CN113988190A - Customer intention analysis method, apparatus, device and storage medium - Google Patents
Customer intention analysis method, apparatus, device and storage medium Download PDFInfo
- Publication number
- CN113988190A CN113988190A CN202111273716.5A CN202111273716A CN113988190A CN 113988190 A CN113988190 A CN 113988190A CN 202111273716 A CN202111273716 A CN 202111273716A CN 113988190 A CN113988190 A CN 113988190A
- Authority
- CN
- China
- Prior art keywords
- intention
- client
- data
- matching
- preset
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to the field of artificial intelligence, and discloses a customer intention analysis method, a customer intention analysis device, customer intention analysis equipment and a storage medium, which are used for improving the efficiency of customer intention analysis. The customer intention analysis method comprises the following steps: preprocessing the historical data of the client, classifying the preprocessed historical data based on a preset decision tree algorithm to obtain a willingness grading standard; configuring an intention rule based on the flow conversational template to obtain a client intention rule, receiving voice interaction data returned by the artificial intelligent voice robot, and comparing the voice interaction data with the client intention rule to obtain a voice comparison result; extracting off-line interactive data in the voice comparison result, and matching the off-line interactive data with a preset customer intention label to obtain a customer intention matching result; and classifying the voice comparison result and the matching result of the customer intention degree to obtain a customer intention analysis result. In addition, the invention also relates to a block chain technology, and the result of the customer intention analysis can be stored in the block chain.
Description
Technical Field
The present invention relates to the field of similarity matching, and in particular, to a method, an apparatus, a device, and a storage medium for analyzing a client intention.
Background
The client intention analysis is mainly used for training a client intention analysis model by learning all voice data after the current artificial intelligence AI outbound call, the outbound call condition, the basic information, the credit card use condition and the like corresponding to the client so as to excavate the client with the handling intention and improve the handling rate.
The traditional client intention analysis method comprises two methods, namely, manually analyzing an interactive text of an AI and a client by hearing back an AI outbound record, extracting keywords and intention in client interaction, and then tracking the intention client in an offline data acquisition mode; secondly, when an AI conversation process is designed, the intention and nodes of the intended customers are set in advance, and if the customers trigger the preset intention nodes in the actual interaction, the part of the customers are defined as the intended customers. However, the analysis process in the above two ways is complex and time consuming, and requires analysis of the full amount of interaction data, resulting in inefficient analysis of the customer's intent.
Disclosure of Invention
The invention provides a customer intention analysis method, a device, equipment and a storage medium, which are used for classifying pre-processed historical data based on a preset decision tree algorithm to obtain an intention grading standard, comparing voice interaction data with customer intention rules to obtain a voice comparison result, extracting off-line interaction data in the voice comparison result, matching the off-line interaction data with a preset customer intention degree label to obtain a customer intention matching result, classifying the voice comparison result and the customer intention degree matching result respectively based on the intention grading standard to obtain a customer intention analysis result, and improving the efficiency of customer intention analysis.
The first aspect of the present invention provides a customer intention analysis method, including: acquiring historical handling data of a client, preprocessing the historical handling data of the client to obtain preprocessed historical data, and classifying the preprocessed historical data based on a preset decision tree algorithm to obtain a willingness grading standard; configuring an intention rule based on a preset flow dialect template to obtain a client intention rule, receiving voice interaction data returned by an artificial intelligent voice robot, and comparing the voice interaction data with the client intention rule to obtain a voice comparison result; extracting off-line interactive data in the voice comparison result, and matching the off-line interactive data with a preset customer intention degree label to obtain a customer intention matching result; and classifying the voice comparison result and the client intention degree matching result respectively based on the intention grading standard to obtain a client intention analysis result.
Optionally, in a first implementation manner of the first aspect of the present invention, the obtaining of the historical transaction data of the client, preprocessing the historical transaction data of the client to obtain preprocessed historical data, and classifying the preprocessed historical data based on a preset decision tree algorithm to obtain the willingness grading criterion includes: acquiring historical transaction data of a client, and performing missing value completion, abnormal value filtration and repeated value filtration on the historical transaction data of the client to obtain preprocessed historical data; calling a preset decision tree algorithm, and performing traversal processing on the preprocessed historical data to obtain a target decision tree, wherein the target decision tree comprises a plurality of leaf nodes; acquiring a service handling rate corresponding to each leaf node in the target decision tree, and sequencing each leaf node according to the sequence of the service handling rates from large to small to obtain a leaf node sequencing result; and classifying the leaf node sequencing results according to a preset customer quantity grading standard to obtain a wish grading standard.
Optionally, in a second implementation manner of the first aspect of the present invention, the invoking a preset decision tree algorithm to perform traversal processing on the preprocessed historical data to obtain a target decision tree, where the target decision tree includes a plurality of leaf nodes, and the method includes: traversing the preprocessed historical data to obtain a traversal result, and classifying the traversal result according to preset guest group characteristics to obtain an initial decision tree; and pruning the initial decision tree to obtain a target decision tree, wherein the target decision tree comprises a plurality of leaf nodes, and each leaf node corresponds to a guest group characteristic.
Optionally, in a third implementation manner of the first aspect of the present invention, the configuring an intention rule based on a preset workflow technology template to obtain a customer intention rule, receiving voice interaction data returned by an artificial intelligent voice robot, and comparing the voice interaction data with the customer intention rule to obtain a voice comparison result includes: acquiring a process technology template, and configuring intention rules based on a plurality of rule categories in the process technology template to obtain client intention rules; receiving voice interaction data returned by the artificial intelligent voice robot, and acquiring a first matching degree between the voice interaction data and the client intention rule; and calling a preset comparison algorithm to judge whether the first matching degree is greater than a preset first matching threshold value or not, and obtaining a voice comparison result.
Optionally, in a fourth implementation manner of the first aspect of the present invention, the extracting offline interaction data in the voice comparison result, and matching the offline interaction data with a preset customer intention degree tag to obtain a customer intention matching result includes: extracting voice interaction data with a first matching degree smaller than or equal to a preset first matching threshold value in the voice comparison result to obtain offline interaction data, wherein the first matching degree is the matching degree of the voice interaction data and the customer intention rule; and acquiring a second matching degree, calling a preset similarity matching algorithm, and judging whether the second matching degree is greater than a preset second matching threshold value to obtain a customer intention matching result, wherein the second matching degree is the matching degree of the offline interactive data and a preset customer intention label.
Optionally, in a fifth implementation manner of the first aspect of the present invention, the classifying the voice comparison result and the client intention degree matching result based on the intention grading criterion, respectively, and obtaining a client intention analysis result includes: extracting first client data from the voice comparison result, and dividing the first client data into preset first echelon willingness grading based on the willingness grading standard to obtain a first classification result, wherein the first client data are voice interaction data with a first matching degree greater than a first matching threshold; extracting second client data from the client intention degree matching result, and dividing the second client data into preset second echelon intention grades based on the intention grading standard to obtain a second classification result, wherein the second client data are offline interaction data of which the second matching degree is greater than a second matching threshold value in the client intention degree matching result; determining the first classification result and the second classification result as a customer intention analysis result.
Optionally, in a sixth implementation manner of the first aspect of the present invention, before the obtaining of the historical transaction data of the client, preprocessing the historical transaction data of the client to obtain preprocessed historical data, and classifying the preprocessed historical data based on a preset decision tree algorithm to obtain a willingness grading standard, the method for analyzing the willingness of the client further includes: the method comprises the steps of obtaining data to be tested of a customer, and sending the data to be tested of the customer to an artificial intelligent voice robot, so that the artificial intelligent voice robot carries out voice interaction, and voice interaction data are obtained.
A second aspect of the present invention provides a customer intention analysis device including: the system comprises an acquisition module, a classification module and a classification module, wherein the acquisition module is used for acquiring historical handling data of a client, preprocessing the historical handling data of the client to obtain preprocessed historical data, and classifying the preprocessed historical data based on a preset decision tree algorithm to obtain a willingness grading standard; the comparison module is used for configuring the intention rule based on a preset flow dialect template to obtain a client intention rule, receiving voice interaction data returned by the artificial intelligent voice robot, and comparing the voice interaction data with the client intention rule to obtain a voice comparison result; the matching module is used for extracting the offline interaction data in the voice comparison result and matching the offline interaction data with a preset client intention label to obtain a client intention matching result; and the classification module is used for classifying the voice comparison result and the client intention degree matching result respectively based on the intention grading standard to obtain a client intention analysis result.
Optionally, in a first implementation manner of the second aspect of the present invention, the obtaining module includes: the system comprises a preprocessing unit, a data processing unit and a data processing unit, wherein the preprocessing unit is used for acquiring historical transaction data of a client, and performing missing value completion, abnormal value filtration and repeated value filtration on the historical transaction data of the client to obtain preprocessed historical data; the traversal unit is used for calling a preset decision tree algorithm and performing traversal processing on the preprocessed historical data to obtain a target decision tree, and the target decision tree comprises a plurality of leaf nodes; the sorting unit is used for acquiring the service transaction rate corresponding to each leaf node in the target decision tree, and sorting each leaf node according to the sequence of the service transaction rates from large to small to obtain a leaf node sorting result; and the classification unit is used for classifying the leaf node sequencing results according to a preset customer quantity grading standard to obtain a willingness grading standard.
Optionally, in a second implementation manner of the second aspect of the present invention, the traversal unit is specifically configured to: traversing the preprocessed historical data to obtain a traversal result, and classifying the traversal result according to preset guest group characteristics to obtain an initial decision tree; and pruning the initial decision tree to obtain a target decision tree, wherein the target decision tree comprises a plurality of leaf nodes, and each leaf node corresponds to a guest group characteristic.
Optionally, in a third implementation manner of the second aspect of the present invention, the comparing module includes: the configuration unit is used for acquiring a flow language template, configuring intention rules based on a plurality of rule categories in the flow language template and obtaining client intention rules; the receiving unit is used for receiving voice interaction data returned by the artificial intelligent voice robot and acquiring a first matching degree between the voice interaction data and the client intention rule; and the first judging unit is used for calling a preset comparison algorithm to judge whether the first matching degree is greater than a preset first matching threshold value or not so as to obtain a voice comparison result.
Optionally, in a fourth implementation manner of the second aspect of the present invention, the matching module includes: the extracting unit is used for extracting voice interaction data with a first matching degree smaller than or equal to a preset first matching threshold value in the voice comparison result to obtain offline interaction data, wherein the first matching degree is the matching degree of the voice interaction data and the customer intention rule; and the second judging unit is used for acquiring a second matching degree, calling a preset similarity matching algorithm, and judging whether the second matching degree is greater than a preset second matching threshold value to obtain a customer intention matching result, wherein the second matching degree is the matching degree of the offline interactive data and a preset customer intention label.
Optionally, in a fifth implementation manner of the second aspect of the present invention, the classification module includes: the first classification unit is used for extracting first client data from the voice comparison result, classifying the first client data into a preset first echelon willingness classification based on the willingness classification standard to obtain a first classification result, wherein the first client data are voice interaction data with a first matching degree larger than a first matching threshold; the second dividing unit is used for extracting second client data from the client intention degree matching result, dividing the second client data into preset second echelon intention grades based on the intention grading standard to obtain a second classification result, wherein the second client data are offline interaction data of which the second matching degree is greater than a second matching threshold value in the client intention degree matching result; a determining unit, configured to determine the first classification result and the second classification result as a customer intention analysis result.
Optionally, in a sixth implementation manner of the second aspect of the present invention, before the obtaining module, the customer intention analyzing apparatus further includes a voice interaction module, including: the method comprises the steps of obtaining data to be tested of a customer, and sending the data to be tested of the customer to an artificial intelligent voice robot, so that the artificial intelligent voice robot carries out voice interaction, and voice interaction data are obtained.
A third aspect of the present invention provides a client intention analyzing apparatus including: a memory and at least one processor, the memory having stored therein a computer program; the at least one processor calls the computer program in the memory to cause the customer intention analysis device to perform the customer intention analysis method described above.
A fourth aspect of the present invention provides a computer-readable storage medium having stored therein a computer program which, when run on a computer, causes the computer to execute the above-described client intention analysis method.
According to the technical scheme, historical transaction data of a client are obtained, the historical transaction data of the client are preprocessed to obtain preprocessed historical data, and the preprocessed historical data are classified based on a preset decision tree algorithm to obtain a willingness grading standard; configuring an intention rule based on a preset flow dialect template to obtain a client intention rule, receiving voice interaction data returned by an artificial intelligent voice robot, and comparing the voice interaction data with the client intention rule to obtain a voice comparison result; extracting off-line interactive data in the voice comparison result, and matching the off-line interactive data with a preset customer intention degree label to obtain a customer intention matching result; and classifying the voice comparison result and the client intention degree matching result respectively based on the intention grading standard to obtain a client intention analysis result. In the embodiment of the invention, the preprocessed historical data are classified based on a preset decision tree algorithm to obtain a wish grading standard, the voice interaction data are compared with the client intention rule to obtain a voice comparison result, the offline interaction data in the voice comparison result are extracted, the offline interaction data are matched with the preset client intention degree label to obtain a client intention matching result, the voice comparison result and the client intention degree matching result are classified respectively based on the wish grading standard to obtain a client intention analysis result, and communication nodes and keywords can be extracted effectively aiming at the missing clients in the interaction process to analyze the purchase intention of the clients to products, so that the efficiency of analyzing the client intention is improved.
Drawings
FIG. 1 is a schematic diagram of an embodiment of a method for analyzing a client intention according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of another embodiment of a method for analyzing a client intention according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of an embodiment of a client intention analyzing apparatus according to the present invention;
FIG. 4 is a schematic diagram of another embodiment of a client intention analysis apparatus according to the embodiment of the invention;
fig. 5 is a schematic diagram of an embodiment of a client intention analysis device in the embodiment of the present invention.
Detailed Description
The embodiment of the invention provides a customer intention analysis method, a device, equipment and a storage medium, which are used for classifying pre-processed historical data based on a preset decision tree algorithm to obtain an intention grading standard, comparing voice interaction data with a customer intention rule to obtain a voice comparison result, extracting off-line interaction data in the voice comparison result, matching the off-line interaction data with a preset customer intention degree label to obtain a customer intention matching result, classifying the voice comparison result and the customer intention degree matching result respectively based on the intention grading standard to obtain a customer intention analysis result, and improving the efficiency of customer intention analysis.
The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that the embodiments described herein may be practiced otherwise than as specifically illustrated or described herein. Furthermore, the terms "comprises," "comprising," or "having," and any variations thereof, are intended to cover non-exclusive inclusions, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
For convenience of understanding, a specific flow of an embodiment of the present invention is described below, and referring to fig. 1, an embodiment of a method for analyzing a customer intention according to an embodiment of the present invention includes:
101. the method comprises the steps of obtaining historical handling data of a client, preprocessing the historical handling data of the client to obtain preprocessed historical data, classifying the preprocessed historical data based on a preset decision tree algorithm to obtain a willingness grading standard.
It is to be understood that the execution subject of the present invention may be a client intention analysis device, and may also be a terminal or a server, which is not limited herein. The embodiment of the present invention is described by taking a server as an execution subject. The server may be an independent server, or may be a cloud server that provides basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a Content Delivery Network (CDN), and a big data and artificial intelligence platform.
The embodiment of the application can acquire and process related data based on an artificial intelligence technology. Among them, Artificial Intelligence (AI) is a theory, method, technique and application system that simulates, extends and expands human Intelligence using a digital computer or a machine controlled by a digital computer, senses the environment, acquires knowledge and uses the knowledge to obtain the best result.
The artificial intelligence infrastructure generally includes technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and the like.
The server acquires historical transaction data of the client, preprocesses the historical transaction data of the client to obtain preprocessed historical data, and classifies the preprocessed historical data based on a preset decision tree algorithm to obtain a willingness grading standard. The server acquires the historical client transaction data, the historical client transaction data are acquired through the crawler, the historical client transaction data are authorized by the user, after the historical client transaction data are acquired, the historical client transaction data are preprocessed, and the preprocessing execution process can be as follows: and the server sequentially performs missing value filling, abnormal value filtering and repeated value filtering on the historical transaction data of the client to obtain the preprocessed historical data. The method comprises the steps that a server calls a preset decision tree algorithm to traverse pre-processed historical data to obtain a traversal result, the traversal process can be any one or combination of a pre-sequence traversal, a middle-sequence traversal and a post-sequence traversal, the traversal result is classified according to preset customer group characteristics to obtain an initial decision tree, the preset customer group characteristics comprise customer group quality, customer group level, customer group age and the like, after the initial decision tree is generated, pruning processing needs to be carried out on the initial decision tree to obtain a target decision tree, the target decision tree comprises a plurality of leaf nodes, the server obtains a service handling rate corresponding to each leaf node, sorts each leaf node according to the sequence of the service handling rate from large to small to obtain a leaf node sorting result, and sorts according to a preset customer quantity grading standard to obtain a willingness grading standard.
102. And configuring an intention rule based on a preset flow dialect template to obtain a client intention rule, receiving voice interaction data returned by the artificial intelligent voice robot, and comparing the voice interaction data with the client intention rule to obtain a voice comparison result.
The server configures the intention rule based on a preset flow dialect template to obtain a client intention rule, receives voice interaction data returned by the artificial intelligent voice robot, and compares the voice interaction data with the client intention rule to obtain a voice comparison result. The flow-based conversational template includes a plurality of rule categories, where the plurality of rule categories include tail node, tail intention, client conversational language, stay time of a robot node, an on-hook type, number of times that the robot node passes through, a middle node, conversation time, and number of interactions, the server configures intention rules based on the plurality of rule categories to obtain client intention rules, and the client intention rules in this embodiment include different criteria corresponding to each rule category, for example: the robot node stays for less than 1 minute, the call duration is longer than 10 minutes and the like, voice interaction data returned after the artificial intelligent voice robot calls out are received in real time, the voice interaction data are judged in real time, whether the matching degree of the voice interaction data and the client intention rule is larger than a preset first matching threshold value or not is judged through a preset comparison algorithm, and a voice comparison result is obtained.
103. And extracting off-line interactive data in the voice comparison result, and matching the off-line interactive data with a preset customer intention degree label to obtain a customer intention matching result.
And the server extracts the offline interaction data in the voice comparison result, matches the offline interaction data with a preset client intention degree label, and obtains a client intention matching result. The server extracts voice interaction data which do not meet the intention client rule from the voice comparison result to obtain offline interaction data, the offline interaction data and the client intention label are subjected to secondary matching by calling a preset similarity matching algorithm to obtain a client intention matching result, a second matching threshold value is manually set in advance, the preset similarity calculation method can be an Euclidean metric (euclidean) algorithm, a Pearson correlation coefficient algorithm or a cosine similarity calculation method, and the client intention label is specially set in advance aiming at the client offline data.
104. And classifying the voice comparison result and the client intention degree matching result respectively based on the intention grading standard to obtain a client intention analysis result.
And the server classifies the voice comparison result and the client intention degree matching result respectively based on the intention grading standard to obtain a client intention analysis result. The classification algorithm applied in the classification process can be a K nearest neighbor algorithm, the server screens out first customer data from the voice comparison result, secondary screening is carried out based on a customer intention degree label, second customer data are screened out from a customer intention degree matching result, communication nodes and key words can be extracted according to communication contents between the artificial intelligent voice robot and customers in the interaction process, so that the purchase intention of the customers on products is analyzed, the server sequentially divides the first customer data and the second customer data into the intention grades of different fleets based on an intention grading standard, and a customer intention analysis result is obtained, wherein the preset first fleet and the second fleet are specifically determined manually according to the intention grading standard.
In the embodiment of the invention, the preprocessed historical data are classified based on a preset decision tree algorithm to obtain a wish grading standard, the voice interaction data are compared with the client intention rule to obtain a voice comparison result, the offline interaction data in the voice comparison result are extracted, the offline interaction data are matched with the preset client intention label to obtain a client intention matching result, the voice comparison result and the client intention matching result are classified respectively based on the wish grading standard to obtain a client intention analysis result, and the efficiency of client intention analysis is improved.
Referring to fig. 2, another embodiment of the method for analyzing the client intention according to the embodiment of the present invention includes:
201. and acquiring the historical transaction data of the client, and performing missing value completion, abnormal value filtration and repeated value filtration on the historical transaction data of the client to obtain the preprocessed historical data.
The server acquires the historical transaction data of the client, and performs missing value completion, abnormal value filtration and repeated value filtration on the historical transaction data of the client to obtain the preprocessed historical data. The server acquires the historical client transaction data, the historical client transaction data are acquired through the crawler, the historical client transaction data are authorized by the user, after the historical client transaction data are acquired, the historical client transaction data are preprocessed, and the preprocessing execution process can be as follows: the server sequentially carries out missing value filling, abnormal value filtering and repeated value filtering on the historical transaction data of the client to obtain preprocessed historical data, wherein the missing value filling can be multi-interpolation, the abnormal value filtering mainly adopts an abnormal value detection algorithm z-score to identify and delete abnormal values, and the repeated value filtering is to carry out repeated value removing processing.
202. And calling a preset decision tree algorithm, and performing traversal processing on the preprocessed historical data to obtain a target decision tree, wherein the target decision tree comprises a plurality of leaf nodes.
And calling a preset decision tree algorithm by the server, and traversing the preprocessed historical data to obtain a target decision tree, wherein the target decision tree comprises a plurality of leaf nodes. Specifically, the server performs traversal processing on the preprocessed historical data to obtain traversal results, and classifies the traversal results according to preset guest group characteristics to obtain an initial decision tree; and the server prunes the initial decision tree to obtain a target decision tree, wherein the target decision tree comprises a plurality of leaf nodes, and each leaf node corresponds to a guest group characteristic.
The traversal process may be any one or a combination of several of a forward traversal, a middle traversal and a backward traversal, the traversal result is classified according to preset guest group characteristics to obtain an initial decision tree, the preset guest group characteristics include guest group quality, guest group hierarchy, guest group age, and the like, after the initial decision tree is generated, pruning processing needs to be performed on the initial decision tree to obtain a target decision tree, in this embodiment, the pruning process applied is mainly backward pruning, the backward pruning is bottom-to-top pruning, which means that a non-leaf node is estimated from bottom to top for a generated complete decision tree, if a sub tree corresponding to the node is replaced by a leaf node to bring about enhancement of generalization performance of the decision tree, the backward pruning mainly includes: reduced-error pruning (REP), pessimistic-error pruning (PEP), cost-complexity pruning (CCP), and error-based pruning (EBP).
203. And obtaining the service transaction rate corresponding to each leaf node in the target decision tree, and sequencing each leaf node according to the sequence of the service transaction rates from large to small to obtain the leaf node sequencing result.
And the server acquires the service transaction rate corresponding to each leaf node in the target decision tree, and sequences each leaf node according to the sequence of the service transaction rates from large to small to obtain a leaf node sequencing result. The target decision tree comprises a plurality of leaf nodes, the server obtains the service transaction rate corresponding to each leaf node, and sequences each leaf node according to the sequence of the service transaction rates from large to small to obtain a leaf node sequencing result.
204. And classifying the leaf node sequencing results according to a preset customer quantity grading standard to obtain a wish grading standard.
And the server classifies the leaf node sequencing results according to a preset client quantity grading standard to obtain a wish grading standard. The method comprises the steps that a server classifies according to a preset client quantity grading standard to obtain a wish grading standard, wherein the client quantity grading standard is not limited specifically, a classification algorithm applied in a classification process can be a K nearest neighbor algorithm, for example, the client quantity can be divided into one grade according to 20%, the corresponding wish grading standard has 5 grades, each grade in the wish grading standard has a corresponding standard grading value, the server classifies leaf node sequencing results to obtain the wish grading standard by calling the K nearest neighbor algorithm, the standard grading values are used for subsequently matching and dividing data, and the setting rule of the standard grading values is as follows: and extracting the lowest service transaction rate in the willingness grading of each grade, and determining the lowest service transaction rate as a standard grading value corresponding to each grade.
205. And configuring an intention rule based on a preset flow dialect template to obtain a client intention rule, receiving voice interaction data returned by the artificial intelligent voice robot, and comparing the voice interaction data with the client intention rule to obtain a voice comparison result.
The server configures the intention rule based on a preset flow dialect template to obtain a client intention rule, receives voice interaction data returned by the artificial intelligent voice robot, and compares the voice interaction data with the client intention rule to obtain a voice comparison result. Specifically, the server acquires a flow language template, and configures intention rules based on a plurality of rule categories in the flow language template to obtain client intention rules; the server receives voice interaction data returned by the artificial intelligent voice robot and obtains a first matching degree between the voice interaction data and the client intention rule; and the server calls a preset comparison algorithm to judge whether the first matching degree is greater than a preset first matching threshold value or not, and a voice comparison result is obtained.
The procedural telephony template comprises a plurality of rule categories, wherein the plurality of rule categories comprise tail nodes: final node, tail intention to talk to an artificial intelligence voice robot: intention of the client in the final process of the call, client's talk: specific dialogs containing a plurality of keywords or inputs, robot node dwell time: node stay time and on-hook type of a single robot: the method comprises the following steps of hanging up a system, actively hanging up a user and passing times of robot nodes: the number value corresponding to the number of times of passing through each node is an integer larger than 0, and the check that the upper limit value is larger than the lower limit value and the intermediate node are required to be carried out: the relation between a plurality of nodes passing through in the voice call process (namely, meeting the requirement that the plurality of nodes can judge the intention rule of the hit customer) and the call duration are as follows: the total duration and the interaction times of the whole communication call are as follows: the method comprises the steps that interaction times of an artificial intelligent voice robot and a client are counted in a call process, a server configures intention rules based on a plurality of rule categories to obtain the intention rules of the client, voice interaction data returned after the artificial intelligent voice robot calls out are received in real time, the voice interaction data are judged in real time, whether the matching degree of the voice interaction data and the intention rules of the client is larger than a first matching threshold value or not is judged through a preset comparison algorithm to obtain a voice comparison result, the first matching threshold value is manually set in advance, and the comparison algorithm in the embodiment can be a diff algorithm.
206. And extracting off-line interactive data in the voice comparison result, and matching the off-line interactive data with a preset customer intention degree label to obtain a customer intention matching result.
And the server extracts the offline interaction data in the voice comparison result, matches the offline interaction data with a preset client intention degree label, and obtains a client intention matching result. Specifically, the server extracts voice interaction data with a first matching degree smaller than or equal to a preset first matching threshold value in the voice comparison result to obtain offline interaction data, wherein the first matching degree is the matching degree of the voice interaction data and the customer intention rule; and the server calculates the second matching degree and a preset second matching threshold according to a preset similarity matching algorithm to obtain a client intention matching result, wherein the second matching degree is the matching degree of the offline interaction data and a preset client intention label.
In the process of a call between a client and an artificial intelligent voice robot, problems that the client hangs up in the midway, hangs up in the waiting process, is not connected, and has a call fault due to a signal cause may exist, so that voice interaction data does not hit a client intention rule, a server extracts the voice interaction data which does not meet the intention client rule from a voice comparison result to obtain offline interaction data, and performs secondary matching on the offline interaction data and a client intention label by calling a preset similarity matching algorithm to obtain a client intention matching result, wherein the preset similarity algorithm may be an euclidean metric (euclidean metric) algorithm, a pearson correlation coefficient algorithm or a cosine similarity algorithm, and the client intention label is specially set in advance for the client offline data, for example: the off-hook of the customer waiting for the seat wiring is set as a high intention label, and the off-hook is not connected and defined as a low intention label, so that the intention label of the customer is obtained, and specifically, the matching degree of the off-line interactive data hitting the high intention label and the preset intention label of the customer is higher.
207. And classifying the voice comparison result and the client intention degree matching result respectively based on the intention grading standard to obtain a client intention analysis result.
And the server classifies the voice comparison result and the client intention degree matching result respectively based on the intention grading standard to obtain a client intention analysis result. Specifically, the server extracts first client data from the voice comparison result, and divides the first client data into preset first echelon willingness grades based on willingness grading standards to obtain a first classification result, wherein the first client data are voice interaction data with a first matching degree greater than a first matching threshold; the server extracts second client data from the client intention degree matching results, and divides the second client data into preset second echelon intention grades based on intention grading standards to obtain second classification results, wherein the second client data are offline interaction data with a second matching degree larger than a second matching threshold in the client intention degree matching results; the server determines the first classification result and the second classification result as a client intention analysis result.
The first customer data are screened out through a customer intention rule, secondary screening is carried out based on a customer intention degree label to obtain second customer data, communication nodes and key words can be extracted according to communication contents of an artificial intelligent voice robot and customers in an interaction process aiming at lost customers, so as to analyze the purchase intention of the customers to products, a server sequentially divides the first customer data and the second customer data into intention grades of different echelons based on an intention grading standard to obtain a customer intention analysis result, for example, if the intention grading standard has 5 grades, the first echelon can be a first grade and a second grade which are positioned at the front in the intention grading standard, the second echelon can be a third grade, step 203 shows that each grade in the intention grading standard has a corresponding standard grading value, the server divides the extracted first customer data into preset first echelon intention grading, the first matching degree is also read, and the first customer data is respectively divided into different grades in the first echelon according to a preset standard grade value-first matching degree corresponding table, for example: the willingness grading standard has 5 grades, the standard grading value (namely the lowest business transaction rate) corresponding to each grade is 90%, 75%, 60%, 40% and 15%, the manually set willingness grading of the first team is the first two grades (namely the grading values corresponding to the standard grading values of 90% and 75%), the server divides the extracted first client data into the willingness grading of the first team, the first matching degree is read to be 80%, in the standard grading value-first matching degree corresponding table, the first matching degree corresponding to the standard grading value of 90% is 75%, and 80% > 75% represents the grading corresponding to the standard grading value of 90% in the first client data. And after the server divides the second client data into the preset second echelon willingness grades, reading the second matching degree, and dividing the second client data into different grades in the second echelon according to a preset standard grade value-second matching degree corresponding table. By carrying out secondary screening on offline interaction data (namely second client data) with the second matching degree larger than a second matching threshold value in the client intention degree matching result, secondary follow-up can be carried out on the leaked data in the interaction, the client intention can be analyzed more accurately, the client handling rate is improved, the first client data and the second client data which hit a client intention rule in the voice interaction result are divided into different echelons with intention grading standards and different intention grading in the different echelons, and subsequent follow-up processing can be carried out on the intended clients corresponding to the different client data in a targeted manner according to different grading in the client intention analysis result, for example: and performing manual secondary follow-up, sending a short message to the client or sending an intention confirmation mail, and the like, wherein the follow-up frequency can be specifically adjusted for different echelons in the intention grading standard, for example: the frequency of subsequent manual follow-up of the corresponding clients is higher when the first echelon wishes to be graded.
In the embodiment of the invention, the preprocessed historical data are classified based on a preset decision tree algorithm to obtain a wish grading standard, the voice interaction data are compared with the client intention rule to obtain a voice comparison result, the offline interaction data in the voice comparison result are extracted, the offline interaction data are matched with the preset client intention label to obtain a client intention matching result, the voice comparison result and the client intention matching result are classified respectively based on the wish grading standard to obtain a client intention analysis result, and the efficiency of client intention analysis is improved.
In the above description of the method for analyzing the intention of the customer according to the embodiment of the present invention, referring to fig. 3, the apparatus for analyzing the intention of the customer according to the embodiment of the present invention is described as follows, and one embodiment of the apparatus for analyzing the intention of the customer according to the embodiment of the present invention includes:
the acquisition module 301 is configured to acquire historical client transaction data, preprocess the historical client transaction data to obtain preprocessed historical data, and classify the preprocessed historical data based on a preset decision tree algorithm to obtain a willingness grading standard;
the comparison module 302 is used for configuring the intention rule based on a preset flow dialect template to obtain a client intention rule, receiving voice interaction data returned by the artificial intelligent voice robot, and comparing the voice interaction data with the client intention rule to obtain a voice comparison result;
the matching module 303 is configured to extract offline interaction data in the voice comparison result, and match the offline interaction data with a preset client intention degree tag to obtain a client intention matching result;
and the classification module 304 is configured to classify the voice comparison result and the client intention degree matching result respectively based on the intention grading standard to obtain a client intention analysis result.
In the embodiment of the invention, the preprocessed historical data are classified based on a preset decision tree algorithm to obtain a wish grading standard, the voice interaction data are compared with the client intention rule to obtain a voice comparison result, the offline interaction data in the voice comparison result are extracted, the offline interaction data are matched with the preset client intention label to obtain a client intention matching result, the voice comparison result and the client intention matching result are classified respectively based on the wish grading standard to obtain a client intention analysis result, and the efficiency of client intention analysis is improved.
Referring to fig. 4, another embodiment of the client intention analyzing apparatus according to the embodiment of the present invention includes:
the acquisition module 301 is configured to acquire historical client transaction data, preprocess the historical client transaction data to obtain preprocessed historical data, and classify the preprocessed historical data based on a preset decision tree algorithm to obtain a willingness grading standard;
specifically, the obtaining module 301 includes:
the preprocessing unit 3011 is configured to obtain historical client transaction data, and perform missing value completion, abnormal value filtering, and repeated value filtering on the historical client transaction data to obtain preprocessed historical data;
the traversal unit 3012 is configured to invoke a preset decision tree algorithm, and perform traversal processing on the preprocessed historical data to obtain a target decision tree, where the target decision tree includes multiple leaf nodes;
the sorting unit 3013 is configured to obtain a service transaction rate corresponding to each leaf node in the target decision tree, and sort each leaf node according to a sequence of the service transaction rates from large to small to obtain a leaf node sorting result;
a classification unit 3014, configured to classify the leaf node sorting results according to a preset customer quantity grading standard, so as to obtain a willingness grading standard;
the comparison module 302 is used for configuring the intention rule based on a preset flow dialect template to obtain a client intention rule, receiving voice interaction data returned by the artificial intelligent voice robot, and comparing the voice interaction data with the client intention rule to obtain a voice comparison result;
the matching module 303 is configured to extract offline interaction data in the voice comparison result, and match the offline interaction data with a preset client intention degree tag to obtain a client intention matching result;
and the classification module 304 is configured to classify the voice comparison result and the client intention degree matching result respectively based on the intention grading standard to obtain a client intention analysis result.
Optionally, the traversal unit 3012 may be further specifically configured to:
traversing the preprocessed historical data to obtain a traversal result, and classifying the traversal result according to preset guest group characteristics to obtain an initial decision tree; and pruning the initial decision tree to obtain a target decision tree, wherein the target decision tree comprises a plurality of leaf nodes, and each leaf node corresponds to a guest group characteristic.
Optionally, the comparison module 302 includes:
a configuration unit 3021, configured to obtain a procedural tactical template, and configure an intention rule based on a plurality of rule categories in the procedural tactical template to obtain a client intention rule;
the receiving unit 3022 is configured to receive voice interaction data returned by the artificial intelligent voice robot, and obtain a first matching degree between the voice interaction data and the client intention rule;
the first judging unit 3023 is configured to call a preset comparison algorithm to judge whether the first matching degree is greater than a preset first matching threshold, so as to obtain a voice comparison result.
Optionally, the matching module 303 includes:
the extracting unit 3031 is configured to extract voice interaction data in the voice comparison result, where the first matching degree is smaller than or equal to a preset first matching threshold, to obtain offline interaction data, where the first matching degree is a matching degree of the voice interaction data and a customer intention rule;
a second determining unit 3032, configured to obtain a second matching degree, call a preset similarity matching algorithm, and determine whether the second matching degree is greater than a preset second matching threshold, to obtain a customer intention matching result, where the second matching degree is a matching degree between the offline interaction data and a preset customer intention label.
Optionally, the classification module 304 includes:
a first dividing unit 3041, configured to extract first customer data from the voice comparison result, and divide the first customer data into a preset first echelon willingness grading based on a willingness grading standard to obtain a first classification result, where the first customer data is voice interaction data with a first matching degree greater than a first matching threshold;
a second dividing unit 3042, configured to extract second customer data from the customer intention degree matching result, and divide the second customer data into a preset second echelon intention grading based on an intention grading standard to obtain a second classification result, where the second customer data is offline interaction data in the customer intention degree matching result, where a second matching degree is greater than a second matching threshold;
a determining unit 3043 for determining the first classification result and the second classification result as the customer intention analysis result.
Optionally, before the obtaining module 301, the client intention analyzing apparatus further includes a voice interaction module 305, including:
and acquiring data to be tested of the customer, and sending the data to be tested of the customer to the artificial intelligent voice robot so that the artificial intelligent voice robot performs voice interaction to obtain voice interaction data.
In the embodiment of the invention, the preprocessed historical data are classified based on a preset decision tree algorithm to obtain a wish grading standard, the voice interaction data are compared with the client intention rule to obtain a voice comparison result, the offline interaction data in the voice comparison result are extracted, the offline interaction data are matched with the preset client intention label to obtain a client intention matching result, the voice comparison result and the client intention matching result are classified respectively based on the wish grading standard to obtain a client intention analysis result, and the efficiency of client intention analysis is improved.
Fig. 3 and 4 describe the client intention analysis device in the embodiment of the present invention in detail from the perspective of the modular functional entity, and the client intention analysis device in the embodiment of the present invention is described in detail from the perspective of hardware processing.
Fig. 5 is a schematic structural diagram of a client intention analyzing device 500 according to an embodiment of the present invention, where the client intention analyzing device 500 may have a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 510 (e.g., one or more processors) and a memory 520, one or more storage media 530 (e.g., one or more mass storage devices) for storing applications 533 or data 532. Memory 520 and storage media 530 may be, among other things, transient or persistent storage. The program stored in the storage medium 530 may include one or more modules (not shown), each of which may include a series of computer program operations in the client intention analysis device 500. Still further, the processor 510 may be configured to communicate with the storage medium 530, and execute a series of computer program operations in the storage medium 530 on the client intention analysis device 500.
The client intent analysis device 500 may also include one or more power supplies 540, one or more wired or wireless network interfaces 550, one or more input-output interfaces 560, and/or one or more operating systems 531, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc. Those skilled in the art will appreciate that the configuration of the customer intention analysis device shown in fig. 5 does not constitute a limitation of the customer intention analysis device, and may include more or less components than those shown, or some components in combination, or a different arrangement of components.
The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium, and which may also be a volatile computer-readable storage medium, having stored thereon a computer program, which, when run on a computer, causes the computer to perform the steps of the client intention analysis method.
Further, the computer-readable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created according to the use of the blockchain node, and the like.
The block chain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like. A block chain (Blockchain), which is essentially a decentralized database, is a series of data blocks associated by using a cryptographic method, and each data block contains information of a batch of network transactions, so as to verify the validity (anti-counterfeiting) of the information and generate a next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, and the like.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes several computer programs to enable a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A customer intention analysis method, characterized by comprising:
acquiring historical handling data of a client, preprocessing the historical handling data of the client to obtain preprocessed historical data, and classifying the preprocessed historical data based on a preset decision tree algorithm to obtain a willingness grading standard;
configuring an intention rule based on a preset flow dialect template to obtain a client intention rule, receiving voice interaction data returned by an artificial intelligent voice robot, and comparing the voice interaction data with the client intention rule to obtain a voice comparison result;
extracting off-line interactive data in the voice comparison result, and matching the off-line interactive data with a preset customer intention degree label to obtain a customer intention matching result;
and classifying the voice comparison result and the client intention degree matching result respectively based on the intention grading standard to obtain a client intention analysis result.
2. The method for analyzing client intention according to claim 1, wherein the obtaining of the client historical transaction data, the preprocessing of the client historical transaction data to obtain preprocessed historical data, and the classifying of the preprocessed historical data based on a preset decision tree algorithm to obtain the will grading criteria comprise:
acquiring historical transaction data of a client, and performing missing value completion, abnormal value filtration and repeated value filtration on the historical transaction data of the client to obtain preprocessed historical data;
calling a preset decision tree algorithm, and performing traversal processing on the preprocessed historical data to obtain a target decision tree, wherein the target decision tree comprises a plurality of leaf nodes;
acquiring a service handling rate corresponding to each leaf node in the target decision tree, and sequencing each leaf node according to the sequence of the service handling rates from large to small to obtain a leaf node sequencing result;
and classifying the leaf node sequencing results according to a preset customer quantity grading standard to obtain a wish grading standard.
3. The method of claim 2, wherein the invoking a preset decision tree algorithm to traverse the pre-processed historical data to obtain a target decision tree, the target decision tree comprising a plurality of leaf nodes comprises:
traversing the preprocessed historical data to obtain a traversal result, and classifying the traversal result according to preset guest group characteristics to obtain an initial decision tree;
and pruning the initial decision tree to obtain a target decision tree, wherein the target decision tree comprises a plurality of leaf nodes, and each leaf node corresponds to a guest group characteristic.
4. The method according to claim 1, wherein the configuring intent rules based on the preset conversational template to obtain the client intent rules, receiving voice interaction data returned by the artificial intelligent voice robot, and comparing the voice interaction data with the client intent rules to obtain a voice comparison result comprises:
acquiring a process technology template, and configuring intention rules based on a plurality of rule categories in the process technology template to obtain client intention rules;
receiving voice interaction data returned by the artificial intelligent voice robot, and acquiring a first matching degree between the voice interaction data and the client intention rule;
and calling a preset comparison algorithm to judge whether the first matching degree is greater than a preset first matching threshold value or not, and obtaining a voice comparison result.
5. The method according to claim 1, wherein the extracting offline interaction data in the voice comparison result and matching the offline interaction data with a preset client intention degree tag to obtain a client intention matching result comprises:
extracting voice interaction data with a first matching degree smaller than or equal to a preset first matching threshold value in the voice comparison result to obtain offline interaction data, wherein the first matching degree is the matching degree of the voice interaction data and the customer intention rule;
and acquiring a second matching degree, calling a preset similarity matching algorithm, and judging whether the second matching degree is greater than a preset second matching threshold value to obtain a customer intention matching result, wherein the second matching degree is the matching degree of the offline interactive data and a preset customer intention label.
6. The method according to claim 1, wherein the classifying the voice comparison result and the client intention degree matching result based on the intention grading criteria, respectively, and the obtaining the client intention analysis result includes:
extracting first client data from the voice comparison result, and dividing the first client data into preset first echelon willingness grading based on the willingness grading standard to obtain a first classification result, wherein the first client data are voice interaction data with a first matching degree greater than a first matching threshold;
extracting second client data from the client intention degree matching result, and dividing the second client data into preset second echelon intention grades based on the intention grading standard to obtain a second classification result, wherein the second client data are offline interaction data of which the second matching degree is greater than a second matching threshold value in the client intention degree matching result;
determining the first classification result and the second classification result as a customer intention analysis result.
7. The method for analyzing client intention according to any one of claims 1 to 6, wherein before the obtaining of the client history transaction data, the preprocessing of the client history transaction data to obtain the preprocessed history data, and the classification of the preprocessed history data based on a preset decision tree algorithm to obtain the willingness grading criteria, the method for analyzing client intention further comprises:
the method comprises the steps of obtaining data to be tested of a customer, and sending the data to be tested of the customer to an artificial intelligent voice robot, so that the artificial intelligent voice robot carries out voice interaction, and voice interaction data are obtained.
8. A client intention analysis device, characterized by comprising:
the system comprises an acquisition module, a classification module and a classification module, wherein the acquisition module is used for acquiring historical handling data of a client, preprocessing the historical handling data of the client to obtain preprocessed historical data, and classifying the preprocessed historical data based on a preset decision tree algorithm to obtain a willingness grading standard;
the comparison module is used for configuring the intention rule based on a preset flow dialect template to obtain a client intention rule, receiving voice interaction data returned by the artificial intelligent voice robot, and comparing the voice interaction data with the client intention rule to obtain a voice comparison result;
the matching module is used for extracting the offline interaction data in the voice comparison result and matching the offline interaction data with a preset client intention label to obtain a client intention matching result;
and the classification module is used for classifying the voice comparison result and the client intention degree matching result respectively based on the intention grading standard to obtain a client intention analysis result.
9. A customer intention analysis device characterized by comprising:
a memory and at least one processor, the memory having stored therein a computer program;
the at least one processor calls the computer program in the memory to cause the customer intention analysis device to perform the customer intention analysis method according to any one of claims 1 to 7.
10. A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the client intention analysis method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111273716.5A CN113988190A (en) | 2021-10-29 | 2021-10-29 | Customer intention analysis method, apparatus, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111273716.5A CN113988190A (en) | 2021-10-29 | 2021-10-29 | Customer intention analysis method, apparatus, device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113988190A true CN113988190A (en) | 2022-01-28 |
Family
ID=79744511
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111273716.5A Pending CN113988190A (en) | 2021-10-29 | 2021-10-29 | Customer intention analysis method, apparatus, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113988190A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115309737A (en) * | 2022-10-11 | 2022-11-08 | 深圳市明源云客电子商务有限公司 | Visitor intention analysis method and system, terminal device and readable storage medium |
-
2021
- 2021-10-29 CN CN202111273716.5A patent/CN113988190A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115309737A (en) * | 2022-10-11 | 2022-11-08 | 深圳市明源云客电子商务有限公司 | Visitor intention analysis method and system, terminal device and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110992167B (en) | Bank customer business intention recognition method and device | |
| CN107066616A (en) | Method, device and electronic equipment for account processing | |
| CN107038449B (en) | Method and device for identifying fraudulent user | |
| CN110399490A (en) | A kind of barrage file classification method, device, equipment and storage medium | |
| CN109447180A (en) | A kind of fooled people's discovery method of the telecommunication fraud based on big data and machine learning | |
| CN112733146B (en) | Penetration testing method, device and equipment based on machine learning and storage medium | |
| CN114389834B (en) | Method, device, equipment and product for identifying abnormal call of API gateway | |
| CN112329811A (en) | Abnormal account identification method and device, computer equipment and storage medium | |
| CN110263155A (en) | The training method and system of data classification method, data classification model | |
| CN108334895A (en) | Sorting technique, device, storage medium and the electronic device of target data | |
| CN108268886A (en) | For identifying the method and system of plug-in operation | |
| CN114419363A (en) | Target classification model training method and device based on label-free sample data | |
| CN113988190A (en) | Customer intention analysis method, apparatus, device and storage medium | |
| CN115577172A (en) | Article recommendation method, device, equipment and medium | |
| US7236612B2 (en) | Method of video coding images comprising address information | |
| CN111091408A (en) | User identification model creating method and device and identification method and device | |
| CN113762392A (en) | Financial product recommendation method, device, equipment and medium based on artificial intelligence | |
| CN117172795A (en) | Intelligent technical service fee online consultation system | |
| CN116452212A (en) | Intelligent customer service commodity knowledge base information management method and system | |
| CN114637917A (en) | Information head bar recommendation method and device based on artificial intelligence | |
| CN114037395A (en) | Abnormal consignment data identification method and system, electronic equipment and storage medium | |
| CN108763242A (en) | Label generating method and device | |
| CN113191711A (en) | Express delivery sending strategy determining method, device, equipment and storage medium | |
| Varun et al. | An efficient technique for feature selection to predict customer churn in telecom industry | |
| CN114189585A (en) | Crank call abnormity detection method and device and computing equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |