CN117196692A - Client behavior prediction method, device, equipment and storage medium - Google Patents
Client behavior prediction method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN117196692A CN117196692A CN202311152672.XA CN202311152672A CN117196692A CN 117196692 A CN117196692 A CN 117196692A CN 202311152672 A CN202311152672 A CN 202311152672A CN 117196692 A CN117196692 A CN 117196692A
- Authority
- CN
- China
- Prior art keywords
- client
- data
- predicted
- knowledge
- customer
- 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
- 238000000034 method Methods 0.000 title claims abstract description 68
- 230000006399 behavior Effects 0.000 claims description 34
- 238000012545 processing Methods 0.000 claims description 33
- 238000004422 calculation algorithm Methods 0.000 claims description 28
- 238000003064 k means clustering Methods 0.000 claims description 26
- 238000004458 analytical method Methods 0.000 claims description 23
- 230000004927 fusion Effects 0.000 claims description 16
- 230000000694 effects Effects 0.000 abstract description 5
- 238000004891 communication Methods 0.000 description 14
- 238000000605 extraction Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 7
- 208000025174 PANDAS Diseases 0.000 description 6
- 208000021155 Paediatric autoimmune neuropsychiatric disorders associated with streptococcal infection Diseases 0.000 description 6
- 240000004718 Panda Species 0.000 description 6
- 235000016496 Panda oleosa Nutrition 0.000 description 6
- 238000004140 cleaning Methods 0.000 description 6
- 238000012217 deletion Methods 0.000 description 6
- 230000037430 deletion Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000003672 processing method Methods 0.000 description 5
- 230000002159 abnormal effect Effects 0.000 description 4
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 4
- 239000010931 gold Substances 0.000 description 4
- 229910052737 gold Inorganic materials 0.000 description 4
- 238000007726 management method Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 230000005236 sound signal Effects 0.000 description 4
- 206010000117 Abnormal behaviour Diseases 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000000295 complement effect Effects 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000003058 natural language processing Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a client behavior prediction method, device, equipment and storage medium, which can be used in the financial field or other fields. The method comprises the following steps: acquiring optimized customer data, and acquiring a customer classification report and a classification customer data report corresponding to each influence factor according to the optimized customer data; and constructing a knowledge base based on the customer classification report and the classified customer data report corresponding to each influencing factor; and inputting the client data of the client to be predicted and the predicted product into a prediction model so that the prediction model calculates the matching degree between the client to be predicted and the predicted product, and obtaining a prediction result according to the matching degree between the client to be predicted and the predicted product. Based on the method of the application, the client data can be reliably analyzed and the next behavior of the client can be accurately predicted, so as to realize the effects of accurate marketing and quick decision.
Description
Technical Field
The present application relates to the financial field or other fields, and in particular, to a method, apparatus, device and storage medium for predicting customer behavior.
Background
The knowledge base is a special database for knowledge management, so that the knowledge in the related fields can be collected, managed and extracted conveniently, and the knowledge base is a set of internal or external knowledge of an enterprise in essence, and can help staff or clients to search out answers of wanted questions or questions in time. Knowledge of customer characteristics, records of customer-related information in the system, and customer-related contact's assessment of customers is all knowledge of business personnel. Enterprises can effectively integrate related knowledge of different sources and different forms only by establishing a related knowledge base, so that knowledge is converted, the aims of co-creation, sharing and application innovation are achieved, and the problem of timely and effective prediction of customer behaviors is solved by application.
The existing method for creating the knowledge base cannot accurately ensure objectivity in the knowledge base creation process, meanwhile, the clients have the possibility of abnormal behaviors, the prediction of related client behaviors can only play a role in suggestion, the next behaviors of the clients are reliably analyzed and accurately predicted based on client data, and the effect of achieving accurate marketing and quick decision is a problem which is solved in the field.
Disclosure of Invention
The application provides a client behavior prediction method, device, equipment and storage medium, which are used for reliably analyzing client data and accurately predicting the next behavior of a client so as to realize the effects of accurate marketing and quick decision.
In a first aspect, the present application provides a method for predicting customer behavior, including:
acquiring and optimizing client data of a plurality of clients to obtain optimized client data, wherein the client data comprises client values and a plurality of influencing factors influencing the client values;
performing k-means clustering algorithm analysis on the client value in the optimized client data to obtain a client classification report, and performing k-means clustering algorithm analysis on a plurality of influence factors influencing the client value in the optimized client data to obtain a classification client data report corresponding to each influence factor; and constructing a knowledge base based on the customer classification report and the classified customer data report corresponding to each influencing factor;
inputting client data of clients to be predicted and predicted products into a prediction model, so that the prediction model searches the knowledge base based on a search engine to determine a first client similar to the clients to be predicted, calculates the matching degree between the clients to be predicted and the predicted products based on the client data optimized with the first client, and obtains a prediction result according to the matching degree between the clients to be predicted and the predicted products, wherein the prediction result is used for representing whether the clients to be predicted intend to obtain the predicted products.
In one example, the obtaining and optimizing the client data of the plurality of clients, to obtain optimized client data, includes:
acquiring client data of the plurality of clients;
and sequentially performing repeated value removing operation, missing data filling operation and linear interpolation operation on the client data of the clients to obtain the optimized client data.
In one example, the building a knowledge base based on the customer classification report and the classified customer data report corresponding to each influencing factor includes:
extracting data associated with a plurality of preset feature words from the classified client data report corresponding to each influence factor in the client classified report to obtain knowledge data;
according to the sequence of the corresponding client value in the knowledge data from high to low, correlating the knowledge data to obtain a knowledge structure;
and carrying out knowledge fusion on the knowledge structure by taking the client as a body, and constructing a knowledge base by using a data-driven form through the knowledge fusion result.
In one example, the obtaining the prediction result according to the matching degree between the to-be-predicted client and the predicted product includes:
if the matching degree between the client to be predicted and the predicted product exceeds a preset threshold, judging that the predicted result is that the client to be predicted is intended to obtain the predicted product;
And if the matching degree between the client to be predicted and the predicted product does not exceed the threshold value, judging that the predicted result is that the client to be predicted does not intend to obtain the predicted product.
In one example, the knowledge base is a graph knowledge base.
In a second aspect, the present application provides a customer behavior prediction apparatus, the apparatus comprising:
the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring and optimizing client data of a plurality of clients to obtain optimized client data, and the client data comprises client values and a plurality of influence factors influencing the client values;
the processing module is used for carrying out k-means clustering algorithm analysis on the client value in the optimized client data to obtain a client classification report, and respectively carrying out k-means clustering algorithm analysis on a plurality of influence factors influencing the client value in the optimized client data to obtain a classification client data report corresponding to each influence factor; and constructing a knowledge base based on the customer classification report and the classified customer data report corresponding to each influencing factor;
the input module is used for inputting the client data of the client to be predicted and the predicted product into the prediction model, so that the prediction model searches the knowledge base based on a search engine to determine a first client similar to the client to be predicted, calculates the matching degree between the client to be predicted and the predicted product based on the client data optimized with the first client, and obtains a prediction result according to the matching degree between the client to be predicted and the predicted product, wherein the prediction result is used for representing whether the client to be predicted is intended to obtain the predicted product.
In one example, the obtaining module is specifically configured to obtain client data of the plurality of clients;
the acquisition module is specifically further configured to sequentially perform an operation of removing duplicate values, an operation of filling missing data, and a linear interpolation operation on the client data of the plurality of clients, so as to obtain the optimized client data.
In one example, the processing module is specifically configured to extract data associated with a plurality of preset feature words from the classified client data report corresponding to each influence factor in the client classified report, so as to obtain knowledge data;
the processing module is specifically configured to correlate the knowledge data according to the order of the corresponding client values in the knowledge data from high to low to obtain a knowledge structure;
the processing module is specifically further configured to perform knowledge fusion on the knowledge structure with the client as a body, and construct a knowledge base from the knowledge fusion result in a data driven manner.
In a third aspect, the present application provides an electronic device comprising: a processor, and a memory communicatively coupled to the processor;
the memory stores computer-executable instructions;
the processor executes computer-executable instructions stored in the memory to implement the method as described above.
In a fourth aspect, the application provides a computer readable storage medium having stored therein computer executable instructions which when executed by a processor are for carrying out the method as described above.
According to the client behavior prediction method, the client behavior prediction device, the client behavior prediction equipment and the storage medium, client data of a plurality of clients are obtained and optimized, and the optimized client data are obtained, wherein the client data comprise client values and a plurality of influence factors influencing the client values; performing k-means clustering algorithm analysis on the client value in the optimized client data to obtain a client classification report, and performing k-means clustering algorithm analysis on a plurality of influence factors influencing the client value in the optimized client data to obtain a classification client data report corresponding to each influence factor; and constructing a knowledge base based on the customer classification report and the classified customer data report corresponding to each influencing factor; inputting client data of clients to be predicted and predicted products into a prediction model, so that the prediction model searches the knowledge base based on a search engine to determine a first client similar to the clients to be predicted, calculates the matching degree between the clients to be predicted and the predicted products based on the client data optimized with the first client, and obtains a prediction result according to the matching degree between the clients to be predicted and the predicted products, wherein the prediction result is used for representing whether the clients to be predicted intend to obtain the predicted products. Based on the method provided by the application, the actually acquired client data is subjected to a k-means clustering algorithm to obtain a client classification report and a classification client data report, a database is created based on the client classification report and the classification client data report, and the behavior of a client to be predicted is predicted through the client data in the database.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application.
Fig. 1 is a schematic view of an exemplary application scenario of the present application;
FIG. 2 is a flowchart of a method for predicting customer behavior according to an embodiment of the present application;
FIG. 3 is a flowchart illustrating another method for predicting customer behavior according to an embodiment of the present application;
FIG. 4 is a flowchart of a method for predicting customer behavior according to a first embodiment of the present application;
FIG. 5 is a flowchart of a method for predicting customer behavior according to a first embodiment of the present application;
fig. 6 is a schematic structural diagram of a client behavior prediction apparatus according to a second embodiment of the present application;
fig. 7 is a schematic structural diagram of an electronic device according to a third embodiment of the present application;
fig. 8 is a block diagram of a terminal device according to an exemplary embodiment.
Specific embodiments of the present application have been shown by way of the above drawings and will be described in more detail below. The drawings and the written description are not intended to limit the scope of the inventive concepts in any way, but rather to illustrate the inventive concepts to those skilled in the art by reference to the specific embodiments.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the application. Rather, they are merely examples of apparatus and methods consistent with aspects of the application as detailed in the accompanying claims.
It should be noted that, the client information (including, but not limited to, client device information, client personal information, etc.) and the data (including, but not limited to, data for analysis, stored data, presented data, etc.) related to the present application are information and data authorized by the client or fully authorized by each party, and the collection, use and processing of the related data need to comply with the relevant laws and regulations and standards, and provide corresponding operation entries for the client to select authorization or rejection.
It should be noted that the client behavior prediction method and apparatus of the present application may be used in the financial field, and may be used in any field other than the financial field.
The knowledge base is a special database for knowledge management, so that the knowledge in the related fields can be collected, tidied and extracted conveniently, and the knowledge base is a set of internal or external knowledge of an enterprise in essence, so that staff or clients can be helped to search out answers of wanted questions or questions in time. Knowledge of customer characteristics, records of customer-related information in the system, and customer-related contact's assessment of customers is all knowledge of business personnel. Enterprises can effectively integrate related knowledge of different sources and different forms only by establishing a related knowledge base, so that knowledge is converted, the aims of co-creation, sharing and application innovation are achieved, and the problem of timely and effective prediction of customer behaviors is solved by application.
