CN109636378B - Account identification method and device and electronic equipment - Google Patents
Account identification method and device and electronic equipment Download PDFInfo
- Publication number
- CN109636378B CN109636378B CN201811290108.3A CN201811290108A CN109636378B CN 109636378 B CN109636378 B CN 109636378B CN 201811290108 A CN201811290108 A CN 201811290108A CN 109636378 B CN109636378 B CN 109636378B
- Authority
- CN
- China
- Prior art keywords
- candidate account
- account
- user
- incoming call
- candidate
- 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
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/30—Payment architectures, schemes or protocols characterised by the use of specific devices or networks
- G06Q20/34—Payment architectures, schemes or protocols characterised by the use of specific devices or networks using cards, e.g. integrated circuit [IC] cards or magnetic cards
- G06Q20/357—Cards having a plurality of specified features
- G06Q20/3572—Multiple accounts on card
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/38—Payment protocols; Details thereof
- G06Q20/40—Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
- G06Q20/401—Transaction verification
- G06Q20/4016—Transaction verification involving fraud or risk level assessment in transaction processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0281—Customer communication at a business location, e.g. providing product or service information, consulting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0633—Lists, e.g. purchase orders, compilation or processing
- G06Q30/0635—Processing of requisition or of purchase orders
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- Marketing (AREA)
- Economics (AREA)
- Computer Security & Cryptography (AREA)
- Computer Networks & Wireless Communication (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Telephonic Communication Services (AREA)
Abstract
One or more embodiments of the present disclosure provide an account identification method and apparatus, and an electronic device, where the method is applied to a customer service system, and the method includes: when a service call of a user is received, determining the call number of the call; wherein the incoming call number is associated with at least one candidate account presence service; extracting feature data based on service data of the candidate account in a preset time period before the incoming call moment; wherein the feature data is related to user behavior of the user to consult the candidate account in an incoming call; inputting the extracted characteristic data into a machine learning model for calculation to obtain a probability value of the candidate account as the target account for the call consultation, and outputting an account identification result to customer service personnel based on the probability value.
Description
Technical Field
One or more embodiments of the present disclosure relate to the field of computer application technologies, and in particular, to a method and apparatus for account identification, and an electronic device.
Background
Today, the same user can often hold multiple accounts. If some problems are encountered during the process of using a certain account by a user, the user usually calls a customer service, and consults the account with a customer service person to solve the encountered problems. Under the condition, if the account consulted by the user in the incoming call can be identified before the user is connected by the incoming call, the customer service personnel can provide personalized intelligent service for the user, provide convenience for the customer service personnel service user, and reduce the time consumed by the incoming call consultation of the user.
Disclosure of Invention
The specification provides an account identification method, which is applied to a customer service system and comprises the following steps:
when a service call of a user is received, determining the call number of the call; wherein the incoming call number is associated with at least one candidate account presence service;
extracting feature data based on service data of the candidate account in a preset time period before the incoming call moment; wherein the feature data is related to user behavior of the user to consult the candidate account in an incoming call;
inputting the extracted characteristic data into a machine learning model for calculation to obtain a probability value of the candidate account as the target account for the call consultation, and outputting an account identification result to customer service personnel based on the probability value.
The specification also provides an account identification device, the device is applied to a customer service system, and the device comprises:
the determining module is used for determining the incoming call number of the incoming call when receiving the service incoming call of the user; wherein the incoming call number is associated with at least one candidate account presence service;
the extraction module is used for extracting feature data based on the service data of the candidate account in a preset time before the incoming call time; wherein the feature data is related to user behavior of the user to consult the candidate account in an incoming call;
The computing module is used for inputting the extracted characteristic data into a machine learning model for computing, obtaining the probability value of the candidate account as the target account for the call consultation, and outputting an account identification result to customer service personnel based on the probability value.
The present specification also provides an electronic apparatus including:
a processor;
a memory for storing machine-executable instructions;
wherein, by reading and executing machine-executable instructions stored in the memory corresponding to user-registered control logic, the processor is caused to:
when a service call of a user is received, determining the call number of the call; wherein the incoming call number is associated with at least one candidate account presence service;
extracting feature data based on service data of the candidate account in a preset time period before the incoming call moment; wherein the feature data is related to user behavior of the user to consult the candidate account in an incoming call;
inputting the extracted characteristic data into a machine learning model for calculation to obtain a probability value of the candidate account as the target account for the call consultation, and outputting an account identification result to customer service personnel based on the probability value.
In the above technical solution, when receiving a service call of a user, the account that the user may consult with the call at this time can be automatically identified according to the call number of the call at this time, and the probability value of each account that the user consults with the call at this time is calculated. Subsequently, based on the calculated probability value, an account identification result can be output to the customer service personnel for the customer service personnel to check, so that the user does not need to input the account to be consulted by himself. By adopting the mode, the user experience can be improved, and the recognition efficiency and the success rate can be improved.
Drawings
FIG. 1 is a flow chart of an account identification method according to an exemplary embodiment of the present disclosure;
FIG. 2 is a flow chart of another method of account identification shown in an exemplary embodiment of the present disclosure;
FIG. 3 is a flow chart illustrating another method of account identification according to an exemplary embodiment of the present disclosure;
fig. 4 is a hardware configuration diagram of a device in which an account identifying apparatus is located, which is shown in an exemplary embodiment of the present disclosure;
fig. 5 is a block diagram of an account identification apparatus according to an exemplary embodiment of the present specification.
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 present specification. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present description.
The terminology used in the description presented herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the description. As used in this specification, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any or all possible combinations of one or more of the associated listed items.
It should be understood that although the terms first, second, third, etc. may be used in this specification to describe various information, these information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, the first information may also be referred to as second information, and similarly, the second information may also be referred to as first information, without departing from the scope of the present description. The word "if" as used herein may be interpreted as "at … …" or "at … …" or "responsive to a determination", depending on the context.
The specification aims to provide a technical scheme for calculating a probability value of a user incoming call consultation account associated with an incoming call number existence service according to an incoming call number of a current incoming call when a service incoming call of the user is received, and outputting the probability value to customer service personnel for the customer service personnel to check and provide convenience for the customer service personnel service user.
In the above technical solution, when receiving a service call of a user, the account that the user may consult with the call at this time can be automatically identified according to the call number of the call at this time, and the probability value of each account that the user consults with the call at this time is calculated. Subsequently, based on the calculated probability value, an account identification result can be output to the customer service personnel for the customer service personnel to check, so that the user does not need to input the account to be consulted by himself. By adopting the mode, the user experience can be improved, and the recognition efficiency and the success rate can be improved.
In the related art, in order to identify an account in which a user can consult in the current incoming call, the user may input an account name or an identification card number corresponding to the account to be consulted through a key pad, or the user may input an account name or an identification card number corresponding to the account to be consulted through voice. However, in practical applications, account names of a part of accounts are often mailbox including english and symbols, but not only are composed of numbers, which are difficult to be input through a key keyboard, and user experience is poor. On the other hand, the voice input mode is often limited by the conditions such as background noise of the call environment, accents of the callers, diversified description modes and the like, and the recognition efficiency and the success rate are affected.
In order to solve the problems, the specification provides an account identification method and device and electronic equipment.
Referring to fig. 1, fig. 1 is a flowchart of an account identification method according to an exemplary embodiment of the present disclosure. The method can be applied to the electronic equipment in the customer service system, and comprises the following steps:
102, when a service call of a user is received, determining a call number of the call; wherein the incoming number is associated with at least one candidate account presence service.
And 106, inputting the extracted characteristic data into a machine learning model for calculation to obtain a probability value of the candidate account as the target account for the call consultation, and outputting an account identification result to customer service personnel based on the probability value.
In this embodiment, when a user needs to consult a certain account held by the user, the user may make a service consultation with respect to the account.
When receiving a user service incoming call, the electronic equipment in the customer service system can firstly determine the incoming call number of the incoming call.
In one embodiment shown, after the caller number is determined, an account associated with the caller number presence service may be queried in stored service data based on the caller number, and the queried account may be determined to be a candidate account.
For example, assume that the stored service data includes service data of an online shopping order, in which an account used when a user makes a payment is account 1, and a recipient contact filled by the user is account 1, that is, the service data includes account 1 and account 1 at the same time, then when a user receives a service call, if it is determined that the incoming call number of the call is account 1, account 1 may be determined as a candidate account associated with the existence service of the incoming call number.
After determining the number of the incoming call in the step 102, and thus determining the candidate account associated with the presence service of the number of the incoming call, service data of the candidate account in a preset time period before the incoming call time (i.e. the time when the incoming call is received) can be acquired, and feature data can be extracted based on the acquired service data.
For example, assuming that the time of receiving the user service call is 3:25 pm on 8 months and 18 days, and the duration of extracting the feature data preset by the technician is 48 hours, after determining that the candidate account associated with the caller number existence service of the call is present, the service data of the candidate account in the time period from 3:25 pm on 8 months and 16 days to 3:25 pm on 8 months and 18 days can be acquired, and the feature data is extracted based on the acquired service data.
It should be noted that, the feature data extracted for the candidate account is related to the user behavior of the user to consult the candidate account.
In an embodiment shown, referring to fig. 2, the following steps may be used to extract feature data based on the service data of the candidate account in a preset time period before the incoming call time:
It should be noted that, there is no explicit timing relationship between the steps 202 and 204, and the two steps may be performed simultaneously, or the step 202 may be performed first and then the step 204 may be performed, or the step 204 may be performed first and then the step 202 may be performed, which is not limited in this specification.
In one aspect, after obtaining service data of the candidate account within a preset time period before the incoming call time, a relevance score between the candidate account and the incoming call number may be calculated based on the service data. Wherein the relevancy score may be used to characterize the degree of relevancy between the candidate account and the caller number.
In one embodiment, after the service data is acquired, the association degree evaluation index between the candidate account and the caller number may be counted based on the service data.
It should be noted that, the association degree evaluation index may be preset by a technician, and may include one or a combination of more of the following indexes:
the number of times the candidate account and the caller number appear in the same piece of business data;
a time interval between a time when the candidate account and the caller number appear in the same piece of service data and a time when the candidate account and the caller number appear next in the same piece of service data;
And simultaneously comprises the service amount in the service data of the candidate account and the incoming call number.
For example, assuming that the determined caller number is number 1, the determined candidate account associated with the caller number presence service is account 1, further assuming that stored service data includes service data of an online shopping order, in the online shopping order, an account used when a user makes a payment is account 1, and a contact of a recipient filled by the user is number 1, the candidate account (account 1) and the caller number (number 1) may be considered to appear in the same service data, i.e., the service data includes the candidate account and the caller number at the same time.
In another example, assume that the determined caller number is number 1 and the determined candidate account associated with the caller number presence service is account 1. In practical application, the stored service data may be queried according to time sequence, where the service data includes the candidate account (account 1) and the incoming call number (number 1) at the same time. Assuming that the service data of an air ticket booking order is queried this time, in the air ticket booking order, an account used when a user pays is account 1, the number of an emergency contact person filled by the user is number 1, and the payment time in the air ticket booking order is 10:15 in 8 months and 20 days, the candidate account and the incoming call number can be considered to appear in the same service data at the time of 10:15 in 8 months and 20 days; further, assuming that the next time the service data of an online shopping order is queried, in the online shopping order, an account used when the user pays is account 1, the contact way of a receiver filled by the user is number 1, and the payment time in the online shopping order is 10:45 am on 8 months and 20 days, the candidate account and the incoming call number can be considered to appear in the same service data at the time of 10:45 am on 8 months and 20 days. In this case, the time interval of 30 minutes may be determined as one of the time intervals between the time when the candidate account and the caller number appear in the same piece of service data and the time when the candidate account and the caller number appear next in the same piece of service data.
In another example, assuming that the determined caller number is number 1, the determined candidate account associated with the caller number presence service is account 1, further assuming that stored service data includes service data of a telephone charge order in which an account used by a user for payment is account 1, the telephone charge number filled by the user is number 1, and the telephone charge amount is 200, 200 may be determined as one of service amounts included in the service data of the candidate account (account 1) and the caller number (number 1) at the same time.
After the association degree evaluation indexes between the candidate account and the caller number are obtained through statistics, evaluation calculation can be carried out on the obtained association degree evaluation indexes, and the association degree score between the candidate account and the caller number is obtained.
In one embodiment, the obtained relevancy assessment indexes may be evaluated based on a preset scoring rule or scoring card model, so as to obtain a relevancy score between the candidate account and the caller number.
In practical application, if the number of times that the candidate account and the caller number appear in the same service data is more, it can be stated that the frequency of the user using the candidate account recently is higher, and the possibility that the user calls to consult the candidate account is higher, so that a higher association score can be set for the candidate account and the caller number.
If the time interval between the moment that the candidate account and the caller number appear in the same service data and the moment that the candidate account and the caller number appear in the same service data next time is shorter, the fact that the frequency of the user using the candidate account recently is higher can also be indicated, the probability that the user calls the call to consult the candidate account is higher, and therefore a higher association degree score can be set for the candidate account and the caller number.
If the service amount in the service data containing the candidate account and the caller number is larger, it can be stated that the service processed by the user using the candidate account recently is more important, and the possibility that the user consults the candidate account in an incoming call is larger, so that a higher association degree score can be set for the candidate account and the caller number.
On the other hand, after the service data of the candidate account within the preset time period before the incoming call time is acquired, the advisory degree score corresponding to the candidate account can be calculated based on the service data. Wherein the advisory score may be used to characterize a probability that a user is incoming to consult the candidate account.
In one embodiment shown, after the business data is obtained, user risk behaviors of the user for the candidate accounts may be counted based on the business data. Wherein the user risk behavior is related to user behavior of the user to consult the candidate account for incoming calls.
For example, the user risk behavior may include a behavior in which a number of times a login password is erroneously entered when the user logs into the candidate account reaches an account locking threshold; alternatively, the user risk actions may include actions such as the user paying more than a common amount threshold using the candidate account.
After the user risk behaviors of the user for the candidate account are obtained through statistics, evaluation calculation can be conducted on the obtained user risk behaviors, and the consultancy score corresponding to the candidate account is obtained.
In one embodiment shown, evaluation calculation may be performed on the obtained risk behaviors of the user based on preset scoring rules, so as to obtain a consultancy score corresponding to the candidate account.
In practical application, if the number of times of wrongly inputting the login password reaches the account locking threshold when the user logs in the candidate account, it can be stated that the user may need to perform an incoming call consultation to unlock the candidate account, so that a higher consultancy score can be set for the candidate account.
In one embodiment, after the service data are acquired, behavior indexes related to the incoming call consultation behavior of the user for the candidate account can be counted based on the service data.
It should be noted that, the behavior index may be preset by a technician, and may include one or a combination of more of the following indexes:
the number of times the user makes an incoming call consultation with respect to the candidate account;
the time interval between the moment when the user makes an incoming call consultation with respect to the candidate account and the moment when the user makes an incoming call consultation with respect to the candidate account next time.
For example, assume that the determined caller number is number 1, the determined candidate account associated with the caller number presence service is account 1, further assume that a user uses number 1 to make an incoming call consultation with account 1, and the time of the incoming call consultation is 8 months, 20 days, 10:15 am; and assuming that the next time the user uses the number 1 to make an incoming call consultation with the account 1 and the time of the incoming call consultation is 10:45 am on 8 months and 20 days, the time interval of 30 minutes can be determined as one of the time intervals between the time when the user makes an incoming call consultation with the candidate account and the time when the next time the user makes an incoming call consultation with the candidate account.
After the behavior indexes related to the incoming call consultation behaviors of the user for the candidate account are obtained through statistics, evaluation calculation can be conducted on the obtained behavior indexes, and the consultation degree score corresponding to the candidate account is obtained.
In one embodiment shown, evaluation calculation may be performed on the obtained behavior indexes based on preset scoring rules, so as to obtain a consultancy score corresponding to the candidate account.
In practical application, if the number of times of the user carrying out the call consultation on the candidate account is more, the user can be considered to have a higher possibility of the call consultation on the candidate account, so that a higher consultancy score can be set for the candidate account.
If the time interval between the moment when the user makes an incoming call consultation for the candidate account and the moment when the user makes an incoming call consultation for the candidate account next time is shorter, the possibility that the user makes an incoming call consultation for the candidate account can be considered to be higher, and therefore a higher consultation degree score can be set for the candidate account.
After the feature data of the candidate account is extracted in the step 104, the extracted feature data may be input into a machine learning model for calculation, so as to obtain a probability value of the candidate account being the target account of the current call consultation of the user, and an account identification result is output to the customer service personnel based on the probability value.
For example, for a certain candidate account, the candidate account and the probability value calculated for the candidate account may be directly output to the customer service personnel, so that the customer service personnel may directly check the probability value of the candidate account as the target account for the current call consultation of the user.
Alternatively, a plurality of probability intervals characterizing different account identification results may be preset, for example: the probability interval [0,0.3 ] may be set as a probability interval representing that the probability of the user consulting the candidate account at this time is low, the probability interval [0.3,0.7 ] may be set as a probability interval representing that the probability of the user consulting the candidate account at this time is medium, and the probability interval [0.7,1] may be set as a probability interval representing that the probability of the user consulting the candidate account at this time is high. After the probability value of a candidate account for the target account of the user for the call consultation is calculated, the probability interval to which the probability value belongs can be determined, so that the candidate account and the degree of the possibility of the user for the call consultation can be output to customer service personnel for the customer service personnel to check.
In one embodiment, referring to fig. 3, the machine learning model may be a two-class model. Further, the machine learning model may be trained using the following steps:
And step 304, determining a sample based on the marked candidate account set and the characteristic data corresponding to each candidate account in the candidate account set, and inputting the sample into the machine learning model for training.
To train the machine learning model described above, a training sample first needs to be determined. Specifically, all candidate accounts associated with the caller number presence service may be acquired, and the acquired candidate accounts may be added to the same candidate account set. Alternatively, each candidate account obtained (i.e., each candidate account in the set of candidate accounts) may be individually tagged. In practical applications, candidate accounts that have been previously queried by the user may be marked as 1, and candidate accounts that have not been previously queried by the user may be marked as 0, based on historical query data. It should be noted that the marking process may be performed by a technician or by the device itself.
In addition, the feature data may be extracted based on the service data of each candidate account in the candidate account set within a preset time period before the incoming call time, and a specific method for extracting the feature data may refer to the description of the foregoing step 102, which is not repeated herein.
After the labeling of each candidate account in the candidate account set and the extraction of the feature data corresponding to each candidate account in the candidate account set are completed, a training sample can be determined based on the labeled candidate account set and the feature data corresponding to each candidate account in the candidate account set, and the determined training sample is input into the machine learning model to train the machine learning model, namely, the machine learning model is trained based on the labeling and the corresponding feature data of each candidate account in the candidate account set.
After the training of the machine learning model is completed, the trained machine learning model can be used for calculating the probability value of the target account for the subsequent candidate account consultation for the incoming call.
In one embodiment shown, to output more comprehensive incoming call consultation information to the customer service personnel, all candidate accounts associated with the incoming call number presence service may be taken and added to the same candidate account set.
In this case, the probability value of the candidate account being the target account consulted by the user for the current incoming call may be calculated for each candidate account in the candidate account set.
And then, all candidate accounts in the candidate account set can be ordered according to the order of the calculated probability values from large to small, and the ordering result is output to customer service personnel, so that the customer service personnel can check the candidate accounts most likely to be consulted by the incoming call of the user conveniently.
Of course, from the candidate accounts ranked first, the preset number of candidate accounts in the ranking result can be sequentially output to customer service staff for the customer service staff to check. This description is not limiting.
In the above technical solution, when receiving a service call of a user, the account that the user may consult with the call at this time can be automatically identified according to the call number of the call at this time, and the probability value of each account that the user consults with the call at this time is calculated. Subsequently, based on the calculated probability value, an account identification result can be output to the customer service personnel for the customer service personnel to check, so that the user does not need to input the account to be consulted by himself. By adopting the mode, the user experience can be improved, and the recognition efficiency and the success rate can be improved.
Corresponding to the embodiment of the account identification method, the present specification also provides an embodiment of the account identification device.
The embodiment of the account identification device can be applied to electronic equipment in a customer service system. The apparatus embodiments may be implemented by software, or may be implemented by hardware or a combination of hardware and software. Taking software implementation as an example, the device in a logic sense is formed by reading corresponding computer program instructions in a nonvolatile memory into a memory by a processor of an electronic device where the device is located for operation. In terms of hardware, as shown in fig. 4, a hardware structure diagram of an electronic device where the account identifying apparatus in the present disclosure is located is shown in fig. 4, and in addition to the processor, the memory, the network interface, and the nonvolatile memory shown in fig. 4, the electronic device where the apparatus is located in the embodiment generally includes other hardware according to the actual function identified by the account, which is not described herein again.
Referring to fig. 5, fig. 5 is a block diagram of an account identifying apparatus according to an exemplary embodiment of the present disclosure. The apparatus 500 may be applied to the electronic device shown in fig. 4, including:
a determining module 501, configured to determine an incoming number of a service incoming of a user when the incoming number is received; wherein the incoming call number is associated with at least one candidate account presence service;
An extracting module 502, configured to extract feature data based on service data of the candidate account within a preset duration before the incoming call time; wherein the feature data is related to user behavior of the user to consult the candidate account in an incoming call;
the calculating module 503 is configured to input the extracted feature data into a machine learning model for calculation, obtain a probability value of the candidate account being the target account for the call consultation, and output an account identification result to a customer service person based on the probability value.
In this embodiment, the extracting module 502 may specifically be configured to:
calculating a relevancy score between the candidate account and the incoming call number based on service data of the candidate account in a preset time period before the incoming call time; wherein the relevancy score characterizes a degree of relevancy between the candidate account and the incoming call number;
calculating a consultancy score corresponding to the candidate account based on business data of the candidate account in a preset time period before the incoming call moment; wherein the advisory level score characterizes a probability that the user is incoming to consult the candidate account.
In this embodiment, the extracting module 502 may specifically be configured to:
Based on the business data of the candidate account in a preset time before the incoming call time, counting preset association degree evaluation indexes between the candidate account and the incoming call number;
performing evaluation calculation on the evaluation index to obtain the association degree score;
wherein the relevancy assessment indicator includes one or a combination of more of the following indicators:
the number of times the candidate account and the caller number appear in the same piece of business data;
a time interval between a time when the candidate account and the caller number appear in the same piece of service data and a time when the candidate account and the caller number appear next in the same piece of service data;
and simultaneously containing the service amount in the service data of the candidate account and the incoming call number.
In this embodiment, the extracting module 502 may specifically be configured to:
based on business data of the candidate account in a preset time period before the incoming call moment, counting user risk behaviors of the user on the candidate account; wherein the user risk behavior is related to the user behavior of the user to consult the candidate account in an incoming call;
And carrying out evaluation calculation on the risk behaviors of the user to obtain the consultancy score.
In this embodiment, the user risk behavior may include:
and when the user logs in the candidate account, the number of times of wrongly inputting the login password reaches an account locking threshold value.
In this embodiment, the extracting module 502 may specifically be configured to:
based on business data of the candidate account in a preset time before the incoming call time, counting behavior indexes related to the incoming call consultation behavior of the user aiming at the candidate account;
evaluating and calculating the behavior indexes to obtain the consultancy score;
wherein the behavioral indicators include a combination of one or more of the following:
the number of times that the user makes an incoming call consultation with respect to the candidate account;
and the time interval between the moment when the user conducts the call consultation on the candidate account and the moment when the user conducts the call consultation on the candidate account next time.
In this embodiment, the machine learning model may be a classification model;
the apparatus 500 may further include:
a tagging module 504, configured to add a candidate account associated with the caller number presence service to a candidate account set, and tag candidate accounts in the candidate account set; wherein, the candidate account with the incoming call consultation by the user is marked as 1, and the candidate account without the incoming call consultation by the user is marked as 0;
The training module 505 is configured to determine a sample based on the marked candidate account set and feature data corresponding to each candidate account in the candidate account set, and input the sample into the machine learning model for training.
In this embodiment, the apparatus 500 may further include:
an adding module 506, configured to add a candidate account associated with the caller number presence service to a candidate account set;
and the sorting module 507 is configured to sort each candidate account based on a probability value of the candidate account in the candidate account set for the target account of the call consultation, and output a sorting result to the customer service personnel.
The implementation process of the functions and roles of each unit in the above device is specifically shown in the implementation process of the corresponding steps in the above method, and will not be described herein again.
For the device embodiments, reference is made to the description of the method embodiments for the relevant points, since they essentially correspond to the method embodiments. The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purposes of the present description. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
The system, apparatus, module or module set forth in the above embodiments may be implemented in particular by a computer chip or entity, or by a product having some function. A typical implementation device is a computer, which may be in the form of a personal computer, laptop computer, cellular telephone, camera phone, smart phone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or a combination of any of these devices.
Corresponding to the embodiment of the account identification method, the present specification also provides an embodiment of an electronic device. The electronic device includes: a processor and a memory for storing machine executable instructions; wherein the processor and the memory are typically interconnected by an internal bus. In other possible implementations, the device may also include an external interface to enable communication with other devices or components.
In this embodiment, the processor is caused to, by reading and executing machine-executable instructions stored in the memory corresponding to the user-registered control logic:
When a service call of a user is received, determining the call number of the call; wherein the incoming call number is associated with at least one candidate account presence service;
extracting feature data based on service data of the candidate account in a preset time period before the incoming call moment; wherein the feature data is related to user behavior of the user to consult the candidate account in an incoming call;
inputting the extracted characteristic data into a machine learning model for calculation to obtain a probability value of the candidate account as the target account for the call consultation, and outputting an account identification result to customer service personnel based on the probability value.
In this embodiment, the processor is caused to, by reading and executing machine-executable instructions stored in the memory corresponding to the user-registered control logic:
calculating a relevancy score between the candidate account and the incoming call number based on service data of the candidate account in a preset time period before the incoming call time; wherein the relevancy score characterizes a degree of relevancy between the candidate account and the incoming call number;
calculating a consultancy score corresponding to the candidate account based on business data of the candidate account in a preset time period before the incoming call moment; wherein the advisory level score characterizes a probability that the user is incoming to consult the candidate account.
In this embodiment, the processor is caused to, by reading and executing machine-executable instructions stored in the memory corresponding to the user-registered control logic:
based on the business data of the candidate account in a preset time before the incoming call time, counting preset association degree evaluation indexes between the candidate account and the incoming call number;
performing evaluation calculation on the evaluation index to obtain the association degree score;
wherein the relevancy assessment indicator includes one or a combination of more of the following indicators:
the number of times the candidate account and the caller number appear in the same piece of business data;
a time interval between a time when the candidate account and the caller number appear in the same piece of service data and a time when the candidate account and the caller number appear next in the same piece of service data;
and simultaneously containing the service amount in the service data of the candidate account and the incoming call number.
In this embodiment, the processor is caused to, by reading and executing machine-executable instructions stored in the memory corresponding to the user-registered control logic:
Based on business data of the candidate account in a preset time period before the incoming call moment, counting user risk behaviors of the user on the candidate account; wherein the user risk behavior is related to the user behavior of the user to consult the candidate account in an incoming call;
and carrying out evaluation calculation on the risk behaviors of the user to obtain the consultancy score.
In this embodiment, the user risk behavior includes:
and when the user logs in the candidate account, the number of times of wrongly inputting the login password reaches an account locking threshold value.
In this embodiment, the processor is caused to, by reading and executing machine-executable instructions stored in the memory corresponding to the user-registered control logic:
based on business data of the candidate account in a preset time before the incoming call time, counting behavior indexes related to the incoming call consultation behavior of the user aiming at the candidate account;
evaluating and calculating the behavior indexes to obtain the consultancy score;
wherein the behavioral indicators include a combination of one or more of the following:
the number of times that the user makes an incoming call consultation with respect to the candidate account;
And the time interval between the moment when the user conducts the call consultation on the candidate account and the moment when the user conducts the call consultation on the candidate account next time.
In this embodiment, the machine learning model is a classification model;
by reading and executing machine-executable instructions stored by the memory corresponding to user-registered control logic, the processor is further caused to:
adding a candidate account associated with the caller number presence service to a candidate account set, and marking candidate accounts in the candidate account set; wherein, the candidate account with the incoming call consultation by the user is marked as 1, and the candidate account without the incoming call consultation by the user is marked as 0;
and determining a sample based on the marked candidate account set and the characteristic data corresponding to each candidate account in the candidate account set, and inputting the sample into the machine learning model for training.
By reading and executing machine-executable instructions stored by the memory corresponding to user-registered control logic, the processor is further caused to:
adding a candidate account associated with the caller number presence service to a set of candidate accounts;
And sequencing each candidate account based on the probability value of the target account consulted for the incoming call by each candidate account in the candidate account set, and outputting the sequencing result to the customer service personnel.
Other embodiments of the present disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This specification is intended to cover any variations, uses, or adaptations of the specification following, in general, the principles of the specification and including such departures from the present disclosure as come within known or customary practice within the art to which the specification pertains. The specification and examples are to be regarded in an illustrative manner only.
It is to be understood that the present description 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 made without departing from the scope thereof.
The foregoing description of the preferred embodiments is provided for the purpose of illustration only, and is not intended to limit the scope of the disclosure, since any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the disclosure are intended to be included within the scope of the disclosure.
Claims (17)
1. An account identification method, the method being applied to a customer service system, the method comprising:
when a service call of a user is received, determining the call number of the call; wherein the incoming call number is associated with at least one candidate account presence service;
extracting feature data based on service data of the candidate account in a preset time period before the incoming call moment; wherein the characteristic data comprises data representing the association degree between the candidate account and the caller number and data representing the probability of the user to consult the candidate account in an incoming call;
inputting the extracted characteristic data into a machine learning model for calculation to obtain a probability value of the candidate account as the target account for the call consultation, and outputting an account identification result to customer service personnel based on the probability value.
2. The method of claim 1, the extracting feature data based on business data of the candidate account within a preset time period before the incoming call time, comprising:
calculating a relevancy score between the candidate account and the incoming call number based on service data of the candidate account in a preset time period before the incoming call time; wherein the relevancy score characterizes a degree of relevancy between the candidate account and the incoming call number;
Calculating a consultancy score corresponding to the candidate account based on business data of the candidate account in a preset time period before the incoming call moment; wherein the advisory level score characterizes a probability that the user is incoming to consult the candidate account.
3. The method of claim 2, wherein the calculating a relevance score between the candidate account and the incoming phone number based on the service data of the candidate account within a preset time period before the incoming phone call time comprises:
based on the business data of the candidate account in a preset time before the incoming call time, counting preset association degree evaluation indexes between the candidate account and the incoming call number;
performing evaluation calculation on the evaluation index to obtain the association degree score;
wherein the relevancy assessment indicator includes one or a combination of more of the following indicators:
the number of times the candidate account and the caller number appear in the same piece of business data;
a time interval between a time when the candidate account and the caller number appear in the same piece of service data and a time when the candidate account and the caller number appear next in the same piece of service data;
And simultaneously containing the service amount in the service data of the candidate account and the incoming call number.
4. The method of claim 2, the calculating a advisory score corresponding to the candidate account based on business data of the candidate account for a preset period of time prior to the incoming call time, comprising:
based on business data of the candidate account in a preset time period before the incoming call moment, counting user risk behaviors of the user on the candidate account; wherein the user risk behavior is related to the user behavior of the user to consult the candidate account in an incoming call;
and carrying out evaluation calculation on the risk behaviors of the user to obtain the consultancy score.
5. The method of claim 4, the user risk behavior comprising:
and when the user logs in the candidate account, the number of times of wrongly inputting the login password reaches an account locking threshold value.
6. The method of claim 2, the calculating a advisory score corresponding to the candidate account based on business data of the candidate account for a preset period of time prior to the incoming call time, comprising:
based on business data of the candidate account in a preset time before the incoming call time, counting behavior indexes related to the incoming call consultation behavior of the user aiming at the candidate account;
Evaluating and calculating the behavior indexes to obtain the consultancy score;
wherein the behavioral indicators include a combination of one or more of the following:
the number of times that the user makes an incoming call consultation with respect to the candidate account;
and the time interval between the moment when the user conducts the call consultation on the candidate account and the moment when the user conducts the call consultation on the candidate account next time.
7. The method of claim 1, the machine learning model being a classification model;
training the machine learning model by adopting the following steps:
adding a candidate account associated with the caller number presence service to a candidate account set, and marking candidate accounts in the candidate account set; wherein, the candidate account with the incoming call consultation by the user is marked as 1, and the candidate account without the incoming call consultation by the user is marked as 0;
and determining a sample based on the marked candidate account set and the characteristic data corresponding to each candidate account in the candidate account set, and inputting the sample into the machine learning model for training.
8. The method of claim 1, the method further comprising:
Adding a candidate account associated with the caller number presence service to a set of candidate accounts;
and sequencing each candidate account based on the probability value of the target account consulted for the incoming call by each candidate account in the candidate account set, and outputting the sequencing result to the customer service personnel.
9. An account identification device for use in a customer service system, the device comprising:
the determining module is used for determining the incoming call number of the incoming call when receiving the service incoming call of the user; wherein the incoming call number is associated with at least one candidate account presence service;
the extraction module is used for extracting feature data based on the service data of the candidate account in a preset time before the incoming call time; wherein the characteristic data comprises data representing the association degree between the candidate account and the caller number and data representing the probability of the user to consult the candidate account in an incoming call;
the computing module is used for inputting the extracted characteristic data into a machine learning model for computing, obtaining the probability value of the candidate account as the target account for the call consultation, and outputting an account identification result to customer service personnel based on the probability value.
10. The apparatus of claim 9, the extraction module being specifically configured to:
calculating a relevancy score between the candidate account and the incoming call number based on service data of the candidate account in a preset time period before the incoming call time; wherein the relevancy score characterizes a degree of relevancy between the candidate account and the incoming call number;
calculating a consultancy score corresponding to the candidate account based on business data of the candidate account in a preset time period before the incoming call moment; wherein the advisory level score characterizes a probability that the user is incoming to consult the candidate account.
11. The apparatus of claim 10, the extraction module being specifically configured to:
based on the business data of the candidate account in a preset time before the incoming call time, counting preset association degree evaluation indexes between the candidate account and the incoming call number;
performing evaluation calculation on the evaluation index to obtain the association degree score;
wherein the relevancy assessment indicator includes one or a combination of more of the following indicators:
the number of times the candidate account and the caller number appear in the same piece of business data;
A time interval between a time when the candidate account and the caller number appear in the same piece of service data and a time when the candidate account and the caller number appear next in the same piece of service data;
and simultaneously containing the service amount in the service data of the candidate account and the incoming call number.
12. The apparatus of claim 10, the extraction module being specifically configured to:
based on business data of the candidate account in a preset time period before the incoming call moment, counting user risk behaviors of the user on the candidate account; wherein the user risk behavior is related to the user behavior of the user to consult the candidate account in an incoming call;
and carrying out evaluation calculation on the risk behaviors of the user to obtain the consultancy score.
13. The apparatus of claim 12, the user risk behavior comprising:
and when the user logs in the candidate account, the number of times of wrongly inputting the login password reaches an account locking threshold value.
14. The apparatus of claim 10, the extraction module being specifically configured to:
based on business data of the candidate account in a preset time before the incoming call time, counting behavior indexes related to the incoming call consultation behavior of the user aiming at the candidate account;
Evaluating and calculating the behavior indexes to obtain the consultancy score;
wherein the behavioral indicators include a combination of one or more of the following:
the number of times that the user makes an incoming call consultation with respect to the candidate account;
and the time interval between the moment when the user conducts the call consultation on the candidate account and the moment when the user conducts the call consultation on the candidate account next time.
15. The apparatus of claim 9, the machine learning model being a classification model;
the apparatus further comprises:
the marking module is used for adding the candidate account associated with the caller number existence service to a candidate account set and marking the candidate account in the candidate account set; wherein, the candidate account with the incoming call consultation by the user is marked as 1, and the candidate account without the incoming call consultation by the user is marked as 0;
and the training module is used for determining samples based on the marked candidate account set and the characteristic data corresponding to each candidate account in the candidate account set, and inputting the samples into the machine learning model for training.
16. The apparatus of claim 9, the apparatus further comprising:
An adding module, configured to add a candidate account associated with the caller number presence service to a candidate account set;
and the sorting module is used for sorting each candidate account based on the probability value of the candidate account in the candidate account set for the target account of the call consultation, and outputting the sorting result to the customer service personnel.
17. An electronic device, the electronic device comprising:
a processor;
a memory for storing machine-executable instructions;
wherein, by reading and executing machine-executable instructions stored in the memory corresponding to user-registered control logic, the processor is caused to:
when a service call of a user is received, determining the call number of the call; wherein the incoming call number is associated with at least one candidate account presence service;
extracting feature data based on service data of the candidate account in a preset time period before the incoming call moment; wherein the characteristic data comprises data representing the association degree between the candidate account and the caller number and data representing the probability of the user to consult the candidate account in an incoming call;
Inputting the extracted characteristic data into a machine learning model for calculation to obtain a probability value of the candidate account as the target account for the call consultation, and outputting an account identification result to customer service personnel based on the probability value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811290108.3A CN109636378B (en) | 2018-10-31 | 2018-10-31 | Account identification method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811290108.3A CN109636378B (en) | 2018-10-31 | 2018-10-31 | Account identification method and device and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109636378A CN109636378A (en) | 2019-04-16 |
| CN109636378B true CN109636378B (en) | 2023-06-02 |
Family
ID=66067005
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811290108.3A Active CN109636378B (en) | 2018-10-31 | 2018-10-31 | Account identification method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109636378B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112819263B (en) * | 2019-10-31 | 2024-08-20 | 北京沃东天骏信息技术有限公司 | Method and device for scheduling customer service |
| CN113743838B (en) * | 2020-05-27 | 2024-08-06 | 顺丰恒通支付有限公司 | Target user identification method, device, computer equipment and storage medium |
| CN113469710B (en) * | 2021-07-06 | 2022-10-11 | 携程商旅信息服务（上海）有限公司 | Consultation order prediction method, system, electronic equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0295837A2 (en) * | 1987-06-16 | 1988-12-21 | Inventions, Inc. | Customer account online servicing system |
| CN102546987A (en) * | 2012-01-12 | 2012-07-04 | 江苏电力信息技术有限公司 | Method for realizing rapid identification of electricity customer information |
| CN105243252A (en) * | 2014-07-09 | 2016-01-13 | 阿里巴巴集团控股有限公司 | Account risk evaluation method and apparatus |
| CN105657201A (en) * | 2016-01-26 | 2016-06-08 | 北京京东尚科信息技术有限公司 | Method and system for processing call based on decision tree model |
| CN106034149A (en) * | 2015-03-13 | 2016-10-19 | 阿里巴巴集团控股有限公司 | Account identification method and device |
| CN107071193A (en) * | 2016-11-28 | 2017-08-18 | 阿里巴巴集团控股有限公司 | The method and apparatus of interactive answering system accessing user |
| CN107608979A (en) * | 2016-07-08 | 2018-01-19 | 阿里巴巴集团控股有限公司 | Identify the method and device of the potential knowledge point sought help of user |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8588395B2 (en) * | 2008-06-11 | 2013-11-19 | Time Warner Cable Enterprises Llc | Customer service methods, apparatus and report/alert generation based on customer service call information |
-
2018
- 2018-10-31 CN CN201811290108.3A patent/CN109636378B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0295837A2 (en) * | 1987-06-16 | 1988-12-21 | Inventions, Inc. | Customer account online servicing system |
| CN102546987A (en) * | 2012-01-12 | 2012-07-04 | 江苏电力信息技术有限公司 | Method for realizing rapid identification of electricity customer information |
| CN105243252A (en) * | 2014-07-09 | 2016-01-13 | 阿里巴巴集团控股有限公司 | Account risk evaluation method and apparatus |
| CN106034149A (en) * | 2015-03-13 | 2016-10-19 | 阿里巴巴集团控股有限公司 | Account identification method and device |
| CN105657201A (en) * | 2016-01-26 | 2016-06-08 | 北京京东尚科信息技术有限公司 | Method and system for processing call based on decision tree model |
| CN107608979A (en) * | 2016-07-08 | 2018-01-19 | 阿里巴巴集团控股有限公司 | Identify the method and device of the potential knowledge point sought help of user |
| CN107071193A (en) * | 2016-11-28 | 2017-08-18 | 阿里巴巴集团控股有限公司 | The method and apparatus of interactive answering system accessing user |
Non-Patent Citations (1)
| Title |
|---|
| 电信运营商统一新媒体分析管理平台建设工程可行性研究;赵慧君;《中国优秀硕士论文电子期刊网》;20181015;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109636378A (en) | 2019-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109815314B (en) | Intent recognition method, recognition device and computer readable storage medium | |
| CN108615119B (en) | Abnormal user identification method and equipment | |
| CN112560453B (en) | Voice information verification method and device, electronic equipment and medium | |
| CN109977403B (en) | Malicious comment information identification method and device | |
| CN109345417B (en) | Online assessment method and terminal equipment for business personnel based on identity authentication | |
| CN113383362B (en) | User identification method and related product | |
| CN109636378B (en) | Account identification method and device and electronic equipment | |
| CN109583966A (en) | A kind of high value customer recognition methods, system, equipment and storage medium | |
| CN109840323A (en) | The voice recognition processing method and server of insurance products | |
| CN106713579B (en) | Telephone number identification method and device | |
| CN111709052A (en) | A method, apparatus, device and readable medium for identifying and processing private data | |
| CN112927061B (en) | User operation detection method and program product | |
| CN111510368B (en) | Family group identification method, device, equipment and computer readable storage medium | |
| CN110287318B (en) | Service operation detection method and device, storage medium and electronic device | |
| CN106910135A (en) | User recommends method and device | |
| CN107729456A (en) | Sensitive information search method, server and storage medium | |
| CN110349039A (en) | Complaint risk appraisal procedure, system, computer equipment and readable storage medium storing program for executing | |
| CN113032524A (en) | Trademark infringement identification method, terminal device and storage medium | |
| CN113129057A (en) | Software cost information processing method and device, computer equipment and storage medium | |
| CN115577172A (en) | Article recommendation method, device, equipment and medium | |
| CN115618415A (en) | Sensitive data identification method and device, electronic equipment and storage medium | |
| CN110389963A (en) | The recognition methods of channel effect, device, equipment and storage medium based on big data | |
| CN108711073B (en) | User analysis method, device and terminal | |
| CN111353015B (en) | Crowd-sourced question recommendation method, device, equipment and storage medium | |
| CN111402924A (en) | Spoken language evaluation method and device and computer readable 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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200923 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant after: Innovative advanced technology Co.,Ltd. Address before: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant before: Advanced innovation technology Co.,Ltd. Effective date of registration: 20200923 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant after: Advanced innovation technology Co.,Ltd. Address before: A four-storey 847 mailbox in Grand Cayman Capital Building, British Cayman Islands Applicant before: Alibaba Group Holding Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |