vectorization processing, converting the insurance sales talk sentences into a fixed-length vector representation, extracting semantic vectors that reflect the semantic and structural information of the sentences from the insurance sales talk sentences, and obtaining insurance sales talk vectors.

[0094] Specifically, the insurance sales talk sentences are tokenized to obtain insurance sales talk words. Stop words such as "de" (of), "le" (already) in the insurance sales talk words are removed to obtain words that can provide key information, resulting in initial talk words. The initial talk words are subjected to word feature extraction through a pre-trained word embedding model to obtain word semantic features. The word embedding model can be a word2vec model, a GloVe model, etc. The semantic features of all initial talk words are semantically encoded to obtain insurance sales talk vectors.

[0095] The semantic features of all initial talk words can be averaged to obtain insurance sales talk vectors. For example, if the number of initial talk words in the insurance sales talk sentence is C, and the semantic feature of the i-th initial talk word is represented as xi, then the insurance sales talk vector is represented as:

[0096]

[0097] It is also possible to obtain the word weights of the initial talk words, and perform weighted calculation on the semantic features of the initial talk words according to the word weights to obtain insurance sales talk vectors. The process of obtaining word weights is as follows: Obtain the frequency of occurrence of the initial talk words in the insurance sales talk sentences to get the term frequency. Take the total number of insurance sales talk sentences as the first quantity, and the number of insurance sales talk sentences in which the initial talk words appear as the second quantity, and calculate the inverse document frequency according to the first quantity and the second quantity. Multiply the term frequency and the inverse document frequency to obtain the word weights. The calculation formula of the term frequency is expressed as:

[0098]

[0099] Among them, TF represents the term frequency; t represents the number of times the initial talk word appears in the insurance sales talk sentence; d represents the total number of words in the insurance sales talk sentence.

[0100] The calculation formula of the inverse document frequency is expressed as:

[0101]

[0102] Among them, IDF represents the inverse document frequency; N represents the first quantity; DF represents the second quantity.

[0103] It is also possible to use an encoding network to perform feature encoding on the semantic features of all initial talk words to obtain insurance sales talk vectors. The encoding network can be a recurrent neural network, a Transformer model, etc.

[0104] In step S220 of some embodiments, K insurance speech vectors are randomly selected as K preset cluster centers. For each insurance speech vector, the Euclidean distance between the insurance speech vector and each preset cluster center is calculated to obtain the speech distance from the insurance speech vector to each preset cluster center. The larger the speech distance, the smaller the similarity between the insurance speech vector and the preset cluster center.

[0105] In step S230 of some embodiments, the preset cluster center with the smallest speech distance is selected as the original cluster center, and the insurance speech vector is clustered to the original cluster center to obtain the original speech cluster. The insurance speech vector in the original speech cluster is mean calculated to obtain the mean speech vector, and the original cluster center is updated according to the mean speech vector to obtain the reference cluster center. If the reference cluster center changes slightly for multiple consecutive times or the number of clustering times reaches the preset number threshold, the speech distance between the insurance speech vector and the reference cluster center is calculated, and the reference cluster center with the smallest speech distance is selected as the target cluster center, and the insurance speech vector is clustered to the target cluster center to obtain the insurance speech cluster. By clustering, insurance speech vectors with similar semantics can be classified into the same insurance speech cluster, for example, "no money to pay for the time being" and "a little tight on money recently" are classified into the same insurance speech cluster, and "this insurance product is useless" and "the price of this insurance product is too high" are classified into the same insurance speech cluster.

[0106] In step S240 of some embodiments, the insurance speech vectors in the insurance speech cluster are averaged to obtain speech expression features. For example, the insurance speech cluster includes three insurance speech vectors s1, s2 and s3, and the speech expression features can be expressed as (s1+s2+s3) / 3.

[0107] In step S250 of some embodiments, the category label of the insurance speech cluster is obtained to obtain the speech category of the speech expression feature. The speech category is used to indicate the speech intention expressed by the insurance speech sentence, such as financial difficulties, opinions on insurance products, etc. The speech expression features and the speech category of the speech expression features are recorded in a hash table to build an accurate speech label system.