The existing method for creating the knowledge base cannot accurately ensure objectivity in the knowledge base creation process, meanwhile, the clients have the possibility of abnormal behaviors, the prediction of related client behaviors can only play a role in suggestion, the next behaviors of the clients are reliably analyzed and accurately predicted based on client data, and the effect of achieving accurate marketing and quick decision is a problem which is solved in the field.
Fig. 1 is a schematic diagram of an application scenario of an example of the present application, where the example is based on that actually obtained client data is subjected to a k-means clustering algorithm to obtain a client classification report and a classification client data report, after a database is created based on the client classification report and the classification client data report, the client data of a client to be predicted and a predicted product are input into the database together, the client data similar to the client to be predicted is found from the database, the matching degree between the client to be predicted and the predicted product is obtained based on the similar client data, and whether the user to be predicted has an acquisition intention on the predicted product is determined based on the matching degree, so as to achieve the effects of accurate marketing and quick decision of the client to be predicted.
It should be noted that the brief description of the terminology in the present application is for the purpose of facilitating understanding of the embodiments described below only and is not intended to limit the embodiments of the present application. Unless otherwise indicated, these terms should be construed in their ordinary and customary meaning.
The following describes the technical scheme of the present application and how the technical scheme of the present application solves the above technical problems in detail with specific embodiments. The following embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments. Embodiments of the present application will be described below with reference to the accompanying drawings.
Example 1
Fig. 2 is a flow chart of a client behavior prediction method according to an embodiment of the present application, as shown in fig. 2, where the method includes:
step 201, obtaining and optimizing client data of a plurality of clients to obtain optimized client data, wherein the client data comprises client values and a plurality of influence factors influencing the client values;
step 202, performing k-means clustering algorithm analysis on the client value in the optimized client data to obtain a client classification report, and performing k-means clustering algorithm analysis on a plurality of influence factors influencing the client value in the optimized client data to obtain a classification client data report corresponding to each influence factor; and constructing a knowledge base based on the customer classification report and the classified customer data report corresponding to each influencing factor;
step 203, inputting the client data of the client to be predicted and the predicted product into a prediction model, so that the prediction model searches the knowledge base based on a search engine to determine a first client similar to the client to be predicted, calculates the matching degree between the client to be predicted and the predicted product based on the client data optimized with the first client, and obtains a prediction result according to the matching degree between the client to be predicted and the predicted product, wherein the prediction result is used for representing whether the client to be predicted is intended to obtain the predicted product.
The execution subject of the present embodiment is a client behavior prediction apparatus, which may be implemented by a computer program, for example, application software or the like; alternatively, the computer program may be implemented as a medium storing a related computer program, for example, a usb disk, a cloud disk, or the like; still alternatively, it may be implemented by a physical device, e.g., a chip or the like, in which the relevant computer program is integrated or installed.
By combining scene examples, taking a bank as an example, information such as the asset value of a bank customer in the bank, the real estate quantity under the name, the average consumption level in recent years and the like can be taken as customer data, so that the customer data of the customer in the bank can be collected from an artificial angle, but the currently obtained customer data is generally initial data, the reliability is low, the customer data needs to be preprocessed, and the customer data is optimized mainly through preprocessing to obtain optimized customer data. The client data includes a client value of the client and a plurality of influencing factors influencing the client value, for example, in the case of client data of a bank client, the asset value, the real estate quantity in the bank and the average consumption level in recent years of the bank client are influencing factors influencing the client value, the client value is determined by the asset value, the real estate quantity in the bank and the average consumption level in recent years of the bank client, for example, the influencing factors, namely the real estate quantity in the bank client, can be converted into market assets, and the sum of the asset value in the bank, the real estate quantity in the bank and the average consumption level in recent years is taken as the client value of the bank client.
Analyzing the client value in the client data and each influence factor influencing the client value by a k-means clustering algorithm (k-means clustering algorithm), completing feature selection and extraction of the data according to a similarity principle, and then performing similarity calculation between data objects; and finally, grouping the data objects according to the similarity to obtain a client classification report which is grouped according to the client value and a classification client data report which is respectively grouped according to each influencing factor. The K-means clustering algorithm is an iterative solution clustering analysis algorithm, and comprises the steps of dividing data into K groups, randomly selecting K objects as initial clustering centers, calculating the distance between each object and each seed clustering center, and distributing each object to the closest clustering center. The cluster centers and the objects assigned to them represent a cluster. For each sample assigned, the cluster center of the cluster is recalculated based on the existing objects in the cluster. This process will repeat until a certain termination condition is met. The termination condition may be that no or a minimum number of objects are reassigned to different clusters, no or a minimum number of cluster centers are changed again, and the sum of squares of errors is locally minimum.
Establishing a database by using the obtained customer classification report which is grouped by the customer value and the classified customer data report which is respectively grouped by each influencing factor as data sources of the database, adding a prediction model with a search function into the database, inputting the customer data and the predicted products of the customers to be predicted into the prediction model, searching the data in the database by the prediction model based on the customer data of the customers to be predicted, finding the customer data similar to the customers to be predicted, judging the matching degree between the customers to be predicted and the predicted products based on the customer data similar to the customers to be predicted, wherein the matching degree can be in a form of percentage, and judging whether the customers to be predicted have intention to obtain the predicted products according to the matching degree between the customers to be predicted and the predicted products. The customer data of the customer to be predicted input into the prediction model may be the customer value of the customer to be predicted, or may be the value of any influencing factor influencing the customer value. For example, if the customer data of the customer to be predicted inputted into the prediction model is a customer value, the prediction model screens the customer data of all bank customers consistent with the customer value of the customer to be predicted from the database based on the customer value of the customer to be predicted, and gives a matching degree with respect to the predicted product based on the customer data of all bank customers. If the predicted product is a product for obtaining real estate, the customer data of all banking customers screened by the prediction model and consistent with the customer value of the customer to be predicted show that the customer value of the banking customers is generally higher, but the number of real estate is smaller, which means that the banking customers have the ability to obtain real estate and generally need real estate, and the matching degree is higher. If the customer value of such banking customers is generally high, but there is a large amount of real estate in the name, then the degree of matching given is low.
According to the method, a client classification report and a classified client data report are obtained through a k-means clustering algorithm on actually obtained client data, a database is created based on the client classification report and the classified client data report, and the behavior of a client to be predicted is predicted through the client data in the database.
Optionally, fig. 3 is a flowchart of another client behavior prediction method according to the first embodiment of the present application, as shown in fig. 3, where the step 201 includes:
step 301, obtaining client data of the plurality of clients;
and 302, sequentially performing repeated value removal operation, missing data filling operation and linear interpolation operation on the client data of the clients to obtain the optimized client data.
By combining scene examples, combining actual conditions of banks, centralizing backbone service personnel and existing system data, collecting customer data such as asset values, real properties under the name and average consumption level of the last three years of clients in a row from an artificial angle, folding the influencing factors such as the real properties under the name of the bank clients into market assets, folding the asset values in the bank and the real properties under the name into the sum of the market assets and the average consumption level in recent years as the customer value of the bank clients, and firstly sequencing the customer data of the clients according to the customer value from low to high. And performing first data cleaning by using a repeated observation processing method based on Python, and removing the repeated value after detecting the repeated observation by using a redundant method, wherein a function in a redundant method Pandas library is used for searching and marking the repeated value. Specifically, if the duplicate method detects that the same client and client value exist in the acquired client data, the duplicate client and client value is deleted. For example, if two identical clients a exist in the acquired client data and the client values of the two clients a are also identical, the client value of one client a and the client value of the client a are reserved, and the client value of the other client a and the client a which are duplicated is deleted. Then, the deletion value processing method based on Python is used for carrying out the second data cleaning, and firstly, the data filtering dropana method is carried out, wherein the dropana method is a method for deleting the deletion value in the Python pandas library, and then, the data filling filter method is carried out, and the filter method pandas library provides a very useful function, and the main function of the filter method panas library is to fill the deletion value. If there is a missing item in the acquired customer data, for example, if there is an empty asset value of a customer, the asset value of the customer is completely filled after the second cleaning of the customer data, and the missing values of other customers are also completely filled. After the multi-client data is cleaned twice, the abnormal value in the client data is required to be processed, the abnormal value in the client data is mainly subjected to the complementary processing through the linear interpolation, and the optimized client data is obtained after the data is cleaned twice and the linear interpolation is processed, so that the acquired client data has higher credibility.
Optionally, fig. 4 is a flowchart of another method for predicting customer behavior according to the first embodiment of the present application, as shown in fig. 4, in step 202, a knowledge base is constructed based on the customer classification report and the classified customer data report corresponding to each influencing factor, including:
step 401, extracting data associated with a plurality of preset feature words from the classified client data report corresponding to each influence factor in the client classified report to obtain knowledge data;
step 402, associating the knowledge data according to the order of the corresponding client value in the knowledge data from high to low to obtain a knowledge structure;
and 403, carrying out knowledge fusion on the knowledge structure by taking the client as a body, and constructing a knowledge base by using a data-driven form through the knowledge fusion result.
In combination with a scenario example, the client classification report and the classified client data report corresponding to each influencing factor are processed by using a Neuro-Linguistic Programming (NLP) natural language processing technology, specifically, a plurality of feature words are preset, for example, the feature words are set to be gold, 100 and dollars, and entity knowledge extraction, relation extraction and attribute extraction related to the feature words are performed from the classified client data report corresponding to each influencing factor in the client classification report, so that knowledge data related to the feature words is obtained. For example, the asset value of the client a is 100 ten thousand dollars in the client classification report corresponding to each influencing factor, so that the relevant knowledge data is obtained as client a→ (possession) →100→ten thousand →dollars, and all the knowledge data associated with "gold", "100", "dollars" are extracted in this way. In all the extracted knowledge data, a plurality of clients may be included, and all the extracted knowledge data may be sequenced from high to low according to the client value of the clients to obtain a knowledge structure composed of the plurality of extracted knowledge data. And carrying out knowledge fusion on the obtained knowledge data according to the client as the body, and fusing the independently flattened knowledge data into a net knowledge structure with the client as the body. Specifically, similarity of entity attributes is calculated through coreference resolution, and correct entity objects in the database are confirmed by adopting equivalent analysis based on the ontology language. The ambiguity and the repeated problems are eliminated through entity disambiguation, so that knowledge fusion based on the fact that the client is an ontology is finally realized. And then constructing a graph knowledge base in a data-driven form, wherein the knowledge base is the graph knowledge base. The graph knowledge base can more intuitively embody the mode that a client is taken as an ontology, all information related to the client is connected in the mode of nodes, and the mode based on the mesh node centered on the client is formed. Because the graph knowledge base adopts node connection, knowledge analysis and knowledge processing can be realized based on graph analysis, and certain client related knowledge data in the graph knowledge base can be updated.
Optionally, fig. 5 is a flowchart of another client behavior prediction method according to the first embodiment of the present application, as shown in fig. 5, in step 203, the obtaining a prediction result according to the matching degree between the client to be predicted and the predicted product includes:
step 501, if the matching degree between the client to be predicted and the predicted product exceeds a preset threshold, determining that the predicted result is that the client to be predicted intends to obtain the predicted product;
step 502, if the matching degree between the client to be predicted and the predicted product does not exceed the threshold, determining that the predicted result is that the client to be predicted does not intend to obtain the predicted product.
In combination with the scenario example, the matching degree may take the form of a percentage, and a threshold value is set for the matching degree, for example, the threshold value is set to 50%, when the matching degree between the client to be predicted and the predicted product exceeds 50%, the predicted result is determined to be that the client to be predicted intends to obtain the predicted product, and the obtaining information about the predicted product may be transmitted to the client to be predicted. And when the matching degree between the client to be predicted and the predicted product is not more than 50%, judging that the predicted result is that the client to be predicted does not intend to obtain the predicted product.
In the embodiment, a k-means clustering algorithm is performed on actually acquired client data to obtain a client classification report and a classification client data report, a database is created based on the client classification report and the classification client data report, and the behavior of a client to be predicted is predicted through the client data in the database.
Example two
Fig. 6 is a schematic structural diagram of a customer behavior prediction apparatus according to a second embodiment of the present application, where the apparatus includes:
an obtaining module 61, configured to obtain and optimize client data of a plurality of clients, to obtain optimized client data, where the client data includes a client value and a plurality of influencing factors that influence the client value;
the processing module 62 is configured to perform k-means clustering algorithm analysis on the client value in the optimized client data to obtain a client classification report, and perform k-means clustering algorithm analysis on a plurality of influence factors influencing the client value in the optimized client data to obtain a classified client data report corresponding to each influence factor; and constructing a knowledge base based on the customer classification report and the classified customer data report corresponding to each influencing factor;
The input module 63 is configured to input customer data of a customer to be predicted and a predicted product into a prediction model, so that the prediction model searches the knowledge base based on a search engine to determine a first customer similar to the customer to be predicted, calculates a matching degree between the customer to be predicted and the predicted product based on the customer data optimized with the first customer, and obtains a prediction result according to the matching degree between the customer to be predicted and the predicted product, where the prediction result is used to characterize whether the customer to be predicted has an intention to obtain the predicted product.
Taking a bank as an example in combination with a scene example, information such as the asset value of a bank customer in the bank, the real estate quantity under the name and the average consumption level in recent years can be taken as customer data, so the acquisition module 61 can collect customer data of customers in a row from a human perspective, but the currently obtained customer data is generally initial data, has low reliability, needs to be preprocessed, and mainly optimizes the customer data through preprocessing to obtain optimized customer data. The client data includes a client value of the client and a plurality of influencing factors influencing the client value, for example, in the case of client data of a bank client, the asset value, the real estate quantity in the bank and the average consumption level in recent years of the bank client are influencing factors influencing the client value, the client value is determined by the asset value, the real estate quantity in the bank and the average consumption level in recent years of the bank client, for example, the influencing factors, namely the real estate quantity in the bank client, can be converted into market assets, and the sum of the asset value in the bank, the real estate quantity in the bank and the average consumption level in recent years is taken as the client value of the bank client.
The processing module 62 analyzes the client value in the client data and each influence factor influencing the client value by a k-means clustering algorithm (k-means clustering algorithm), completes the feature selection and extraction of the data according to a similarity principle, and then performs similarity calculation between data objects; and finally, grouping the data objects according to the similarity to obtain a client classification report which is grouped according to the client value and a classification client data report which is respectively grouped according to each influencing factor. The K-means clustering algorithm is an iterative solution clustering analysis algorithm, and comprises the steps of dividing data into K groups, randomly selecting K objects as initial clustering centers, calculating the distance between each object and each seed clustering center, and distributing each object to the closest clustering center. The cluster centers and the objects assigned to them represent a cluster. For each sample assigned, the cluster center of the cluster is recalculated based on the existing objects in the cluster. This process will repeat until a certain termination condition is met. The termination condition may be that no or a minimum number of objects are reassigned to different clusters, no or a minimum number of cluster centers are changed again, and the sum of squares of errors is locally minimum.
The prediction module 63 establishes a database by using the obtained client classification report grouped by client value and the classified client data report respectively grouped by each influencing factor as data sources of the database, adds a prediction model with a search function into the database, inputs the client data of the client to be predicted and the predicted product into the prediction model, searches the data in the database based on the client data of the client to be predicted, finds the client data similar to the client to be predicted, and judges the matching degree between the client to be predicted and the predicted product based on the client data similar to the client to be predicted, wherein the matching degree can be in the form of percentage, and judges whether the client to be predicted has intention to obtain the predicted product according to the matching degree between the client to be predicted and the predicted product. The customer data of the customer to be predicted input into the prediction model may be the customer value of the customer to be predicted, or may be the value of any influencing factor influencing the customer value. For example, if the customer data of the customer to be predicted inputted into the prediction model is a customer value, the prediction model screens the customer data of all bank customers consistent with the customer value of the customer to be predicted from the database based on the customer value of the customer to be predicted, and gives a matching degree with respect to the predicted product based on the customer data of all bank customers. If the predicted product is a product for obtaining real estate, the customer data of all banking customers screened by the prediction model and consistent with the customer value of the customer to be predicted show that the customer value of the banking customers is generally higher, but the number of real estate is smaller, which means that the banking customers have the ability to obtain real estate and generally need real estate, and the matching degree is higher. If the customer value of such banking customers is generally high, but there is a large amount of real estate in the name, then the degree of matching given is low.
According to the method, a client classification report and a classified client data report are obtained through a k-means clustering algorithm on actually obtained client data, a database is created based on the client classification report and the classified client data report, and the behavior of a client to be predicted is predicted through the client data in the database.
Optionally, the acquiring module 61 is specifically configured to acquire client data of the plurality of clients;
the obtaining module 61 is specifically further configured to sequentially perform an operation of removing duplicate values, an operation of filling missing data, and a linear interpolation operation on the client data of the plurality of clients, so as to obtain the optimized client data.
In combination with the scene example, and with the actual situation of the bank, the acquisition module 61 gathers backbone service personnel and existing system data, collects customer data such as asset values, real properties under the name and average consumption level of the last three years of customers in the bank from an artificial angle, converts the influencing factor of the real properties under the name of the bank customer into market assets, converts the asset values in the bank, the real properties under the name into the sum of the market assets and the average consumption level in recent years as the customer value of the bank customer, and sorts the customer data of the customers according to the customer value from low to high. And performing first data cleaning by using a repeated observation processing method based on Python, and removing the repeated value after detecting the repeated observation by using a redundant method, wherein a function in a redundant method Pandas library is used for searching and marking the repeated value. Specifically, if the duplicate method detects that the same client and client value exist in the acquired client data, the duplicate client and client value is deleted. For example, if two identical clients a exist in the acquired client data and the client values of the two clients a are also identical, the client value of one client a and the client value of the client a are reserved, and the client value of the other client a and the client a which are duplicated is deleted. Then, the deletion value processing method based on Python is used for carrying out the second data cleaning, and firstly, the data filtering dropana method is carried out, wherein the dropana method is a method for deleting the deletion value in the Python pandas library, and then, the data filling filter method is carried out, and the filter method pandas library provides a very useful function, and the main function of the filter method panas library is to fill the deletion value. If there is a missing item in the acquired customer data, for example, if there is an empty asset value of a customer, the asset value of the customer is completely filled after the second cleaning of the customer data, and the missing values of other customers are also completely filled. After the multi-client data is cleaned twice, the abnormal value in the client data is required to be processed, the abnormal value in the client data is mainly subjected to the complementary processing through the linear interpolation, and the optimized client data is obtained after the data is cleaned twice and the linear interpolation is processed, so that the acquired client data has higher credibility.
Optionally, the processing module 62 is specifically configured to extract data associated with a plurality of preset feature words from the classified client data report corresponding to each influence factor in the client classified report, so as to obtain knowledge data;
the processing module 62 is specifically further configured to correlate the knowledge data according to the order of the corresponding client values in the knowledge data from high to low to obtain a knowledge structure;
the processing module 62 is specifically further configured to perform knowledge fusion on the knowledge structure with the client as a body, and construct a knowledge base from the knowledge fusion result in a data driven manner.
In combination with the scenario example, the processing module 62 processes the client classification report and the classified client data report corresponding to each influencing factor by using a Neuro-Linguistic Programming (NLP) natural language processing technology, specifically presets a plurality of feature words, for example, sets the feature words as "gold", "100", "dollar", and performs entity knowledge extraction, relationship extraction and attribute extraction related to the feature words from the classified client data report corresponding to each influencing factor in the client classification report, so as to obtain knowledge data related to the feature words. For example, the asset value of the client a is 100 ten thousand dollars in the client classification report corresponding to each influencing factor, so that the relevant knowledge data is obtained as client a→ (possession) →100→ten thousand →dollars, and all the knowledge data associated with "gold", "100", "dollars" are extracted in this way. In all the extracted knowledge data, a plurality of clients may be included, and all the extracted knowledge data may be sequenced from high to low according to the client value of the clients to obtain a knowledge structure composed of the plurality of extracted knowledge data. And carrying out knowledge fusion on the obtained knowledge data according to the client as the body, and fusing the independently flattened knowledge data into a net knowledge structure with the client as the body. Specifically, similarity of entity attributes is calculated through coreference resolution, and correct entity objects in the database are confirmed by adopting equivalent analysis based on the ontology language. The ambiguity and the repeated problems are eliminated through entity disambiguation, so that knowledge fusion based on the fact that the client is an ontology is finally realized. And then constructing a graph knowledge base in a data-driven form, wherein the knowledge base is the graph knowledge base. The graph knowledge base can more intuitively embody the mode that a client is taken as an ontology, all information related to the client is connected in the mode of nodes, and the mode based on the mesh node centered on the client is formed. Because the graph knowledge base adopts node connection, knowledge analysis and knowledge processing can be realized based on graph analysis, and certain client related knowledge data in the graph knowledge base can be updated.
In combination with the scenario example, the matching degree may take the form of a percentage, and a threshold value is set for the matching degree, for example, the threshold value is set to 50%, when the matching degree between the client to be predicted and the predicted product exceeds 50%, the predicted result is determined to be that the client to be predicted intends to obtain the predicted product, and the obtaining information about the predicted product may be transmitted to the client to be predicted. And when the matching degree between the client to be predicted and the predicted product is not more than 50%, judging that the predicted result is that the client to be predicted does not intend to obtain the predicted product.
In the embodiment, a k-means clustering algorithm is performed on actually acquired client data to obtain a client classification report and a classification client data report, a database is created based on the client classification report and the classification client data report, and the behavior of a client to be predicted is predicted through the client data in the database.
Example III
Fig. 7 is a schematic structural diagram of an electronic device according to a third embodiment of the present application, as shown in fig. 7, where the electronic device includes:
a processor 291, the electronic device further comprising a memory 292; a communication interface (Communication Interface) 293 and bus 294 may also be included. The processor 291, the memory 292, and the communication interface 293 may communicate with each other via the bus 294. Communication interface 293 may be used for information transfer. The processor 291 may call logic instructions in the memory 292 to perform the method of the first embodiment described above.
Further, the logic instructions in memory 292 described above may be implemented in the form of software functional units and stored in a computer-readable storage medium when sold or used as a stand-alone product.
The memory 292 is a computer readable storage medium, and may be used to store a software program, a computer executable program, and program instructions/modules corresponding to the methods in the embodiments of the present application. The processor 291 executes the functional applications and data processing by running the software programs, instructions and modules stored in the memory 292, i.e., implements the method of the first embodiment described above.
Memory 292 may include a storage program area that may store an operating system, at least one application program required for functionality, and a storage data area; the storage data area may store data created according to the use of the terminal device, etc. Further, memory 292 may include high-speed random access memory, and may also include non-volatile memory.
Embodiments of the present application provide a non-transitory computer-readable storage medium having stored therein computer-executable instructions that, when executed by a processor, are configured to implement a method as described in the previous embodiments.
Example IV
The embodiment of the application provides a computer program product, which comprises a computer program, and the computer program is executed by a processor to realize the private network data acquisition method provided by any embodiment of the application.
Example five
Fig. 8 is a block diagram of a terminal device, which may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, an exercise device, a personal digital assistant, etc., according to an exemplary embodiment.
The apparatus 800 may include one or more of the following components: a processing component 802, a memory 804, a power component 806, a multimedia component 808, an audio component 810, an input/output (I/O) interface 812, a sensor component 814, and a communication component 816.
The processing component 802 generally controls overall operation of the apparatus 800, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing component 802 may include one or more processors 820 to execute instructions to perform all or part of the steps of the methods described above. Further, the processing component 802 can include one or more modules that facilitate interactions between the processing component 802 and other components. For example, the processing component 802 can include a multimedia module to facilitate interaction between the multimedia component 808 and the processing component 802.
The memory 804 is configured to store various types of data to support operations at the apparatus 800. Examples of such data include instructions for any application or method operating on the device 800, contact data, phonebook data, messages, pictures, videos, and the like. The memory 804 may be implemented by any type or combination of volatile or nonvolatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk.
The power supply component 806 provides power to the various components of the device 800. The power components 806 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for the device 800.
The multimedia component 808 includes a screen between the device 800 and the client that provides an output interface. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a customer. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensor may sense not only the boundary of the action of a touch or a slide, but also the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front camera and/or a rear camera. The front camera and/or the rear camera may receive external multimedia data when the apparatus 800 is in an operational mode, such as a photographing mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have focal length and optical zoom capabilities.
The audio component 810 is configured to output and/or input audio signals. For example, the audio component 810 includes a Microphone (MIC) configured to receive external audio signals when the device 800 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may be further stored in the memory 804 or transmitted via the communication component 816. In some embodiments, audio component 810 further includes a speaker for outputting audio signals.
The I/O interface 812 provides an interface between the processing component 802 and peripheral interface modules, which may be a keyboard, click wheel, buttons, etc. These buttons may include, but are not limited to: homepage button, volume button, start button, and lock button.
The sensor assembly 814 includes one or more sensors for providing status assessment of various aspects of the device 800. For example, the sensor assembly 814 may detect the on/off state of the device 800, the relative positioning of the components, such as the display and keypad of the device 800, the sensor assembly 814 may also detect a change in position of the device 800 or a component of the device 800, the presence or absence of customer contact with the device 800, the orientation or acceleration/deceleration of the device 800, and a change in temperature of the device 800. The sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an acceleration sensor, a gyroscopic sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.
The communication component 816 is configured to facilitate communication between the apparatus 800 and other devices, either in a wired or wireless manner. The device 800 may access a wireless network based on a communication standard, such as WiFi,2G or 3G, or a combination thereof. In one exemplary embodiment, the communication component 816 receives broadcast signals or broadcast related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, the communication component 816 further includes a Near Field Communication (NFC) module to facilitate short range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, ultra Wideband (UWB) technology, bluetooth (BT) technology, and other technologies.
In an exemplary embodiment, the apparatus 800 may be implemented by one or more Application Specific Integrated Circuits (ASICs), digital Signal Processors (DSPs), digital Signal Processing Devices (DSPDs), programmable Logic Devices (PLDs), field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic elements for executing the methods described above.
In an exemplary embodiment, a non-transitory computer readable storage medium is also provided, such as memory 804 including instructions executable by processor 820 of apparatus 800 to perform the above-described method. For example, the non-transitory computer readable storage medium may be ROM, random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.
A non-transitory computer readable storage medium, which when executed by a processor of a terminal device, causes the terminal device to perform the split screen processing method of the terminal device.
Other embodiments of the application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. This application is intended to cover any variations, uses, or adaptations of the application following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the application pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.
It is to be understood that the application is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the application is limited only by the appended claims.
Claims (10)
1. A method of customer behavior prediction, the method comprising:
acquiring and optimizing client data of a plurality of clients to obtain optimized client data, wherein the client data comprises client values and a plurality of influencing factors influencing the client values;
Performing k-means clustering algorithm analysis on the client value in the optimized client data to obtain a client classification report, and performing k-means clustering algorithm analysis on a plurality of influence factors influencing the client value in the optimized client data to obtain a classification client data report corresponding to each influence factor; and constructing a knowledge base based on the customer classification report and the classified customer data report corresponding to each influencing factor;
inputting client data of clients to be predicted and predicted products into a prediction model, so that the prediction model searches the knowledge base based on a search engine to determine a first client similar to the clients to be predicted, calculates the matching degree between the clients to be predicted and the predicted products based on the client data optimized with the first client, and obtains a prediction result according to the matching degree between the clients to be predicted and the predicted products, wherein the prediction result is used for representing whether the clients to be predicted intend to obtain the predicted products.
2. The method of claim 1, wherein the obtaining and optimizing the customer data of the plurality of customers to obtain optimized customer data comprises:
Acquiring client data of the plurality of clients;
and sequentially performing repeated value removing operation, missing data filling operation and linear interpolation operation on the client data of the clients to obtain the optimized client data.
3. The method of claim 1, wherein the constructing a knowledge base based on the customer classification report and the classified customer data report corresponding to each influencing factor comprises:
extracting data associated with a plurality of preset feature words from the classified client data report corresponding to each influence factor in the client classified report to obtain knowledge data;
according to the sequence of the corresponding client value in the knowledge data from high to low, correlating the knowledge data to obtain a knowledge structure;
and carrying out knowledge fusion on the knowledge structure by taking the client as a body, and constructing a knowledge base by using a data-driven form through the knowledge fusion result.
4. The method according to claim 1, wherein obtaining the prediction result according to the matching degree between the client to be predicted and the predicted product comprises:
if the matching degree between the client to be predicted and the predicted product exceeds a preset threshold, judging that the predicted result is that the client to be predicted is intended to obtain the predicted product;
And if the matching degree between the client to be predicted and the predicted product does not exceed the threshold value, judging that the predicted result is that the client to be predicted does not intend to obtain the predicted product.
5. The method of any one of claims 1-4, wherein the knowledge base is a graph knowledge base.
6. A customer behavior prediction apparatus, the apparatus comprising:
the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring and optimizing client data of a plurality of clients to obtain optimized client data, and the client data comprises client values and a plurality of influence factors influencing the client values;
the processing module is used for carrying out k-means clustering algorithm analysis on the client value in the optimized client data to obtain a client classification report, and respectively carrying out k-means clustering algorithm analysis on a plurality of influence factors influencing the client value in the optimized client data to obtain a classification client data report corresponding to each influence factor; and constructing a knowledge base based on the customer classification report and the classified customer data report corresponding to each influencing factor;
the input module is used for inputting the client data of the client to be predicted and the predicted product into the prediction model, so that the prediction model searches the knowledge base based on a search engine to determine a first client similar to the client to be predicted, calculates the matching degree between the client to be predicted and the predicted product based on the client data optimized with the first client, and obtains a prediction result according to the matching degree between the client to be predicted and the predicted product, wherein the prediction result is used for representing whether the client to be predicted is intended to obtain the predicted product.
7. The apparatus of claim 6, wherein the device comprises a plurality of sensors,
the acquisition module is specifically configured to acquire client data of the plurality of clients;
the acquisition module is specifically further configured to sequentially perform an operation of removing duplicate values, an operation of filling missing data, and a linear interpolation operation on the client data of the plurality of clients, so as to obtain the optimized client data.
8. The apparatus of claim 6, wherein the device comprises a plurality of sensors,
the processing module is specifically configured to extract data associated with a plurality of preset feature words from the classified client data report corresponding to each influence factor in the client classified report, so as to obtain knowledge data;
the processing module is specifically configured to correlate the knowledge data according to the order of the corresponding client values in the knowledge data from high to low to obtain a knowledge structure;
the processing module is specifically further configured to perform knowledge fusion on the knowledge structure with the client as a body, and construct a knowledge base from the knowledge fusion result in a data driven manner.
9. An electronic device, comprising: a processor, and a memory communicatively coupled to the processor;
The memory stores computer-executable instructions;
the processor executes computer-executable instructions stored in the memory to implement the method of any one of claims 1-5.
10. A computer readable storage medium having stored therein computer executable instructions which when executed by a processor are adapted to carry out the method of any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311152672.XA CN117196692A (en) | 2023-09-07 | 2023-09-07 | Client behavior prediction method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311152672.XA CN117196692A (en) | 2023-09-07 | 2023-09-07 | Client behavior prediction method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117196692A true CN117196692A (en) | 2023-12-08 |
Family
ID=88986403
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311152672.XA Pending CN117196692A (en) | 2023-09-07 | 2023-09-07 | Client behavior prediction method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117196692A (en) |
-
2023
- 2023-09-07 CN CN202311152672.XA patent/CN117196692A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11449766B2 (en) | Invitation behavior prediction method and apparatus, and storage medium | |
| CN109543566B (en) | Information processing method and device, electronic equipment and storage medium | |
| US20220084056A1 (en) | Methods and apparatuses for managing visitor information, electronic devices and storage media | |
| CN111859020B (en) | Recommendation method, recommendation device, electronic equipment and computer readable storage medium | |
| CN112426724B (en) | Matching method and device for game users, electronic equipment and storage medium | |
| CN107193983A (en) | Image search method and device | |
| CN106126592B (en) | Processing method and device for search data | |
| CN112949172A (en) | Data processing method and device, machine readable medium and equipment | |
| CN112783779B (en) | Method and device for generating test case, electronic equipment and storage medium | |
| CN113128437A (en) | Identity recognition method and device, electronic equipment and storage medium | |
| CN116127353A (en) | Classification method, classification model training method, equipment and medium | |
| CN111651627A (en) | Data processing method and device, electronic equipment and storage medium | |
| CN113590605B (en) | Data processing method, device, electronic equipment and storage medium | |
| CN117196692A (en) | Client behavior prediction method, device, equipment and storage medium | |
| CN116167454A (en) | Intelligent two-classification model training method and device | |
| CN112884040B (en) | Training sample data optimization method, system, storage medium and electronic equipment | |
| CN113254726B (en) | Account grouping method and device, electronic equipment and storage medium | |
| CN112992152B (en) | Individual-soldier voiceprint recognition system and method, storage medium and electronic equipment | |
| CN114117058A (en) | Account information determination method and device, electronic equipment and storage medium | |
| CN114359783A (en) | Abnormal event detection method, device and equipment | |
| CN117034094B (en) | Account type prediction method and account type prediction device | |
| CN115525635A (en) | Session data processing method, device, equipment and medium | |
| CN115361588B (en) | Object display method and device, electronic equipment and storage medium | |
| CN115225702B (en) | Information pushing method and device, electronic equipment and storage medium | |
| CN118276901A (en) | Method, device, equipment, medium and program product for generating software update strategy |
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 |