CN114020687B - User retention analysis method, device, equipment and storage medium - Google Patents

User retention analysis method, device, equipment and storage medium Download PDF

Info

Publication number
CN114020687B
CN114020687B CN202111306579.0A CN202111306579A CN114020687B CN 114020687 B CN114020687 B CN 114020687B CN 202111306579 A CN202111306579 A CN 202111306579A CN 114020687 B CN114020687 B CN 114020687B
Authority
CN
China
Prior art keywords
information
index
initial
user
characteristic
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.)
Active
Application number
CN202111306579.0A
Other languages
Chinese (zh)
Other versions
CN114020687A (en
Inventor
熊龙飞
张茜
叶聆音
许春林
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ping An Technology Shenzhen Co Ltd
Original Assignee
Ping An Technology Shenzhen Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Ping An Technology Shenzhen Co Ltd filed Critical Ping An Technology Shenzhen Co Ltd
Priority to CN202111306579.0A priority Critical patent/CN114020687B/en
Publication of CN114020687A publication Critical patent/CN114020687A/en
Application granted granted Critical
Publication of CN114020687B publication Critical patent/CN114020687B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/10—File systems; File servers
    • G06F16/11—File system administration, e.g. details of archiving or snapshots
    • G06F16/113—Details of archiving
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/10—Text processing
    • G06F40/166—Editing, e.g. inserting or deleting
    • G06F40/186—Templates

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention relates to artificial intelligence and provides a user retention analysis method, device, equipment and storage medium. According to the method, sample information of a plurality of sample users on a plurality of initial indexes can be obtained, characterization information of the plurality of sample users on the plurality of initial indexes is generated according to the sample information, the characterization information is subjected to standardized processing, the characteristic information of the plurality of sample users on the plurality of initial indexes is obtained, the index characteristic value on each initial index is analyzed according to the characteristic information, the target index is selected from the plurality of initial indexes according to the index characteristic value, when a user retention analysis request is received, user information of a user to be tested on the target index is obtained according to the user retention analysis request, and a retention result of the user to be tested is generated according to the user information and the target index, so that the retention analysis accuracy and efficiency can be improved. Furthermore, the present invention also relates to blockchain techniques, where the persisted results may be stored in the blockchain.

Description

User retention analysis method, device, equipment and storage medium
Technical Field
The present invention relates to the field of artificial intelligence technologies, and in particular, to a method, an apparatus, a device, and a storage medium for user retention analysis.
Background
With the development of artificial intelligence, retention analysis algorithms have also developed. In the existing user retention analysis, the loss condition of the user can be determined by analyzing the behaviors of the user in a plurality of preset label dimensions. However, the number of dimensions of the preset label dimensions is large, which results in low analysis efficiency of the user churn situation.
In order to improve the analysis efficiency of the user retention analysis, a factor analysis algorithm is adopted to perform dimension reduction processing on the plurality of preset label dimensions at present, however, the method reduces the number of dimensions and simultaneously causes loss of important information in user information, so that the accuracy of the user retention analysis is low.
Therefore, on the premise of ensuring the accuracy of the user retention analysis, how to improve the efficiency of the user retention analysis is a problem to be solved.
Disclosure of Invention
In view of the foregoing, it is necessary to provide a user retention analysis method, apparatus, device, and storage medium, which can improve the efficiency of user retention analysis while ensuring the accuracy of user retention analysis.
In one aspect, the present invention provides a method for user retention analysis, where the method for user retention analysis includes:
acquiring sample information of a plurality of sample users on a plurality of initial indexes;
Generating characterization information of the plurality of sample users on the plurality of initial indexes according to the sample information;
carrying out standardization processing on the characterization information to obtain the characteristic information of the plurality of sample users on the plurality of initial indexes;
Analyzing index characteristic values on each initial index according to the characteristic information;
selecting a target index from the plurality of initial indexes according to the index characteristic value;
when a user retention analysis request is received, acquiring user information of a user to be detected on the target index according to the user retention analysis request;
and generating a retention result of the user to be tested according to the user information and the target index.
According to a preferred embodiment of the present invention, the generating characterization information of the plurality of sample users on the plurality of initial indicators according to the sample information includes:
Comparing the information format of the sample information with the configuration format in the type template, and determining the type corresponding to the configuration format identical to the information format as the index type of the plurality of initial indexes;
determining an initial index with the index type not being a preset type as a characteristic index;
Screening information corresponding to the initial index with the index type not being the preset type from the sample information as first characteristic information, and determining the rest information except the first characteristic information in the sample information as second characteristic information;
Mapping the first characteristic information to obtain numerical value information;
Determining the numerical information and the second characteristic information as target characteristic information;
acquiring information of each sample user on the plurality of initial indexes from the target characteristic information as row vectors;
and splicing the row vectors of each sample user to obtain the characterization information.
According to a preferred embodiment of the present invention, the normalizing the characterization information to obtain the feature information of the plurality of sample users on the plurality of initial indexes includes:
calculating average index information of the plurality of sample users on each initial index according to the characterization information;
analyzing the characterization information and the average index information according to the following formula to obtain the difference information of each initial index:
Wherein S refers to the difference information, x ij refers to the characterization information of the ith sample user on the jth initial index, Average index information of the jth initial index is referred to, and n is referred to the total user amount of the plurality of sample users;
And carrying out standardization processing on the characterization information according to the average index information and the difference information to obtain the characteristic information.
According to a preferred embodiment of the present invention, the analyzing the index feature value on each initial index according to the feature information includes:
calculating the characteristic information according to the following formula to obtain the index correlation degree of any two initial indexes:
Wherein r hq refers to the index correlation degree between the h initial index and the q initial index, n refers to the total user quantity, X kh refers to the characteristic information of the kth sample user on the h initial index, and X kq refers to the characteristic information of the kth sample user on the q initial index;
analyzing the discrete degree of the characteristic information on each initial index to obtain the information discrete degree of each initial index;
sequentially sequencing the index relativity to obtain an initial diagonal matrix, and filling the initial diagonal matrix according to the information dispersion to obtain an index feature matrix;
And calculating the characteristic value of the index characteristic matrix as the index characteristic value.
According to a preferred embodiment of the present invention, the selecting a target index from the plurality of initial indexes according to the index feature value includes:
selecting an index characteristic value which is larger than or equal to a preset characteristic threshold value from the index characteristic values as a target characteristic value, and determining an initial index corresponding to the target characteristic value as an index to be selected;
sorting the indexes to be selected according to the sequence from the big to the small of the target characteristic value to obtain a characteristic sequence;
calculating an accumulated contribution rate according to the feature sequence and the target feature value:
Wherein P t refers to the cumulative contribution rate of the first t indexes to be selected in the feature sequence, λ k refers to the target feature values corresponding to the first k indexes to be selected in the feature sequence, and t=1, 2,3 …, m;
And if the accumulated contribution rate is greater than or equal to a preset contribution threshold, determining the first t indexes to be selected as the target indexes.
According to a preferred embodiment of the present invention, the obtaining, according to the user retention analysis request, user information of the user to be tested on the target index includes:
Analyzing the message of the user retention analysis request to obtain data information carried by the message;
extracting a user identification code from the data information, and determining a binding terminal associated with the user identification code;
Generating an information acquisition request according to the user identification code and the target index, and sending the information acquisition request to the binding terminal;
after a preset time interval, receiving an acquisition response result sent by the binding terminal, and extracting a secret key from the acquisition response result;
acquiring ciphertext information corresponding to the user identification code;
and decrypting the ciphertext information based on the key, and determining the information which is successfully decrypted as the user information.
According to a preferred embodiment of the present invention, the user information includes information to be measured of the user to be measured on each target index, and the generating the retention result of the user to be measured according to the user information and the target index includes:
normalizing the index characteristic value corresponding to the target index to obtain an index weight value of each target index;
calculating the product of each piece of information to be detected and each index weight to obtain the score of the user to be detected on each target index;
and calculating the sum of a plurality of scores to obtain the retention result.
On the other hand, the invention also provides a user retention analysis device, which comprises:
The acquisition unit is used for acquiring sample information of a plurality of sample users on a plurality of initial indexes;
The generation unit is used for generating characterization information of the plurality of sample users on the plurality of initial indexes according to the sample information;
The processing unit is used for carrying out standardized processing on the characterization information to obtain the characteristic information of the plurality of sample users on the plurality of initial indexes;
an analysis unit for analyzing the index feature value on each initial index according to the feature information;
the selecting unit is used for selecting a target index from the plurality of initial indexes according to the index characteristic value;
The acquisition unit is further used for acquiring user information of the user to be detected on the target index according to the user retention analysis request when the user retention analysis request is received;
The generating unit is further configured to generate a retention result of the user to be tested according to the user information and the target index.
In another aspect, the present invention also proposes an electronic device, including:
A memory storing computer readable instructions; and
And a processor executing computer readable instructions stored in the memory to implement the user retention analysis method.
In another aspect, the present invention also proposes a computer readable storage medium having stored therein computer readable instructions that are executed by a processor in an electronic device to implement the user retention analysis method.
According to the technical scheme, the influence of scale difference among different initial indexes on the index characteristic values can be eliminated by carrying out standardized processing on the characterization information, so that the selection accuracy of the target indexes can be improved, the selection efficiency of the target indexes can be improved by analyzing the index characteristic values on each initial index, the number of the target indexes can be reduced by selecting the target indexes through the index characteristic values, the analysis efficiency of the retention results can be improved, the loss of important information in the initial indexes can be avoided, the selection accuracy of the target indexes is improved, and the analysis accuracy of the retention results can be ensured.
Drawings
FIG. 1 is a flow chart of a preferred embodiment of the user retention analysis method of the present invention.
FIG. 2 is a functional block diagram of a preferred embodiment of the user retention analysis device of the present invention.
Fig. 3 is a schematic structural diagram of an electronic device according to a preferred embodiment of the present invention for implementing a user retention analysis method.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in detail with reference to the accompanying drawings and specific embodiments.
FIG. 1 is a flow chart of a preferred embodiment of the user retention analysis method of the present invention. The order of the steps in the flowchart may be changed and some steps may be omitted according to various needs.
The user retention analysis method can acquire and process related data based on artificial intelligence technology. Wherein artificial intelligence (ARTIFICIAL INTELLIGENCE, AI) is the theory, method, technique, and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend, and expand human intelligence, sense the environment, acquire knowledge, and use knowledge to obtain optimal results.
Artificial intelligence infrastructure technologies generally include 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 other directions.
The user retention analysis method is applied to one or more electronic devices, wherein the electronic devices are devices capable of automatically performing numerical calculation and/or information processing according to preset or stored computer readable instructions, and the hardware of the electronic devices comprises, but is not limited to, microprocessors, application SPECIFIC INTEGRATED Circuits (ASICs), programmable gate arrays (Field-Programmable GATE ARRAY, FPGA), digital signal processors (DIGITAL SIGNAL processors, DSPs), embedded devices and the like.
The electronic device may be any electronic product that can interact with a user in a human-computer manner, such as a Personal computer, a tablet computer, a smart phone, a Personal digital assistant (Personal DIGITAL ASSISTANT, PDA), a game console, an interactive internet protocol television (Internet Protocol Television, IPTV), a smart wearable device, etc.
The electronic device may comprise a network device and/or a user device. Wherein the network device includes, but is not limited to, a single network electronic device, a group of electronic devices made up of multiple network electronic devices, or a Cloud based Cloud Computing (Cloud Computing) made up of a large number of hosts or network electronic devices.
The network on which the electronic device is located includes, but is not limited to: the internet, wide area networks, metropolitan area networks, local area networks, virtual private networks (Virtual Private Network, VPN), etc.
S10, sample information of a plurality of sample users on a plurality of initial indexes is acquired.
In at least one embodiment of the present invention, the plurality of sample users refer to test users for performing the dimension reduction processing on the plurality of initial indexes, where the plurality of sample users may be internal employees of an enterprise, and the present invention is not limited to the plurality of sample users.
The plurality of initial indicators refer to preset labels for analyzing the user loss, for example, the plurality of initial indicators may include, but are not limited to: a tag indicating user liveness, such as attendance days, effective contact numbers, etc., wherein the effective contact numbers refer to the total number of people who establish contact in an enterprise.
The sample information refers to relevant information corresponding to the plurality of sample users on the plurality of initial indexes, for example, sample information of sample user a on a attendance day label is 18 days/month.
In at least one embodiment of the present invention, the electronic device may obtain the sample information from a user library according to the plurality of sample users and the plurality of initial indicators.
S11, generating characterization information of the plurality of sample users on the plurality of initial indexes according to the sample information.
In at least one embodiment of the present invention, the characterization information refers to a quantized value indicating the sample information, for example, the characterization information may be a matrix, and each row vector in the matrix may be used to characterize the sample information of each sample user on the plurality of initial indicators. And the total element amount in the characterization information is the product result of the total user amount of the plurality of sample users and the total index amount of the plurality of initial indexes.
In at least one embodiment of the present invention, the generating, by the electronic device, characterization information of the plurality of sample users on the plurality of initial metrics according to the sample information includes:
Comparing the information format of the sample information with the configuration format in the type template, and determining the type corresponding to the configuration format identical to the information format as the index type of the plurality of initial indexes;
determining an initial index with the index type not being a preset type as a characteristic index;
Screening information corresponding to the initial index with the index type not being the preset type from the sample information as first characteristic information, and determining the rest information except the first characteristic information in the sample information as second characteristic information;
Mapping the first characteristic information to obtain numerical value information;
Determining the numerical information and the second characteristic information as target characteristic information;
acquiring information of each sample user on the plurality of initial indexes from the target characteristic information as row vectors;
and splicing the row vectors of each sample user to obtain the characterization information.
Wherein, the type template stores a plurality of mapping relations between configuration formats and types. The configuration formats are used for indicating variable formats corresponding to each type.
The index types include, but are not limited to: short integer, long integer, character type, etc.
The preset type refers to integer types such as short integer type, long integer type and the like.
Through analysis of the index types, the characteristic indexes can be accurately screened out, further, sample information corresponding to the characteristic indexes is mapped, generation of the numerical information is facilitated, and the characteristic information only contains integer type information, so that characteristic intuitiveness of the characteristic information to the plurality of initial indexes can be improved.
Specifically, the electronic device performs mapping processing on the first feature information, and the obtaining numerical value information includes:
Traversing a preset mapping table according to each character in the first characteristic information, and acquiring numbers corresponding to each character in the preset mapping table;
And splicing a plurality of numbers according to the character sequence of each character in the first characteristic information to obtain the numerical information.
Wherein, the preset mapping table stores mapping relations between a plurality of characters and a plurality of numbers.
The digits can be accurately obtained through the preset mapping table, and the numerical information can be accurately generated according to the character sequence.
And S12, carrying out standardization processing on the characterization information to obtain the characteristic information of the plurality of sample users on the plurality of initial indexes.
In at least one embodiment of the present invention, the feature information is information obtained after the normalization processing is performed on the characterization information, and the variation ranges of different initial indicators can be located in the same data interval by performing the normalization processing on the characterization information. For example, the variation range of the initial index a is [1000, 2000], the variation range of the initial index B is [0.01,1], and the variation range of the initial index a in the feature information can be [0,1] after the normalization processing is performed on the feature information, and the variation range of the initial index B is [0,1].
In at least one embodiment of the present invention, the electronic device performing normalization processing on the characterization information to obtain feature information of the plurality of sample users on the plurality of initial indexes includes:
calculating average index information of the plurality of sample users on each initial index according to the characterization information;
analyzing the characterization information and the average index information according to the following formula to obtain the difference information of each initial index:
Wherein S refers to the difference information, x ij refers to the characterization information of the ith sample user on the jth initial index, Average index information of the jth initial index is referred to, and n is referred to the total user amount of the plurality of sample users;
And carrying out standardization processing on the characterization information according to the average index information and the difference information to obtain the characteristic information.
The difference information of each initial index can be quickly generated through the average index information of each initial index, and then the characteristic information can be accurately generated according to the difference information of each initial index, so that the initial indexes with different scales are prevented from playing different roles in dimension reduction processing, and the generation accuracy of the target index is improved.
In this embodiment, by performing the standardization processing on the characterization information, it is possible to avoid that the initial indicators with large scale play a decisive role in performing the dimension reduction processing on the plurality of initial indicators, and the initial indicators with small scale are ignored in the dimension reduction processing, thereby improving the accuracy of the dimension reduction processing.
Specifically, the electronic device performs standardization processing on the characterization information according to the average index information and the difference information, and the obtaining the feature information includes:
Calculating the difference value between the characterization information and the average index information to obtain a deviation value;
And calculating the ratio of the deviation value in the difference information to obtain the characteristic information.
S13, analyzing index characteristic values on each initial index according to the characteristic information.
In at least one embodiment of the present invention, the index feature value is used to indicate the extent to which each initial index affects the user when performing a retention analysis.
In at least one embodiment of the present invention, the electronic device analyzing the index feature value on each initial index according to the feature information includes:
calculating the characteristic information according to the following formula to obtain the index correlation degree of any two initial indexes:
Wherein r hq refers to the index correlation degree between the h initial index and the q initial index, n refers to the total user quantity, X kh refers to the characteristic information of the kth sample user on the h initial index, and X kq refers to the characteristic information of the kth sample user on the q initial index;
analyzing the discrete degree of the characteristic information on each initial index to obtain the information discrete degree of each initial index;
sequentially sequencing the index relativity to obtain an initial diagonal matrix, and filling the initial diagonal matrix according to the information dispersion to obtain an index feature matrix;
And calculating the characteristic value of the index characteristic matrix as the index characteristic value.
For example: the index correlation degree includes: the index correlation degree of the 1 st initial index and the 2 nd initial index is-4, the index correlation degree of the 1 st initial index and the 3 rd initial index is 3, the index correlation degree of the 2 nd initial index and the 3 rd initial index is 2, and the index correlation degrees are sequentially ordered to obtain an initial diagonal matrix which is: The information dispersion of the 1 st initial index is 1, the information dispersion of the 2nd initial index is 3, and the information dispersion of the 3 rd initial index is 0, then the index feature matrix is: /(I)
The index feature matrix can be accurately generated through the index relevance and the information dispersion, and then the index feature values in the plurality of initial indexes are divided according to the index feature matrix, so that the plurality of initial indexes which are mutually relevant are favorably converted into irrelevant target indexes.
Specifically, the electronic device analyzing the degree of dispersion of the feature information on each initial indicator, and obtaining the information dispersion of each initial indicator includes:
and calculating the variance value of the characteristic information for each initial index to obtain the information dispersion.
The calculation process of the variance value belongs to the prior art, and the invention is not repeated.
S14, selecting a target index from the plurality of initial indexes according to the index characteristic value.
In at least one embodiment of the present invention, the target index refers to an initial index that the index feature value is greater than a preset feature threshold, and the cumulative contribution rate is greater than or equal to the preset contribution threshold.
In at least one embodiment of the present invention, the selecting, by the electronic device, a target index from the plurality of initial indexes according to the index feature value includes:
selecting an index characteristic value which is larger than or equal to a preset characteristic threshold value from the index characteristic values as a target characteristic value, and determining an initial index corresponding to the target characteristic value as an index to be selected;
sorting the indexes to be selected according to the sequence from the big to the small of the target characteristic value to obtain a characteristic sequence;
calculating an accumulated contribution rate according to the feature sequence and the target feature value:
Wherein P t refers to the cumulative contribution rate of the first t indexes to be selected in the feature sequence, λ k refers to the target feature values corresponding to the first k indexes to be selected in the feature sequence, and t=1, 2,3 …, m;
And if the accumulated contribution rate is greater than or equal to a preset contribution threshold, determining the first t indexes to be selected as the target indexes.
The preset feature threshold and the preset contribution threshold may be set according to requirements.
The indexes to be selected can be rapidly screened out through the preset characteristic threshold value, and then the indexes to be selected are ordered, so that the calculation of the accumulated contribution rate can be facilitated, and the loss of important information in the plurality of initial indexes can be avoided through the analysis of the accumulated contribution rate, so that the selection accuracy of the target indexes is improved.
And S15, when a user retention analysis request is received, acquiring user information of the user to be detected on the target index according to the user retention analysis request.
In at least one embodiment of the present invention, the information carried in the user retention analysis request includes, but is not limited to: and the user identification code of the user to be tested, wherein the user to be tested is a user needing to analyze the loss condition. The user information refers to information corresponding to the user to be tested on the target index.
In at least one embodiment of the present invention, the electronic device obtaining, according to the user retention analysis request, user information of the user to be tested on the target index includes:
Analyzing the message of the user retention analysis request to obtain data information carried by the message;
extracting a user identification code from the data information, and determining a binding terminal associated with the user identification code;
Generating an information acquisition request according to the user identification code and the target index, and sending the information acquisition request to the binding terminal;
after a preset time interval, receiving an acquisition response result sent by the binding terminal, and extracting a secret key from the acquisition response result;
acquiring ciphertext information corresponding to the user identification code;
and decrypting the ciphertext information based on the key, and determining the information which is successfully decrypted as the user information.
The user identification code is a code capable of uniquely indicating the user to be tested.
The binding terminal refers to a terminal associated with the user to be detected.
The preset time interval can be set according to requirements. For example, the preset time interval may be five minutes.
The ciphertext information and the binding terminal can be accurately determined through the user identification code, the acquisition accuracy of the user information is improved, leakage of the user information caused by the safety problem of the binding terminal can be avoided through setting of the preset time interval, the safety of the user information is improved, and the acquisition legitimacy of the user information can be improved through generation and transmission of the information acquisition request.
S16, generating a retention result of the user to be tested according to the user information and the target index.
It is emphasized that to further ensure the privacy and security of the above-mentioned persisted results, the above-mentioned persisted results may also be stored in a node of a blockchain.
In at least one embodiment of the present invention, the retention result is used to characterize the churn situation of the user to be tested. For example, if the retention result is 0.8, the user to be tested has a 20% loss probability.
In at least one embodiment of the present invention, the user information includes information to be measured of the user to be measured on each target index, and the generating, by the electronic device, a retention result of the user to be measured according to the user information and the target index includes:
normalizing the index characteristic value corresponding to the target index to obtain an index weight value of each target index;
calculating the product of each piece of information to be detected and each index weight to obtain the score of the user to be detected on each target index;
and calculating the sum of a plurality of scores to obtain the retention result.
For example, the index feature value corresponding to the target index 1 is 0.2, the index feature value corresponding to the target index 2 is 0.8, the index feature value corresponding to the target index 3 is 0.6, and after normalization processing, the index weight corresponding to the target index 1 is 0.125, the index weight corresponding to the target index 2 is 0.5, and the index weight corresponding to the target index 3 is 0.375.
By carrying out normalization processing on the index characteristic values, the analysis uniformity of the target index can be improved, and the accuracy of the retention result is improved.
According to the technical scheme, the influence of scale difference among different initial indexes on the index characteristic values can be eliminated by carrying out standardized processing on the characterization information, so that the selection accuracy of the target indexes can be improved, the selection efficiency of the target indexes can be improved by analyzing the index characteristic values on each initial index, the number of the target indexes can be reduced by selecting the target indexes through the index characteristic values, the analysis efficiency of the retention results can be improved, the loss of important information in the initial indexes can be avoided, the selection accuracy of the target indexes is improved, and the analysis accuracy of the retention results can be ensured.
FIG. 2 is a functional block diagram of a preferred embodiment of the user retention analysis device of the present invention. The user retention analysis device 11 includes an acquisition unit 110, a generation unit 111, a processing unit 112, an analysis unit 113, and a selection unit 114. The module/unit referred to herein is a series of computer readable instructions capable of being retrieved by the processor 13 and performing a fixed function and stored in the memory 12. In the present embodiment, the functions of the respective modules/units will be described in detail in the following embodiments.
The acquisition unit 110 acquires sample information on a plurality of initial indexes of a plurality of sample users.
In at least one embodiment of the present invention, the plurality of sample users refer to test users for performing the dimension reduction processing on the plurality of initial indexes, where the plurality of sample users may be internal employees of an enterprise, and the present invention is not limited to the plurality of sample users.
The plurality of initial indicators refer to preset labels for analyzing the user loss, for example, the plurality of initial indicators may include, but are not limited to: a tag indicating user liveness, such as attendance days, effective contact numbers, etc., wherein the effective contact numbers refer to the total number of people who establish contact in an enterprise.
The sample information refers to relevant information corresponding to the plurality of sample users on the plurality of initial indexes, for example, sample information of sample user a on a attendance day label is 18 days/month.
In at least one embodiment of the present invention, the obtaining unit 110 may obtain the sample information from a user library according to the plurality of sample users and the plurality of initial indicators.
The generating unit 111 generates characterization information of the plurality of sample users on the plurality of initial indicators according to the sample information.
In at least one embodiment of the present invention, the characterization information refers to a quantized value indicating the sample information, for example, the characterization information may be a matrix, and each row vector in the matrix may be used to characterize the sample information of each sample user on the plurality of initial indicators. And the total element amount in the characterization information is the product result of the total user amount of the plurality of sample users and the total index amount of the plurality of initial indexes.
In at least one embodiment of the present invention, the generating unit 111 generates characterization information of the plurality of sample users on the plurality of initial indicators according to the sample information includes:
Comparing the information format of the sample information with the configuration format in the type template, and determining the type corresponding to the configuration format identical to the information format as the index type of the plurality of initial indexes;
determining an initial index with the index type not being a preset type as a characteristic index;
Screening information corresponding to the initial index with the index type not being the preset type from the sample information as first characteristic information, and determining the rest information except the first characteristic information in the sample information as second characteristic information;
Mapping the first characteristic information to obtain numerical value information;
Determining the numerical information and the second characteristic information as target characteristic information;
acquiring information of each sample user on the plurality of initial indexes from the target characteristic information as row vectors;
and splicing the row vectors of each sample user to obtain the characterization information.
Wherein, the type template stores a plurality of mapping relations between configuration formats and types. The configuration formats are used for indicating variable formats corresponding to each type.
The index types include, but are not limited to: short integer, long integer, character type, etc.
The preset type refers to integer types such as short integer type, long integer type and the like.
Through analysis of the index types, the characteristic indexes can be accurately screened out, further, sample information corresponding to the characteristic indexes is mapped, generation of the numerical information is facilitated, and the characteristic information only contains integer type information, so that characteristic intuitiveness of the characteristic information to the plurality of initial indexes can be improved.
Specifically, the generating unit 111 performs mapping processing on the first feature information, and the obtaining numerical value information includes:
Traversing a preset mapping table according to each character in the first characteristic information, and acquiring numbers corresponding to each character in the preset mapping table;
And splicing a plurality of numbers according to the character sequence of each character in the first characteristic information to obtain the numerical information.
Wherein, the preset mapping table stores mapping relations between a plurality of characters and a plurality of numbers.
The digits can be accurately obtained through the preset mapping table, and the numerical information can be accurately generated according to the character sequence.
The processing unit 112 performs normalization processing on the characterization information to obtain feature information of the plurality of sample users on the plurality of initial indexes.
In at least one embodiment of the present invention, the feature information is information obtained after the normalization processing is performed on the characterization information, and the variation ranges of different initial indicators can be located in the same data interval by performing the normalization processing on the characterization information. For example, the variation range of the initial index a is [1000, 2000], the variation range of the initial index B is [0.01,1], and the variation range of the initial index a in the feature information can be [0,1] after the normalization processing is performed on the feature information, and the variation range of the initial index B is [0,1].
In at least one embodiment of the present invention, the processing unit 112 performs normalization processing on the characterization information, and obtaining the feature information of the plurality of sample users on the plurality of initial indexes includes:
calculating average index information of the plurality of sample users on each initial index according to the characterization information;
analyzing the characterization information and the average index information according to the following formula to obtain the difference information of each initial index:
Wherein S refers to the difference information, x ij refers to the characterization information of the ith sample user on the jth initial index, Average index information of the jth initial index is referred to, and n is referred to the total user amount of the plurality of sample users;
And carrying out standardization processing on the characterization information according to the average index information and the difference information to obtain the characteristic information.
The difference information of each initial index can be quickly generated through the average index information of each initial index, and then the characteristic information can be accurately generated according to the difference information of each initial index, so that the initial indexes with different scales are prevented from playing different roles in dimension reduction processing, and the generation accuracy of the target index is improved.
In this embodiment, by performing the standardization processing on the characterization information, it is possible to avoid that the initial indicators with large scale play a decisive role in performing the dimension reduction processing on the plurality of initial indicators, and the initial indicators with small scale are ignored in the dimension reduction processing, thereby improving the accuracy of the dimension reduction processing.
Specifically, the processing unit 112 performs normalization processing on the characterization information according to the average index information and the difference information, and the obtaining the feature information includes:
Calculating the difference value between the characterization information and the average index information to obtain a deviation value;
And calculating the ratio of the deviation value in the difference information to obtain the characteristic information.
The analysis unit 113 analyzes the index feature value on each initial index based on the feature information.
In at least one embodiment of the present invention, the index feature value is used to indicate the extent to which each initial index affects the user when performing a retention analysis.
In at least one embodiment of the present invention, the analyzing unit 113 analyzes the index feature value on each initial index according to the feature information includes:
calculating the characteristic information according to the following formula to obtain the index correlation degree of any two initial indexes:
Wherein r hq refers to the index correlation degree between the h initial index and the q initial index, n refers to the total user quantity, X kh refers to the characteristic information of the kth sample user on the h initial index, and X kq refers to the characteristic information of the kth sample user on the q initial index;
analyzing the discrete degree of the characteristic information on each initial index to obtain the information discrete degree of each initial index;
sequentially sequencing the index relativity to obtain an initial diagonal matrix, and filling the initial diagonal matrix according to the information dispersion to obtain an index feature matrix;
And calculating the characteristic value of the index characteristic matrix as the index characteristic value.
For example: the index correlation degree includes: the index correlation degree of the 1 st initial index and the 2 nd initial index is-4, the index correlation degree of the 1 st initial index and the 3 rd initial index is 3, the index correlation degree of the 2 nd initial index and the 3 rd initial index is 2, and the index correlation degrees are sequentially ordered to obtain an initial diagonal matrix which is: The information dispersion of the 1 st initial index is 1, the information dispersion of the 2nd initial index is 3, and the information dispersion of the 3 rd initial index is 0, then the index feature matrix is: /(I)
The index feature matrix can be accurately generated through the index relevance and the information dispersion, and then the index feature values in the plurality of initial indexes are divided according to the index feature matrix, so that the plurality of initial indexes which are mutually relevant are favorably converted into irrelevant target indexes.
Specifically, the analyzing unit 113 analyzes the degree of dispersion of the feature information on each initial index, and the obtaining of the information dispersion of each initial index includes:
and calculating the variance value of the characteristic information for each initial index to obtain the information dispersion.
The calculation process of the variance value belongs to the prior art, and the invention is not repeated.
The selecting unit 114 selects a target index from the plurality of initial indexes according to the index feature value.
In at least one embodiment of the present invention, the target index refers to an initial index that the index feature value is greater than a preset feature threshold, and the cumulative contribution rate is greater than or equal to the preset contribution threshold.
In at least one embodiment of the present invention, the selecting unit 114 selects a target index from the plurality of initial indexes according to the index feature value includes:
selecting an index characteristic value which is larger than or equal to a preset characteristic threshold value from the index characteristic values as a target characteristic value, and determining an initial index corresponding to the target characteristic value as an index to be selected;
sorting the indexes to be selected according to the sequence from the big to the small of the target characteristic value to obtain a characteristic sequence;
calculating an accumulated contribution rate according to the feature sequence and the target feature value:
Wherein P t refers to the cumulative contribution rate of the first t indexes to be selected in the feature sequence, λ k refers to the target feature values corresponding to the first k indexes to be selected in the feature sequence, and t=1, 2,3 …, m;
And if the accumulated contribution rate is greater than or equal to a preset contribution threshold, determining the first t indexes to be selected as the target indexes.
The preset feature threshold and the preset contribution threshold may be set according to requirements.
The indexes to be selected can be rapidly screened out through the preset characteristic threshold value, and then the indexes to be selected are ordered, so that the calculation of the accumulated contribution rate can be facilitated, and the loss of important information in the plurality of initial indexes can be avoided through the analysis of the accumulated contribution rate, so that the selection accuracy of the target indexes is improved.
When receiving the user retention analysis request, the obtaining unit 110 obtains the user information of the user to be tested on the target index according to the user retention analysis request.
In at least one embodiment of the present invention, the information carried in the user retention analysis request includes, but is not limited to: and the user identification code of the user to be tested, wherein the user to be tested is a user needing to analyze the loss condition. The user information refers to information corresponding to the user to be tested on the target index.
In at least one embodiment of the present invention, the obtaining unit 110 obtains, according to the user retention analysis request, user information of the user to be tested on the target index, including:
Analyzing the message of the user retention analysis request to obtain data information carried by the message;
extracting a user identification code from the data information, and determining a binding terminal associated with the user identification code;
Generating an information acquisition request according to the user identification code and the target index, and sending the information acquisition request to the binding terminal;
after a preset time interval, receiving an acquisition response result sent by the binding terminal, and extracting a secret key from the acquisition response result;
acquiring ciphertext information corresponding to the user identification code;
and decrypting the ciphertext information based on the key, and determining the information which is successfully decrypted as the user information.
The user identification code is a code capable of uniquely indicating the user to be tested.
The binding terminal refers to a terminal associated with the user to be detected.
The preset time interval can be set according to requirements. For example, the preset time interval may be five minutes.
The ciphertext information and the binding terminal can be accurately determined through the user identification code, the acquisition accuracy of the user information is improved, leakage of the user information caused by the safety problem of the binding terminal can be avoided through setting of the preset time interval, the safety of the user information is improved, and the acquisition legitimacy of the user information can be improved through generation and transmission of the information acquisition request.
The generating unit 111 generates a retention result of the user to be tested according to the user information and the target index.
It is emphasized that to further ensure the privacy and security of the above-mentioned persisted results, the above-mentioned persisted results may also be stored in a node of a blockchain.
In at least one embodiment of the present invention, the retention result is used to characterize the churn situation of the user to be tested. For example, if the retention result is 0.8, the user to be tested has a 20% loss probability.
In at least one embodiment of the present invention, the user information includes information to be measured of the user to be measured on each target index, and the generating unit 111 generates the retention result of the user to be measured according to the user information and the target index includes:
normalizing the index characteristic value corresponding to the target index to obtain an index weight value of each target index;
calculating the product of each piece of information to be detected and each index weight to obtain the score of the user to be detected on each target index;
and calculating the sum of a plurality of scores to obtain the retention result.
For example, the index feature value corresponding to the target index 1 is 0.2, the index feature value corresponding to the target index 2 is 0.8, the index feature value corresponding to the target index 3 is 0.6, and after normalization processing, the index weight corresponding to the target index 1 is 0.125, the index weight corresponding to the target index 2 is 0.5, and the index weight corresponding to the target index 3 is 0.375.
By carrying out normalization processing on the index characteristic values, the analysis uniformity of the target index can be improved, and the accuracy of the retention result is improved.
According to the technical scheme, the influence of scale difference among different initial indexes on the index characteristic values can be eliminated by carrying out standardized processing on the characterization information, so that the selection accuracy of the target indexes can be improved, the selection efficiency of the target indexes can be improved by analyzing the index characteristic values on each initial index, the number of the target indexes can be reduced by selecting the target indexes through the index characteristic values, the analysis efficiency of the retention results can be improved, the loss of important information in the initial indexes can be avoided, the selection accuracy of the target indexes is improved, and the analysis accuracy of the retention results can be ensured.
Fig. 3 is a schematic structural diagram of an electronic device according to a preferred embodiment of the present invention for implementing a user retention analysis method.
In one embodiment of the invention, the electronic device 1 includes, but is not limited to, a memory 12, a processor 13, and computer readable instructions stored in the memory 12 and executable on the processor 13, such as a user-resident analysis program.
It will be appreciated by those skilled in the art that the schematic diagram is merely an example of the electronic device 1 and does not constitute a limitation of the electronic device 1, and may include more or less components than illustrated, or may combine certain components, or different components, e.g. the electronic device 1 may further include input-output devices, network access devices, buses, etc.
The Processor 13 may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (DIGITAL SIGNAL Processor, DSP), application SPECIFIC INTEGRATED Circuit (ASIC), field-Programmable gate array (Field-Programmable GATE ARRAY, FPGA) or other Programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like. The general purpose processor may be a microprocessor or the processor may be any conventional processor, etc., and the processor 13 is an operation core and a control center of the electronic device 1, connects various parts of the entire electronic device 1 using various interfaces and lines, and executes an operating system of the electronic device 1 and various installed applications, program codes, etc.
Illustratively, the computer readable instructions may be partitioned into one or more modules/units that are stored in the memory 12 and executed by the processor 13 to complete the present invention. The one or more modules/units may be a series of computer readable instructions capable of performing a specific function, the computer readable instructions describing a process of executing the computer readable instructions in the electronic device 1. For example, the computer readable instructions may be divided into an acquisition unit 110, a generation unit 111, a processing unit 112, an analysis unit 113, and a selection unit 114.
The memory 12 may be used to store the computer readable instructions and/or modules, and the processor 13 may implement various functions of the electronic device 1 by executing or executing the computer readable instructions and/or modules stored in the memory 12 and invoking data stored in the memory 12. The memory 12 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 (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data created according to the use of the electronic device, etc. Memory 12 may include non-volatile and volatile memory, such as: a hard disk, memory, plug-in hard disk, smart memory card (SMART MEDIA CARD, SMC), secure Digital (SD) card, flash memory card (FLASH CARD), at least one magnetic disk storage device, flash memory device, or other storage device.
The memory 12 may be an external memory and/or an internal memory of the electronic device 1. Further, the memory 12 may be a physical memory, such as a memory bank, a TF card (Trans-FLASH CARD), or the like.
The integrated modules/units of the electronic device 1 may be stored in a computer readable storage medium if implemented in the form of software functional units and sold or used as separate products. Based on such understanding, the present invention may also be implemented by implementing all or part of the processes in the methods of the embodiments described above, by instructing the associated hardware by means of computer readable instructions, which may be stored in a computer readable storage medium, the computer readable instructions, when executed by a processor, implementing the steps of the respective method embodiments described above.
Wherein the computer readable instructions comprise computer readable instruction code which may be in the form of source code, object code, executable files, or in some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying the computer readable instruction code, a recording medium, a USB flash disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory).
The blockchain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm and the like. The blockchain (Blockchain), essentially a de-centralized database, is a string of data blocks that are generated in association using cryptographic methods, each of which contains information from a batch of network transactions for verifying the validity (anti-counterfeit) of its information and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, an application services layer, and the like.
In connection with fig. 1, the memory 12 in the electronic device 1 stores computer readable instructions implementing a user retention analysis method, the processor 13 being executable to implement:
acquiring sample information of a plurality of sample users on a plurality of initial indexes;
Generating characterization information of the plurality of sample users on the plurality of initial indexes according to the sample information;
carrying out standardization processing on the characterization information to obtain the characteristic information of the plurality of sample users on the plurality of initial indexes;
Analyzing index characteristic values on each initial index according to the characteristic information;
selecting a target index from the plurality of initial indexes according to the index characteristic value;
when a user retention analysis request is received, acquiring user information of a user to be detected on the target index according to the user retention analysis request;
and generating a retention result of the user to be tested according to the user information and the target index.
In particular, the specific implementation method of the processor 13 on the computer readable instructions may refer to the description of the relevant steps in the corresponding embodiment of fig. 1, which is not repeated herein.
In the several embodiments provided in the present invention, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical function division, and there may be other manners of division when actually implemented.
The computer readable storage medium has stored thereon computer readable instructions, wherein the computer readable instructions when executed by the processor 13 are configured to implement the steps of:
acquiring sample information of a plurality of sample users on a plurality of initial indexes;
Generating characterization information of the plurality of sample users on the plurality of initial indexes according to the sample information;
carrying out standardization processing on the characterization information to obtain the characteristic information of the plurality of sample users on the plurality of initial indexes;
Analyzing index characteristic values on each initial index according to the characteristic information;
selecting a target index from the plurality of initial indexes according to the index characteristic value;
when a user retention analysis request is received, acquiring user information of a user to be detected on the target index according to the user retention analysis request;
and generating a retention result of the user to be tested according to the user information and the target index.
The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional module in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units can be realized in a form of hardware or a form of hardware and a form of software functional modules.
The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.
Furthermore, it is evident that the word "comprising" does not exclude other elements or steps, and that the singular does not exclude a plurality. The units or means may also be implemented by one unit or means in software or hardware. The terms first, second, etc. are used to denote a name, but not any particular order.
Finally, it should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention.

Claims (5)

1. A user retention analysis method, the user retention analysis method comprising:
acquiring sample information of a plurality of sample users on a plurality of initial indexes;
Generating characterization information of the plurality of sample users on the plurality of initial indexes according to the sample information, wherein the characterization information comprises the following steps: comparing the information format of the sample information with the configuration format in the type template, and determining the type corresponding to the configuration format identical to the information format as the index type of the plurality of initial indexes; determining an initial index with the index type not being a preset type as a characteristic index; screening information corresponding to the initial index with the index type not being the preset type from the sample information as first characteristic information, and determining the rest information except the first characteristic information in the sample information as second characteristic information; mapping the first characteristic information to obtain numerical value information; determining the numerical information and the second characteristic information as target characteristic information; acquiring information of each sample user on the plurality of initial indexes from the target characteristic information as row vectors; splicing row vectors of each sample user to obtain the characterization information;
The characteristic information is standardized to obtain the characteristic information of the plurality of sample users on the plurality of initial indexes, and the method comprises the following steps: calculating average index information of the plurality of sample users on each initial index according to the characterization information; analyzing the characterization information and the average index information according to the following formula to obtain the difference information of each initial index: ; wherein/> Refers to the difference information,/>Refers to the/>Sample user at/>Characterization information on the initial index,/>Refers to the/>Average index information of the initial indexes,/>Means a total amount of users of the plurality of sample users; carrying out standardization processing on the characterization information according to the average index information and the difference information to obtain the characteristic information;
analyzing the index characteristic value on each initial index according to the characteristic information, including: calculating the characteristic information according to the following formula to obtain the index correlation degree of any two initial indexes: ; wherein, Refers to the/>Initial index and the/>Index relevance of the initial index,/>Refers to the total amount of users,/>Refers to the firstSample user at the/>Characteristic information on the initial index,/>Refers to the/>The sample users are at the firstCharacteristic information on the initial indicators; analyzing the discrete degree of the characteristic information on each initial index to obtain the information discrete degree of each initial index; sequentially sequencing the index relativity to obtain an initial diagonal matrix, and filling the initial diagonal matrix according to the information dispersion to obtain an index feature matrix; calculating the characteristic value of the index characteristic matrix as the index characteristic value;
Selecting a target index from the plurality of initial indexes according to the index characteristic value, wherein the target index comprises: selecting an index characteristic value which is larger than or equal to a preset characteristic threshold value from the index characteristic values as a target characteristic value, and determining an initial index corresponding to the target characteristic value as an index to be selected; sorting the indexes to be selected according to the sequence from the big to the small of the target characteristic value to obtain a characteristic sequence; calculating an accumulated contribution rate according to the feature sequence and the target feature value: ; wherein/> Refers to the front/>, in the characteristic sequenceCumulative contribution rate of individual candidate indices,/>Refers to the front/>, in the characteristic sequenceTarget characteristic values corresponding to the indexes to be selected,/>; If the accumulated contribution rate is greater than or equal to a preset contribution threshold, the front/>Determining the target indexes as the indexes to be selected;
When a user retention analysis request is received, obtaining user information of a user to be tested on the target index according to the user retention analysis request comprises the following steps: analyzing the message of the user retention analysis request to obtain data information carried by the message; extracting a user identification code from the data information, and determining a binding terminal associated with the user identification code; generating an information acquisition request according to the user identification code and the target index, and sending the information acquisition request to the binding terminal; after a preset time interval, receiving an acquisition response result sent by the binding terminal, and extracting a secret key from the acquisition response result; acquiring ciphertext information corresponding to the user identification code; decrypting the ciphertext information based on the key, and determining the information which is successfully decrypted as the user information;
and generating a retention result of the user to be tested according to the user information and the target index.
2. The method of claim 1, wherein the user information includes information to be tested of the user to be tested on each target index, and the generating the retention result of the user to be tested according to the user information and the target index includes:
normalizing the index characteristic value corresponding to the target index to obtain an index weight value of each target index;
calculating the product of each piece of information to be detected and each index weight to obtain the score of the user to be detected on each target index;
and calculating the sum of a plurality of scores to obtain the retention result.
3. A user retention analysis device, the user retention analysis device comprising:
The acquisition unit is used for acquiring sample information of a plurality of sample users on a plurality of initial indexes;
The generating unit is configured to generate characterization information of the plurality of sample users on the plurality of initial indexes according to the sample information, and includes: comparing the information format of the sample information with the configuration format in the type template, and determining the type corresponding to the configuration format identical to the information format as the index type of the plurality of initial indexes; determining an initial index with the index type not being a preset type as a characteristic index; screening information corresponding to the initial index with the index type not being the preset type from the sample information as first characteristic information, and determining the rest information except the first characteristic information in the sample information as second characteristic information; mapping the first characteristic information to obtain numerical value information; determining the numerical information and the second characteristic information as target characteristic information; acquiring information of each sample user on the plurality of initial indexes from the target characteristic information as row vectors; splicing row vectors of each sample user to obtain the characterization information;
The processing unit is used for carrying out standardization processing on the characterization information to obtain the characteristic information of the plurality of sample users on the plurality of initial indexes, and comprises the following steps: calculating average index information of the plurality of sample users on each initial index according to the characterization information; analyzing the characterization information and the average index information according to the following formula to obtain the difference information of each initial index: ; wherein/> Refers to the difference information,/>Refers to the/>Sample user at/>Characterization information on the initial index,/>Refers to the/>Average index information of the initial indexes,/>Means a total amount of users of the plurality of sample users; carrying out standardization processing on the characterization information according to the average index information and the difference information to obtain the characteristic information;
An analysis unit for analyzing the index feature value on each initial index according to the feature information, including: calculating the characteristic information according to the following formula to obtain the index correlation degree of any two initial indexes: ; wherein/> Refers to the/>Initial index and the/>Index relevance of the initial index,/>Refers to the total amount of users,/>Refers to the/>Sample user at the/>Characteristic information on the initial index,/>Refers to the/>Sample user at the/>Characteristic information on the initial indicators; analyzing the discrete degree of the characteristic information on each initial index to obtain the information discrete degree of each initial index; sequentially sequencing the index relativity to obtain an initial diagonal matrix, and filling the initial diagonal matrix according to the information dispersion to obtain an index feature matrix; calculating the characteristic value of the index characteristic matrix as the index characteristic value;
The selecting unit is configured to select a target index from the plurality of initial indexes according to the index feature value, and includes: selecting an index characteristic value which is larger than or equal to a preset characteristic threshold value from the index characteristic values as a target characteristic value, and determining an initial index corresponding to the target characteristic value as an index to be selected; sorting the indexes to be selected according to the sequence from the big to the small of the target characteristic value to obtain a characteristic sequence; calculating an accumulated contribution rate according to the feature sequence and the target feature value: ; wherein/> Refers to the front/>, in the characteristic sequenceCumulative contribution rate of individual candidate indices,/>Refers to the front/>, in the characteristic sequenceTarget characteristic values corresponding to the indexes to be selected,/>; If the accumulated contribution rate is greater than or equal to a preset contribution threshold, the front/>Determining the target indexes as the indexes to be selected;
The obtaining unit is further configured to obtain, when receiving a user retention analysis request, user information of a user to be tested on the target index according to the user retention analysis request, where the obtaining unit includes: analyzing the message of the user retention analysis request to obtain data information carried by the message; extracting a user identification code from the data information, and determining a binding terminal associated with the user identification code; generating an information acquisition request according to the user identification code and the target index, and sending the information acquisition request to the binding terminal; after a preset time interval, receiving an acquisition response result sent by the binding terminal, and extracting a secret key from the acquisition response result; acquiring ciphertext information corresponding to the user identification code; decrypting the ciphertext information based on the key, and determining the information which is successfully decrypted as the user information;
The generating unit is further configured to generate a retention result of the user to be tested according to the user information and the target index.
4. An electronic device, the electronic device comprising:
a memory storing computer readable instructions; and
A processor executing computer readable instructions stored in the memory to implement the user retention analysis method of any one of claims 1 to 2.
5. A computer-readable storage medium, characterized by: the computer readable storage medium has stored therein computer readable instructions that are executed by a processor in an electronic device to implement the user retention analysis method of any one of claims 1 to 2.
CN202111306579.0A 2021-11-05 2021-11-05 User retention analysis method, device, equipment and storage medium Active CN114020687B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111306579.0A CN114020687B (en) 2021-11-05 2021-11-05 User retention analysis method, device, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111306579.0A CN114020687B (en) 2021-11-05 2021-11-05 User retention analysis method, device, equipment and storage medium

Publications (2)

Publication Number Publication Date
CN114020687A CN114020687A (en) 2022-02-08
CN114020687B true CN114020687B (en) 2024-06-25

Family

ID=80061735

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111306579.0A Active CN114020687B (en) 2021-11-05 2021-11-05 User retention analysis method, device, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN114020687B (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112036641A (en) * 2020-08-31 2020-12-04 中国平安人寿保险股份有限公司 Retention prediction method, device, computer equipment and medium based on artificial intelligence
CN112182069A (en) * 2020-09-30 2021-01-05 中国平安人寿保险股份有限公司 Agent retention prediction method and device, computer equipment and storage medium

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113283675B (en) * 2021-06-29 2023-02-03 中国平安人寿保险股份有限公司 Index data analysis method, device, equipment and storage medium

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112036641A (en) * 2020-08-31 2020-12-04 中国平安人寿保险股份有限公司 Retention prediction method, device, computer equipment and medium based on artificial intelligence
CN112182069A (en) * 2020-09-30 2021-01-05 中国平安人寿保险股份有限公司 Agent retention prediction method and device, computer equipment and storage medium

Also Published As

Publication number Publication date
CN114020687A (en) 2022-02-08

Similar Documents

Publication Publication Date Title
CN112417096B (en) Question-answer pair matching method, device, electronic equipment and storage medium
CN112669138B (en) Data processing method and related equipment
CN113656547B (en) Text matching method, device, equipment and storage medium
CN113283675A (en) Index data analysis method, device, equipment and storage medium
CN115222443A (en) Client group division method, device, equipment and storage medium
CN112363923A (en) Test method, device, computer equipment and medium based on questionnaire system
CN114510487A (en) Data table merging method, device, equipment and storage medium
CN113470775B (en) Information acquisition method, device, equipment and storage medium
CN113918467A (en) Financial system testing method, device, equipment and storage medium
CN112395401B (en) Self-adaptive negative sample pair sampling method and device, electronic equipment and storage medium
CN116629423A (en) User behavior prediction method, device, equipment and storage medium
CN112819305A (en) Service index analysis method, device, equipment and storage medium
CN115037790B (en) Abnormal registration identification method, device, equipment and storage medium
CN114360732B (en) Medical data analysis method, device, electronic equipment and storage medium
CN113269179B (en) Data processing method, device, equipment and storage medium
CN116628161A (en) Answer generation method, device, equipment and storage medium
CN113516205B (en) Employee stability classification method based on artificial intelligence and related equipment
CN114020687B (en) User retention analysis method, device, equipment and storage medium
CN113283677B (en) Index data processing method, device, equipment and storage medium
CN113420143B (en) Method, device, equipment and storage medium for generating document abstract
CN112949305B (en) Negative feedback information acquisition method, device, equipment and storage medium
CN111859985B (en) AI customer service model test method and device, electronic equipment and storage medium
CN110889644A (en) Credit data processing method, device, storage medium and computer equipment
CN114971643B (en) Abnormal transaction identification method, device, equipment and storage medium
CN113760777B (en) Application program pressure test method, device, equipment and storage medium

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
GR01 Patent grant