[0108] Through the above steps S210 to S250, a speech tag system can be constructed to accurately and quickly identify the user's renewal intention based on the speech tag system, thereby improving the accuracy of renewal behavior prediction and performing real-time renewal behavior prediction.

[0109] In step S130 of some embodiments, the insurance company uses a telephone call to remind the renewal object to renew the premium, and the call recording data contains detailed interaction information between the renewal object and the insurance company. The audio file containing the call recording data is denoised to remove the background noise of the audio file to obtain the original audio file. The original audio file is edited to highlight the important audio content to obtain the target audio file. The audio content of the target audio file is converted into text through an automatic speech recognition system to obtain a sample renewal reminder dialogue sentence. The sample renewal reminder dialogue sentence is a sample for training the renewal prediction model, which includes the content of the insurance company reminding and guiding the renewal object to renew the premium and the renewal object's response to the renewal premium.

[0110] In step S140 of some embodiments, the large language model is trained by a large amount of text data and can capture complex semantic relationships and contextual information in the text. The embodiment of the present application uses the powerful semantic understanding ability of the large language model to input prompt instructions into the large language model, perform feature extraction on the sample renewal prompt dialogue sentence according to the prompt instructions, extract the objection content of the renewal object to the renewal premium in the call recording text, and obtain the object renewal objection feature. The object renewal objection feature can be the reason why the renewal object does not renew the premium, such as economic reasons, family reasons, dissatisfaction with the insurance product, other insurance product consultation, etc.

[0111] In step S150 of some embodiments, the large language model can process complex text data and semantic relationships, and perform deep semantic understanding and context perception on the renewal objection features through the large language model, and identify the key factors affecting the renewal behavior by analyzing the language pattern and sentiment tendency of the renewal object, so as to accurately predict the renewal behavior of the renewal object and obtain the object renewal category. The object renewal category is used to indicate whether the renewal object renews or does not renew.

[0112] In step S160 of some embodiments, the similarity between the speech expression feature and the object renewal objection feature is calculated, and the speech category corresponding to the speech expression feature with the greatest similarity is used as the target category. The object renewal objection feature can be matched with a suitable speech category label to identify the specific reason why the renewal object does not renew the premium, thereby accurately identifying the renewal intention hidden in the sample renewal prompt dialogue sentence.

[0113] See also Figure 3 In some embodiments, step S170 may include but is not limited to steps S310 to S360:

[0114] Step S310, constructing a decision tree according to the target category, the object renewal category and the preset object features to obtain a first decision tree;

[0115] Step S320, predicting the renewal behavior of the target category and the preset object features through the first decision tree to obtain a predicted renewal category;

[0116] Step S330, obtaining the renewal prediction weight of the first decision tree;

[0117] Step S340, calculating a reference sample gradient according to the object renewal category, the predicted renewal category, and the renewal prediction weight;

[0118] Step S350, constructing a decision tree according to the reference sample gradient, the target category, the object renewal category, and the preset object features to obtain a second decision tree;

[0119] Step S360: Determine a target renewal prediction model based on the first decision tree and the second decision tree.

[0120] In step S310 of some embodiments, the preset object features are pre-acquired features of the renewal object, which can affect the renewal behavior of the renewal object, such as the age of the renewal object, the renewal period, the insurance product to be renewed, the insurance company selected by the renewal object, the price of the insurance product, and the coverage, etc. The renewal behavior is affected by multiple factors such as the renewal period, the age of the renewal object, the age of the vehicle, the insurance company, etc. In order to capture the nonlinear dependencies and complex feature interaction effects among multiple factors and intuitively display the features that have an important impact on the renewal behavior, the embodiment of the present application adopts a decision tree as the basic model for predicting the renewal behavior.

[0121] The embodiment of the present application constructs a new feature, namely the target category, through a sample renewal prompt dialogue statement. The target category indicates the objection reason for the renewal object's non-renewal of the premium and the needs of the renewal object. The target category is related to the renewal behavior of the renewal object. In order to improve the accuracy of the renewal behavior prediction, the target category is used as a new feature to participate in the training process of the renewal behavior prediction model. Specifically, the target category and the preset object features are used as samples, the object renewal category is used as the true label of the sample, and a first decision tree is constructed based on the sample and the true label. A single decision tree is prone to overfitting, resulting in the model being unable to accurately predict the renewal behavior of unknown samples. In order to improve the generalization ability of the model, the embodiment of the present application uses multiple decision trees to learn different features and patterns from the samples to provide comprehensive and accurate renewal behavior predictions.

[0122] In step S320 of some embodiments, the target category and the preset object features are input into the first decision tree to predict the renewal behavior, and obtain the predicted renewal category. The predicted renewal category is used to indicate whether the renewal object renews or not.

[0123] In step S330 of some embodiments, in order to control the contribution of the decision tree to the prediction result of the renewal behavior, pay more attention to the decision tree that has a significant contribution to the prediction result of the renewal behavior during the model training process, balance the contribution of each decision tree, rather than making a single decision tree too powerful to dominate the prediction of the entire model, a weight is set for each decision tree. The weight of the first decision tree is obtained to obtain the renewal prediction weight. The renewal prediction weight is used to reflect the contribution of the first decision tree to the prediction of the renewal behavior. The greater the renewal prediction weight, the greater the contribution of the first decision tree.

[0124] In step S340 of some embodiments, multiple samples are used in the construction process of the first decision tree, each sample includes a target category, an object renewal category, and a preset object feature. The object renewal category has an object renewal value. If the object renewal value is 1, the object renewal category is renewal; if the object renewal value is 0, the object renewal category is not renewed. The object renewal values ​​of all samples are averaged to obtain a renewal mean. An initial renewal label is determined based on the renewal mean. If the renewal mean is greater than a preset renewal threshold, the initial renewal label is determined to be renewal based on the renewal mean. The preset renewal threshold may be 0.5. If the renewal mean is less than or equal to the preset renewal threshold, the initial renewal label is determined to be not renewed based on the renewal mean.

[0125] Multiply the renewal prediction weight by the predicted renewal category, and add the multiplication result to the initial renewal label to obtain the pseudo renewal category. Calculate the gradient of the first decision tree based on the pseudo renewal category and the object renewal category to obtain the reference sample gradient. The formula for gradient calculation is expressed as:

[0126]

[0127] Where g represents the reference sample gradient; represents the pseudo renewal category; y represents the object renewal category.

[0128] In step S350 of some embodiments, in order to improve the accuracy of renewal behavior prediction, it is necessary to pay attention to the samples for which the first decision tree fails to make a good renewal prediction. Referring to step S310, the reference sample gradient is used as a new feature, and a decision tree is constructed according to the reference sample gradient, the target category, the object renewal category, and the preset object feature to fit the reference sample gradient, correct the prediction error generated by the first decision tree, and obtain the second decision tree. It should be noted that the reference sample gradient, the target category, and the preset object feature are all sample features, and the object renewal category is the true label of the sample feature.

[0129] In step S360 of some embodiments, the first decision tree and the second decision tree are used as target renewal prediction models.

[0130] In the above steps S310 to S360, different feature representations can be learned from different perspectives through multiple decision trees, and multiple decision trees can be integrated into a target renewal prediction model to combine the prediction results of multiple decision trees, thereby reducing prediction errors and improving the accuracy of renewal behavior prediction.

[0131] See also Figure 4 In some embodiments, step S310 may include but is not limited to steps S410 to S460:

[0132] Step S410, performing feature screening on the target category and the preset object features to obtain original features;

[0133] Step S420, discretizing the original features to obtain discrete sub-features;

[0134] Step S430, calculating the feature gain of the discrete sub-feature according to the object renewal category;

[0135] Step S440, selecting the discrete sub-feature with the largest feature gain as a reference sub-feature;

[0136] Step S450, constructing nodes according to the reference sub-features to obtain decision nodes;

[0137] Step S460: construct a first decision tree according to the decision nodes.

[0138] In step S410 of some embodiments, the characteristic attributes of the target category and the preset object feature are obtained, the Gini impurity of the characteristic attributes is calculated, and the characteristic attribute with the largest Gini impurity is selected as the original feature. The target category and the preset object feature are both the values ​​of the characteristic attribute. For example, if the characteristic attribute of the target category is speech skills, then the target category is financial difficulties, the characteristic attribute of the preset object feature is age, and the preset object feature is 18.

[0139] In step S420 of some embodiments, if the original feature is a continuous feature, the feature value range and discrete interval of the original feature are obtained, and the feature value range of the original feature is discretized according to the discrete interval to obtain discrete sub-features, and the feature value range of the discrete sub-features is within the feature value range of the original feature. For example, the original feature is age, and its feature value range is 0-100, and the discrete interval is 20. The original feature can be discretized into 5 discrete sub-features according to the discrete interval, and each discrete sub-feature has a different value range, which is divided into 0-20, 20-40, 40-60, 60-80 and 80-100. If the original feature is a discrete feature, there is no need to discretize the original feature, and the node is directly constructed according to the original feature to obtain a decision node.

[0140] In step S430 of some embodiments, in order to evaluate the feature importance of the discrete sub-feature, the feature gain of the discrete sub-feature is calculated according to the object renewal category. The larger the feature gain, the more important the discrete sub-feature is in predicting the renewal behavior.

[0141] In step S440 of some embodiments, the discrete sub-feature with the largest feature gain is selected as the reference sub-feature to select features that play an important role in the model prediction performance, thereby improving the accuracy of renewal behavior prediction.

[0142] In step S450 of some embodiments, a tree node is created according to the reference sub-feature to obtain a decision node.

[0143] In step S460 of some embodiments, the above steps S410 to S450 are repeatedly performed to construct child nodes of the decision node until an iteration stop condition is reached to obtain a first decision tree. The iteration stop condition may be that the depth of the decision tree reaches a preset depth threshold, all samples in the decision node belong to the same category, or the number of samples in the decision node is less than a preset minimum number of samples.

[0144] In the above steps S410 to S460, a decision tree is constructed to capture the complex nonlinear dependencies between features and the correlation between features and renewal behavior, so as to make accurate predictions on renewal behavior.

[0145] See also Figure 5 In some embodiments, step S430 may include but is not limited to steps S510 to S540:

[0146] Step S510, determining a reference renewal category according to the object renewal category;

[0147] Step S520, screening the object renewal category according to the discrete sub-features to obtain candidate renewal categories and the number of candidate renewal categories;

[0148] Step S530, determining an original sample gradient according to the reference renewal category, the candidate renewal category, and the number of the candidate renewal category;

[0149] Step S540, calculating the feature gain of the discrete sub-feature according to the original sample gradient.

[0150] In step S510 of some embodiments, referring to step S340, the object renewal values ​​of the object renewal categories of all samples are averaged to obtain the renewal average, and the reference renewal category is determined according to the renewal average.

[0151] In step S520 of some embodiments, the target category, the object renewal category, and the preset object features are used as original samples. In order to improve the speed of decision tree construction, the original samples are screened according to the discrete sub-features to obtain the target samples, and the object renewal category of the target samples is used as the candidate renewal category, and the number of target samples is used as the number of categories of the candidate renewal category. For example, the discrete sub-feature is age 20-40, and the original samples that meet the age 20-40 are screened according to the discrete sub-features to obtain the target samples.

[0152] In step S530 of some embodiments, a difference calculation is performed based on the reference renewal category and the candidate renewal category to obtain a sample difference value. The sample difference value and the number of candidate renewal categories are used as the original sample gradient.

[0153] In step S540 of some embodiments, the feature gain of the discrete sub-feature is calculated according to the sample difference value and the number of candidate renewal categories to evaluate the feature importance of each discrete sub-feature.

[0154] Through the above steps S510 to S540, the feature importance of different features can be evaluated, so that features that are important to the model prediction performance are selected based on the feature importance, thereby improving the accuracy of renewal behavior prediction.

[0155] See also Figure 6 In some embodiments, step S540 may include but is not limited to steps S610 to S640:

[0156] Step S610, performing feature splitting on the discrete sub-feature to obtain a first sub-feature and a second sub-feature;

[0157] Step S620, calculating a first sub-gain of a first sub-feature according to an original sample gradient;

[0158] Step S630, calculating a second sub-gain of the second sub-feature according to the original sample gradient;

[0159] Step S640: summing the first sub-gain and the second sub-gain to obtain a feature gain of the discrete sub-feature.

[0160] In step S610 of some embodiments, the target category, object renewal category and preset object features are taken as original samples, the original samples with feature values ​​less than or equal to the discrete sub-features are taken as the first sub-features, and the original samples with feature values ​​greater than the discrete sub-features are taken as the second sub-features.

[0161] In step S620 of some embodiments, a sample difference value and the number of candidate renewal categories are obtained from the original sample gradient according to the first sub-feature, the sample difference values ​​are summed to obtain a first total gradient, the number of candidate renewal categories is summed to obtain a first total number, the first total gradient is squared, and the squared result is divided by the first total number to obtain a first sub-gain.

[0162] In step S630 of some embodiments, a sample difference value and the number of candidate renewal categories are obtained from the original sample gradient according to the second sub-feature, the sample difference values ​​are summed to obtain a second total gradient, the number of candidate renewal categories is summed to obtain a second total number, the second total gradient is squared, and the squared result is divided by the second total number to obtain a second sub-gain.

[0163] In step S640 of some embodiments, the first sub-gain and the second sub-gain are added to obtain a feature gain of the discrete sub-feature.

[0164] Through the above steps S610 to S640, the feature gain of the discrete sub-feature can be obtained, so as to screen the discrete sub-feature based on the feature gain and construct a decision tree.

[0165] See also Figure 7 In some embodiments, step S330 may include but is not limited to steps S710 to S730:

[0166] Step S710, performing loss calculation according to the target renewal category and the predicted renewal category to obtain target loss data;

[0167] Step S720, determining first-order moment data and second-order moment data according to the target loss data;

[0168] Step S730, calculating the renewal prediction weight of the first decision tree according to the first-order moment data and the second-order moment data.

[0169] In step S710 of some embodiments, based on the cross entropy loss function, a cross entropy loss calculation is performed on the object renewal category and the predicted renewal category to obtain target loss data.

[0170] In step S720 of some embodiments, first-order moment data and second-order moment data are calculated according to the target loss data, the first-order moment data is used to indicate the gradient direction, and the second-order moment data is used to indicate the gradient change rate. The calculation method of the first moment data is expressed as:

[0171] m1=β1*m01+(1-β1)*L,

[0172] m2=β2*m02+(1-β2)*L 2 ,

[0173] Among them, m1 represents the first-order moment data; m2 represents the second-order moment data; β1 and β2 are both attenuation coefficients; m01 and m02 represent the initial value of the first-order moment and the initial value of the second-order moment respectively; L represents the target loss data.

[0174] In step S730 of some embodiments, the square root of the second-order moment data is obtained, and the first-order moment data is divided by the square root of the second-order moment data to obtain the renewal prediction weight of the first decision tree.

[0175] Through the above steps S710 to S730, the weight of the decision tree can be obtained, so as to balance the contribution of each decision tree in the prediction of renewal behavior based on the weight of the decision tree and improve the generalization ability of the model.

[0176] In step S180 of some embodiments, after the training of the target renewal prediction model is completed, the target renewal prompt dialogue sentence is obtained, and the target renewal prompt dialogue sentence is the call recording text obtained in the model reasoning stage. The target renewal prediction model includes a first decision tree and a second decision tree. The renewal behavior prediction of the target renewal prompt dialogue sentence is performed through the first decision tree to determine the probability of the renewal object renewing the premium and obtain the first renewal probability. The renewal behavior prediction of the target renewal prompt dialogue sentence is performed through the second decision tree to determine the probability of the renewal object renewing the premium and obtain the second renewal probability. The renewal prediction weight of the first decision tree is multiplied by the first renewal probability, and the tree weight of the second decision tree is obtained by referring to steps S710 to S730. The tree weight is multiplied by the second renewal probability, and the two multiplication results are added to obtain the target renewal probability. If the target renewal probability is greater than the preset probability threshold, renewal is indicated. If the target renewal probability is less than or equal to the preset probability threshold, non-renewal is indicated.

[0177] See also Figure 8 The embodiment of the present application further provides a renewal behavior prediction device, which can implement the above-mentioned renewal behavior prediction method, and the renewal behavior prediction device includes:

[0178] A speech sentence acquisition module 810 acquires insurance speech sentences;

[0179] A clustering module 820 is used to cluster insurance speech sentences to obtain speech expression features and speech categories of the speech expression features;

[0180] A dialogue statement acquisition module 830 is used to acquire a sample renewal prompt dialogue statement;

[0181] A feature extraction module 840 is used to extract features from the sample renewal prompt dialogue sentences to obtain the renewal objection features of the object;

[0182] The original renewal behavior prediction module 850 is used to predict the renewal behavior according to the renewal objection characteristics of the object, and obtain the renewal category of the object; the renewal category of the object is used to indicate renewal or non-renewal;

[0183] A screening module 860 is used to screen the dialogue category according to the expression characteristics of the dialogue and the object renewal objection characteristics to obtain the target category;

[0184] A construction module 870 is used to construct a model according to the target category, the object renewal category and the preset object features to obtain a target renewal prediction model; the preset object features are the features of the preset renewal object obtained in advance;

[0185] The target renewal behavior prediction module 880 is used to predict the renewal behavior of the preset target renewal prompt dialogue sentence through the target renewal prediction model.

[0186] The specific implementation of the renewal behavior prediction device is basically the same as the specific implementation of the renewal behavior prediction method described above, and will not be repeated here.

[0187] The embodiment of the present application also provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above-mentioned renewal behavior prediction method when executing the computer program. The electronic device can be any smart terminal including a tablet computer, a car computer, etc.

[0188] See also Fig. 9 , Fig. 9 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0189] The processor 910 may be implemented by a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application.

[0190] The memory 920 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 920 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 920, and the processor 910 calls and executes the renewal behavior prediction method of the embodiment of this application;

[0191] Input / output interface 930, used to implement information input and output;

[0192] Communication interface 940, used to realize communication interaction between the device and other devices, which can be realized through wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WI FI, Bluetooth, etc.);

[0193] bus 950 , which transmits information between the various components of the device (e.g., processor 910 , memory 920 , input / output interface 930 , and communication interface 940 );

[0194] The processor 910 , the memory 920 , the input / output interface 930 , and the communication interface 940 are connected to each other in communication within the device via a bus 950 .

[0195] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the above-mentioned renewal behavior prediction method is implemented.

[0196] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0197] The renewal behavior prediction method, renewal behavior prediction device, electronic device, and computer storage medium provided in the embodiments of the present application extract customer objection speech by pre-constructing a label system, and extracting speech labels with similar meanings to customer objection speech from the label system to accurately identify renewal intention. The speech labels are used as new features to participate in model construction to improve the accuracy of the model in predicting renewal behavior.

[0198] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0199] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0200] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0201] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0202] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0203] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0204] In the several embodiments provided in the present application, 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 above 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.

[0205] The units described above 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.

[0206] In addition, each functional unit in each embodiment of the present application 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. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0207] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0208] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A renewal behavior prediction method, characterized in that: The method comprises: Get insurance jargon phrases; Clustering the insurance speech sentences to obtain speech expression features and speech categories of the speech expression features; Get sample renewal reminder dialogue statements; Extract features from the sample renewal prompt dialogue sentences to obtain renewal objection features of the object; Predicting the renewal behavior of the object according to the renewal objection characteristics of the object, and obtaining the renewal category of the object; the renewal category of the object is used to indicate renewal or non-renewal; The speech category is screened according to the speech expression characteristics and the renewal objection characteristics of the object to obtain a target category; A model is constructed according to the target category, the object renewal category and preset object features to obtain a target renewal prediction model; the preset object features are features of the preset renewal object obtained in advance; The target renewal prediction model is used to predict the renewal behavior of the preset target renewal prompt dialogue sentence.

2. The method according to claim 1, characterized in that The model is constructed according to the target category, the object renewal category and the preset object characteristics to obtain a target renewal prediction model, including: Constructing a decision tree according to the target category, the object renewal category, and the preset object features to obtain a first decision tree; Predicting the renewal behavior of the target category and the preset object features by using the first decision tree to obtain a predicted renewal category; Obtaining the renewal prediction weight of the first decision tree; Calculate a reference sample gradient according to the object renewal category, the predicted renewal category, and the renewal prediction weight; Constructing a decision tree according to the reference sample gradient, the target category, the object renewal category, and the preset object feature to obtain a second decision tree; The target renewal prediction model is determined according to the first decision tree and the second decision tree.

3. The method according to claim 2, characterized in that The step of constructing a decision tree according to the target category, the object renewal category, and the preset object features to obtain a first decision tree includes: Performing feature screening on the target category and the preset object features to obtain original features; Discretizing the original features to obtain discrete sub-features; Calculating a feature gain of the discrete sub-feature according to the object renewal category; Selecting the discrete sub-feature with the largest feature gain as a reference sub-feature; Node construction is performed according to the reference sub-features to obtain a decision node; The first decision tree is constructed according to the decision nodes.

4. The method according to claim 3, characterized in that The calculating the feature gain of the discrete sub-feature according to the object renewal category includes: Determine a reference renewal category according to the renewal category of the object; Screening the renewal category of the object according to the discrete sub-features to obtain candidate renewal categories and the number of the candidate renewal categories; determining an original sample gradient according to the reference renewal category, the candidate renewal category, and the number of categories of the candidate renewal category; The feature gain of the discrete sub-feature is calculated according to the original sample gradient.

5. The method according to claim 4, characterized in that The calculating the feature gain of the discrete sub-feature according to the original sample gradient includes: Performing feature splitting on the discrete sub-feature to obtain a first sub-feature and a second sub-feature; Calculating a first sub-gain of the first sub-feature according to the original sample gradient; Calculating a second sub-gain of the second sub-feature according to the original sample gradient; The first sub-gain and the second sub-gain are summed to obtain a feature gain of the discrete sub-feature.

6. The method according to claim 2, characterized in that The obtaining the renewal prediction weight of the first decision tree includes: Calculate the loss according to the target renewal category and the predicted renewal category to obtain target loss data; Determine first-order moment data and second-order moment data according to the target loss data; The renewal prediction weight of the first decision tree is calculated based on the first-order moment data and the second-order moment data.

7. The method according to any one of claims 1 to 6, characterized in that: The clustering of the insurance speech sentences to obtain speech expression features and speech categories of the speech expression features includes: Performing sentence vectorization processing on the insurance speech phrase to obtain an insurance speech phrase vector; Calculating the distance between the insurance speech vector and a preset cluster center to obtain a speech distance; Clustering the insurance speech vectors according to the speech distance to obtain insurance speech clusters; Performing average calculation on the insurance speech clusters to obtain the speech expression features; Determine the speech category of the speech expression feature based on the insurance speech cluster.

8. A renewal behavior prediction device, characterized in that: The device comprises: A speech sentence acquisition module, which acquires insurance speech sentences; A clustering module, used for clustering the insurance speech sentences to obtain speech expression features and speech categories of the speech expression features; A dialogue sentence acquisition module is used to obtain sample renewal prompt dialogue sentences; A feature extraction module, used to extract features from the sample renewal prompt dialogue sentences to obtain renewal objection features of the object; An original renewal behavior prediction module, used to predict the renewal behavior of the object according to the renewal objection characteristics of the object, and obtain the object renewal category; the object renewal category is used to indicate renewal or non-renewal; A screening module, used to screen the speech category according to the speech expression characteristics and the renewal objection characteristics of the object, to obtain a target category; A construction module, configured to construct a model according to the target category, the object renewal category and preset object features to obtain a target renewal prediction model; the preset object features are features of the preset renewal object obtained in advance; The target renewal behavior prediction module is used to predict the renewal behavior of the preset target renewal prompt dialogue sentence through the target renewal prediction model.

9. An electronic device, characterized in that: The electronic device comprises a memory and a processor, the memory stores a computer program, and the processor implements the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images