WO2021143098A1

WO2021143098A1 - Method, apparatus, electronic device, and storage medium for automatically adjusting user priority

Info

Publication number: WO2021143098A1
Application number: PCT/CN2020/105547
Authority: WO
Inventors: 米扬
Original assignee: 深圳壹账通智能科技有限公司
Priority date: 2020-01-13
Filing date: 2020-07-29
Publication date: 2021-07-22
Also published as: CN111274351A

Abstract

Provided are a method, apparatus, electronic device, and storage medium for automatically adjusting user priority, said method comprising: obtaining an identifier of a user whose user label is an initial label (S100); on the basis of said user identifier, sending a return-visit voice to the user (S110); obtaining the reply voice of the user to the return-visit voice (S120); on the basis of natural language processing (NLP) technology, obtaining text information corresponding to the reply voice (S130); on the basis of a preset keyword table, searching in the text information for keywords matching said keyword table (S140); if a keyword is found in the text information, then updating the user label from the initial label to a first label; if no keyword is found in the text information, then updating the user label from the initial label to a second label (S150); increasing the priority of the user whose user label is the first label, and decreasing the priority of the user whose user label is the second label (S160). The method can identify users having high priority, and is conducive to prioritizing the allocation of resources to users having high priority, improving the matching rate and utilization of resources, and reducing the waste of resources.

Description

Method, device, electronic equipment and storage medium for automatically adjusting user priority

This application is based on and claims the priority of the Chinese patent application CN202010033122.6 filed on January 13, 2020 with the title of "Method, Apparatus, Electronic Equipment and Storage Medium for Automatically Adjusting User Priority", which is hereby incorporated by reference All content is merged here.

Technical field

This application relates to the field of machine learning in the field of artificial intelligence, and in particular to a method, device, electronic device, and storage medium for automatically adjusting user priority.

Background technique

With the development of network technology and the rise of new media, the amount of information received by user terminals has increased dramatically. The inventor realized that terminals that push various resources generally send related resources to the user terminal together, and usually do not consider whether the user needs it or not. This resource also lacks interaction with users to understand user needs, and cannot push the required resources for users in a targeted manner, causing some resources to mismatch with user needs, which results in a waste of resources.

For example, after a patient asks a doctor online or offline, the follow-up usually requires the patient to go to the clinic or hospital for re-examination again. There is a lack of follow-up and return visits to the patient’s recovery status. Moreover, with the rise of Internet hospitals and private mid-to-high-end clinics, there is an urgent need to provide high-end medical services. Quality, efficient service and real-time care. Traditional doctor-patient communication requires patients to report their condition to the doctor after registering at the hospital, which takes a long time and cannot inform the doctor of the patient’s condition in time. Since the doctor cannot grasp the patient’s recovery in time, he cannot give priority to patients with more serious conditions. Treatment causes mismatch of medical resources and waste of resources.

For another example, when the media pushes related information resources, there is a lack of communication and feedback mechanisms with users, and it is impossible to push information resources that users are interested in or need. As a result, many push resources are not effectively read, or due to excessive information resources. Pushing may cause confusion to users who originally needed a certain piece of information resources, and even no longer pay attention to or receive the media. Due to the mismatch of information resources, users are lost and information resources are wasted.

Summary of the invention

In order to solve the problem of resource waste due to the mismatch between some resources and user needs, the present application provides a method, device, electronic device, and storage medium for automatically adjusting user priority.

According to the first aspect of the present application, a method for automatically adjusting user priority is provided, including:

Acquiring an identifier of a user whose user tag is the initial tag;

Sending a return visit voice to the user based on the identity of the user;

Acquiring the user's reply voice for the return visit voice;

Obtain the text information corresponding to the reply voice based on natural language processing NLP technology;

Searching for keywords matching the keyword table in the text information based on a preset keyword table;

When the keyword is searched out from the text information, the user tag is updated from the initial tag to the first tag, and when the keyword cannot be searched out from the text information, the user tag is updated The user label is updated from the initial label to the second label;

The priority of the user whose user label is the first label is increased, and the priority of the user whose user label is the second label is lowered.

According to the second aspect of the present application, there is provided a device for automatically adjusting user priority, including:

The first obtaining module is configured to obtain an identification of a user whose user tag is an initial tag;

A sending module, configured to send a return visit voice to the user based on the user's identity;

The second obtaining module is configured to obtain the reply voice of the user for the return visit voice;

The third acquisition module is configured to acquire text information corresponding to the reply voice based on natural language processing NLP technology;

The search module is configured to search for keywords matching the keyword table in the text information based on a preset keyword table;

The update module is configured to update the user tag from the initial tag to the first tag when the keyword is searched out from the text information, and when the keyword cannot be searched out from the text information When, update the user label from the initial label to the second label;

The priority adjustment module is configured to increase the priority of the user whose user label is the first label, and lower the priority of the user whose user label is the second label.

According to the third aspect of the present application, there is provided an electronic device that automatically adjusts user priority, including:

Memory, configured to store executable instructions;

The processor is configured to execute executable instructions stored in the memory, and the processor is configured to execute the following processing when executing the executable instructions:

Acquiring an identifier of a user whose user tag is the initial tag;

Sending a return visit voice to the user based on the identity of the user;

Acquiring the user's reply voice for the return visit voice;

According to a fourth aspect of the present application, a computer-readable program medium is provided, which stores computer program instructions, and when the computer program instructions are executed by a computer, the computer executes the following processing:

Acquiring an identifier of a user whose user tag is the initial tag;

Sending a return visit voice to the user based on the identity of the user;

Acquiring the user's reply voice for the return visit voice;

The technical solutions provided by the embodiments of the present application may include the following beneficial effects:

This application discloses a method, device, electronic equipment and storage medium for automatically adjusting user priority. Through this method, the priority of users can be automatically adjusted, so that the background control terminal can preferentially allocate related resources to users with high priority, so as to improve the matching rate and utilization of resources and reduce the waste of resources.

Other characteristics and advantages of the present application will become apparent through the following detailed description, or partly learned through the practice of the present application.

It should be understood that the above general description and the following detailed description are only exemplary and cannot limit the application.

Description of the drawings

The drawings here are incorporated into the specification and constitute a part of the specification, show embodiments conforming to the application, and are used together with the specification to explain the principle of the application.

Fig. 1 is a flowchart showing a method for automatically adjusting user priority according to an exemplary embodiment.

FIG. 2 is a flowchart of the steps of sending a return visit voice to the user based on the user's identity in the embodiment corresponding to FIG. 1.

Fig. 3 Fig. 1 corresponds to a flowchart of the steps after increasing the priority of the user whose user label is the first label, and lowering the priority of the user whose user label is the second label.

Fig. 4 shows a diagram of an apparatus for automatically adjusting user priority according to an exemplary embodiment of the present application.

Fig. 5 shows an architecture diagram of automatically adjusting user priority according to an exemplary embodiment of the present application.

Fig. 6 shows a diagram of an electronic device that automatically adjusts user priority according to an exemplary embodiment of the present application.

Fig. 7 shows a diagram of a computer-readable storage medium that automatically adjusts user priorities according to an exemplary embodiment of the present application.

Detailed ways

Here, an exemplary embodiment will be described in detail, and examples thereof are shown in the accompanying drawings. When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementation manners described in the following exemplary embodiments do not represent all implementation manners consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the application as detailed in the appended claims.

In addition, the described features, structures, or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to give a sufficient understanding of the embodiments of the present application. Then, those skilled in the art should understand that the technical solutions of the present application can be practiced without one or more of the specific details, or other methods, group members, steps, etc. can be used. In other cases, well-known structures, methods, implementations, or operations are not shown or described in detail to avoid overwhelming people and obscuring all aspects of the present application.

Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in the form of software, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and/or processor devices and/or microcontroller devices.

This application discloses a method for automatically adjusting the priority of users, and its purpose is to determine users with high priority, improve the matching rate and utilization of resources, and reduce the waste of resources. The method includes: obtaining an identification of a user whose user tag is the initial tag; sending a return speech to the user based on the user identification; obtaining the user's reply voice for the return speech; obtaining text information corresponding to the reply voice based on natural language processing technology; Based on the preset keyword table, search for keywords matching the keyword table in the text information; when the keyword is searched out from the text information, the user tag is updated from the initial tag to the first tag. When a keyword is searched, the user label is updated from the initial label to the second label; the priority of the user of the first label is increased, and the priority of the user of the second label is lowered. This method can determine users with high priority levels, which is beneficial to prioritize the allocation of resources to users with high priority levels, improve the matching rate and utilization of resources, and reduce resource waste.

Fig. 1 is a flow chart showing a method for automatically adjusting user priority according to an exemplary embodiment. As shown in the figure, the method includes:

Step S100: Obtain an identifier of a user whose user tag is the initial tag;

Step S110: Send a return visit voice to the user based on the user's identity;

Step S120: Obtain the reply voice of the user for the return visit voice;

Step S130: Acquire text information corresponding to the reply voice based on natural language processing NLP technology;

Step S140: Based on a preset keyword table, search for keywords that match the keyword table in the text information;

Step S150: When the keyword is searched out from the text information, update the user tag from the initial tag to the first tag, and when the keyword cannot be searched out from the text information, Updating the user label from the initial label to the second label;

Step S160: Increase the priority of the user whose user label is the first label, and lower the priority of the user whose user label is the second label.

In order to facilitate understanding and clearly explain the method, the method will be further described below in conjunction with specific implementation scenarios and embodiments and corresponding drawings.

In an application scenario, after a patient sees a doctor, he can learn about the patient’s needs and recovery status through an automatic return visit, so that the doctor can view the corresponding question voice feedback and related questions through the background control terminal according to the priority level of the patient who has not recovered after the return visit. Data so that doctors can pay attention to the patient’s recovery.

In this scenario, the specific implementation steps of the method include:

Referring to Fig. 1, step S100 is to obtain an identification of a user whose user tag is an initial tag.

When a patient logs in to a related APP (such as Ping An Good Doctor) through a mobile phone, uses a medical insurance card, scans a two-dimensional code, etc., the user's identification is obtained, and the corresponding label of the user's identification is set as the initial identification.

The identification of the user includes the user's phone number, WeChat ID, QQ number, mailbox, etc.

Before the step S100 acquiring the identification of the user whose user tag is the initial tag, the method further includes:

For each user whose user tag is the initial tag, obtain the attribute data of the user;

Based on the attribute data of the user, the priority corresponding to the user is determined.

Among them, for users who have been registered, the user’s identification is obtained to match and retrieve the stored user’s attribute data from the database. For newly registered users, they can obtain the first This is not the only way to obtain the medical insurance card through the Internet when using the medical insurance card or through the local cloud system that the doctor logs into the network during on-site consultation with the doctor.

Wherein, the attribute data of the user includes age data, gender data, and problem description of the user.

According to the obtained user attribute data, a score corresponding to the priority is obtained through calculation to determine the priority corresponding to the user.

When the attribute data of the user includes the user's problem description, before the priority corresponding to the user is determined, it includes:

Get the user’s problem description;

Extract the problem keywords in the problem description;

Based on the question keyword and the preset question keyword table, the question matching value of the user is obtained.

The user attribute data obtained in the first step includes the user’s problem description. The problem description is mainly the patient’s description of their own condition, such as which part of the body is uncomfortable or painful, whether there is fever, cough, vomiting, convulsions, dizziness , Tinnitus, set a corresponding question keyword table for the question keywords that may appear in the problem description, and based on the question keyword table, the user's question matching value can be obtained correspondingly to calculate the user's priority.

Among them, the above question keyword table can be set to the following mode:

Preset 5 keywords for the problem description, search whether the preset keywords appear in the problem description, when the problem description includes 3-5 keywords, B=1000; when the problem description contains less than 3 keywords, B ＝300 (the above numerical value and the number of keywords are only examples for explanation and explanation)

The above is only one form of the problem keyword table setting, and there can be other setting methods, for example: preset multiple keywords for the problem description, and each keyword describes the sign or symptom of the corresponding disease. According to the actual medical experience, each keyword is assigned a different value, and the sum of the corresponding values of all keywords extracted according to the problem description is used as the corresponding problem matching value.

The attribute data of the user further includes age data and gender data of the user, and the determining the priority corresponding to the user based on the attribute data of the user includes:

Determining the age matching value of the user based on the age data of the user;

Determining the gender matching value of the user based on the gender data of the user;

The user’s rating is determined according to the following formula:

R=(A*a+B)+C/(A’*B’)

Where, A is the age matching value of the user, B is the question matching value of the user, C is the gender matching value of the user, a is the age correction coefficient, A'is the standard age matching value, and B'is the standard Question matching value; R is the final score of the user;

Based on the score of the user, the priority corresponding to the user is determined.

Based on the acquired user attribute data, the corresponding age matching value and gender matching value are obtained according to the age data and gender data in the user attribute data through the preset age matching value table and gender matching value table, and the problem matching in the above steps is combined The value is brought into the user scoring formula, calculated to obtain the user’s score, and the user’s priority is determined based on the matching of the preset priority table in the subsequent steps through the score of each user.

In the foregoing, the corresponding age matching value and gender matching value are obtained according to the age data and gender data in the user attribute data through the preset age matching value table and gender matching value table.

Wherein, based on the age data of the user, the age matching value of the user is determined through a preset age matching value table. Specifically, corresponding matching values can be set for different age groups according to different age groups of the users, such as:

When the age is 0-18 years old, it is taken as 100; when the age is 19-60 years old, it is taken as 70; when it is over 60 years old, it is taken as 120.

The above setting is an example, not a limitation. The age matching value is based on the resistance of the human body. The resistance of infants and the elderly is relatively low, while the resistance of young adults is relatively high. This is used as a basis for age The segment sets the corresponding matching value, that is, the preset age matching value, so that the corresponding age matching value can be obtained according to the user's age data.

Based on the gender data of the user, the gender matching value of the user is determined through a preset gender matching value table, for example:

When the gender is male, the gender matching value is 0.01; when the gender is female, the gender matching value is 0.012; the gender matching value corresponding to different genders above is the preset gender matching value table. The gender matching value difference between men and women is small, but because the probability and degree of different genders of some diseases are different, fine-tuning is made by increasing the gender matching value. The above gender matching value is only an example. For different diseases, It can be set according to the actual situation.

A'is the standard value of the adopted age. This value is a default value, which represents the age matching value of a normal healthy person in the young and middle age. For example, taking the above age matching value table as an example, A'can take 50 , Or other values lower than 70.

B'is the standard question matching value, and this value is also a default value. For example, in the way exemplified in step (2), B'=70, or other values lower than 300.

a is the age correction parameter. For example, when taking the value according to the above-mentioned age matching value table, when A=100, a=0.2; A=70; a=0.1; A=120, a=0.25; the age correction parameter is for further Highlight the proportion of the problem matching value in the numerator of the formula (R=(A*a+B)+C/(A'*B')), through the age correction coefficient, under the influence of the age factor, highlight the problem matching The proportion of the value, because the focus is still on the priority of the user’s condition, rather than the age factor.

Through the above calculation formula, the score of each user is calculated, and the priority of the user is determined based on the matching of the preset priority table in the subsequent steps. Wherein, the preset priority table can be set to directly use the user’s score as the user’s priority based on the score of each user; for example, the calculated first user’s score is 100, and the second user’s score is 100. If the score is 90, the score value is the user’s priority level, and the priority among users is determined in descending order. As in the above example, since the first user’s score is higher than the second user’s score, Therefore, the priority of the first user is higher than the priority of the second user.

The above is only one implementation of the preset priority table setting, and there are other ways. For example, users in a score segment can be set to the same priority according to the calculated user score, such as 90-99 is set as the first priority, 80-89 is set as the second priority.

The foregoing manner of setting the preset priority table is only an example, but is not limited to the foregoing implementation manner.

The type of the above-mentioned database is not limited, and it can be a cloud database or a local database in the hospital.

Please continue to refer to FIG. 1, in step S110, based on the user's identity, a return visit voice is sent to the user.

According to the user identification obtained in the previous step, the return visit voice is sent to the corresponding user. The content of the return visit voice sent can be selected according to the department where the doctor is located, and the corresponding problem template can be selected, and the doctor can adjust the problem template according to the actual diagnosis experience Content to meet actual needs.

As shown in Fig. 2, in step S110, sending a return visit voice to the user based on the user's identity may further include:

Step S1101 determines the priority of the user based on the match between the user's identity and a preset priority table, where the priority table describes the user priority corresponding to the user's identity;

Step S1102, based on the matching between the user priority and the preset interval timetable, determine the interval time for sending the return visit voice to the user, where the return visit timetable describes the interval time corresponding to the user priority;

Step S1103 sends a return visit voice to the user after the interval time at the current time point.

The user’s score is calculated through the user’s attribute data, and then based on the matching of the preset priority table, the user’s priority can be determined, and the user attribute corresponds to the user’s identity one-to-one, so the priority The table actually describes the user priority corresponding to the user's identity.

Further, based on the matching between the user priority and the preset interval timetable, the interval time for sending the return visit voice to the user can be determined, and the time interval in the return visit timetable corresponds to each user priority.

Finally, when the patient sees a doctor or asks a doctor after a preset interval time, a return visit voice is sent to the patient through the user's identification.

Please continue to refer to FIG. 1, step S120 obtains the user's reply voice for the return visit voice.

Based on the return voice sent to the user in the previous step, when the user answers the return voice, the user answers the questions preset by the return voice to obtain the user's response voice; the sent return voice and the obtained user reply The voice will be stored in the database.

Please continue to refer to FIG. 1. In step S130, the text information corresponding to the reply voice is obtained based on the natural language processing NLP technology.

After obtaining the user's reply voice in the previous step, the reply voice is parsed into computer-recognizable text information based on natural language processing NLP technology; the corresponding text information of the obtained reply voice will also be stored in the database for subsequent doctors to pass The control terminal in the background calls and checks.

Please continue to refer to FIG. 1. In step S140, based on a preset keyword table, search for keywords that match the keyword table in the text information;

Step S150: When the keyword is searched from the text information, the user tag is updated from the initial tag to the first tag, and when the keyword cannot be searched from the text information, the user tag is updated The user label is updated from the initial label to the second label;

In step S160, the priority of the user whose user label is the first label is increased, and the priority of the user whose user label is the second label is lowered.

Through the above steps, if the text content obtained in step S130 can search for keywords matching the keyword table, the user tag of the user is changed from the default to the first tag, and the user priority is increased; if not A keyword matching the keyword table can be searched from the obtained text content, then the user label of the user is changed from the default to the second label, and the user's priority is lowered.

In step S140, searching for a keyword matching the keyword table in the text information based on a preset keyword table further includes:

The preset keyword table includes a plurality of keywords, and each keyword is set to a corresponding increase level in the keyword table;

When the keyword is searched out from the text information, the user tag is updated from the initial tag to the first tag, and the user tag is assigned to the user tag according to the up-level corresponding to the searched keyword The user of the first label correspondingly increases the level.

The foregoing preset keyword table includes multiple keywords, and each keyword is set to a corresponding increase level in the keyword table. The specific implementation manner may be as follows:

The preset keyword table includes multiple keywords, and each keyword is assigned a different value. For example, "Still hurt" is set to a score of 0.2, "Uncomfortable" is set to a score of 0.5, and "I feel dying" Set the score to 1. When there are multiple keywords, the sum of the corresponding values of the multiple keywords can be used as the corresponding up-regulation score, and the score of the score can be used as the basis for the up-regulation.

Through the above calculation formula R=(A*a+B)+C/(A'*B'), the score of each user is calculated, and based on the matching of the preset priority table in the subsequent steps, the user’s rating is determined priority. When the user's score is directly calculated as the user's own priority level, the user's score is correspondingly increased according to the above keyword score, and then the user's own priority level is correspondingly increased.

That is, in this embodiment, setting the corresponding score for the keyword in the keyword table is the corresponding increase level. The above scores are just examples, and not only the above scores can be used.

Another implementation method can also be adopted: when the more keywords are retrieved, the higher the value is given, and the higher the corresponding upward adjustment level is. For example, suppose that the preset keyword table is set to have a score of 1 when 10 keywords appear, a score of 0.5 when five keywords appear, and a score of 0.1 when one keyword appears, thus forming a gradient of scores. The corresponding score is the corresponding increase level.

The method of setting the keyword table and increasing the level is not limited to the above method, and different values or corresponding methods can also be adopted according to the difference of each department and each disease type.

As shown in FIG. 3, after step S160 increases the priority of the user whose user label is the first label, and lowers the priority of the user whose user label is the second label, the method further includes:

In step S170, an adjusted priority list of all users is obtained according to the priority of the user after the adjustment is increased or decreased.

By performing the above steps, the automatically adjusted user priority list after returning to the patient is obtained. The doctor can view the patient's response from the highest priority to the bottom from the back-end control terminal, and can also retrieve the patient's response voice to understand the patient's status in time. Recent illnesses.

Through the above method, the priority of patients can be automatically obtained, so that doctors can diagnose and treat patients with high priority in a targeted manner, improve the matching rate and utilization of medical resources, and reduce the waste of medical resources.

In another application scenario, according to the behavior data of previously registered users, different user groups are divided into different priority levels, and the priority list of registered users is obtained in order of priority from high to low. High and low set the time period for pushing relevant content and question feedback survey or the time of return visit.

When a new user registers, the newly registered information includes the user's contact information and user preferences, usage habits, frequency of use and other behavioral data. By comparing with the behavior data of previously registered users, the registered user group that best matches the new user is determined, and the priority level of the group is assigned to the new user. And according to the pre-set survey cycle or return visit time through the contact information of new customers to push relevant content or question feedback survey.

According to the survey feedback of the newly registered users on the push content (the voice content of the survey feedback is uploaded and stored in the database), based on the NLP voice technology, the new user’s voice response content is parsed into text content, and keywords are searched, such as "unsatisfied", " Keywords such as “not good”, “annoying”, and “dislike”, when the keyword appears, mark the user as pending confirmation, increase the priority of the newly registered user, and re-update the entire registered user’s Priority level list.

For newly registered users who are not satisfied with the current push content, the background control terminal can view the corresponding problem feedback and their behavior data according to the priority level, and change the relevant push content with high matching degree in a targeted manner to improve the matching rate of information resources and avoid users Of the loss.

Since the steps and specific embodiments of how to implement the automatic priority determination method have been recorded in detail in the previous scenario, those skilled in the art can make modifications or modifications through the specific steps and specific embodiments described above to meet the requirements in another scenario. Therefore, I will not repeat it.

It is worth noting that the above two scenarios are only implementations of the specific application of this method, and do not limit the implementation steps, processes, or implementation scope of this method. This method can also be applied to other similar scenarios that need to solve resource allocation.

In an embodiment, as shown in FIG. 4, an apparatus for automatically adjusting user priority is provided, which specifically includes: a first obtaining module 210, a sending module 220, a second obtaining module 230, and a third obtaining module 240 , Search module 250, update module 260, priority adjustment module 270.

The first obtaining module 210 is configured to obtain an identification of a user whose user tag is an initial tag;

The sending module 220 is configured to send a return visit voice to the user based on the user's identity;

The second obtaining module 230 is configured to obtain the user's reply voice for the return visit voice;

The third obtaining module 240 is configured to obtain the text information corresponding to the reply voice based on the natural language processing NLP technology;

The search module 250 is configured to search for keywords matching the keyword table in the text information based on a preset keyword table;

The update module 260 is configured to update the user tag from the initial tag to the first tag when the keyword is searched from the text information, and when the key cannot be searched from the text information When writing a word, update the user label from the initial label to the second label;

The priority adjustment module 270 is configured to increase the priority of the user whose user label is the first label, and lower the priority of the user whose user label is the second label.

For the implementation process of the functions and roles of each module in the above-mentioned device, refer to the implementation process of corresponding steps in the above-mentioned method for automatically adjusting user priority, which will not be repeated here.

It should be noted that although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules or units described above may be embodied in one module or unit. Conversely, the features and functions of a module or unit described above can be further divided into multiple modules or units to be embodied.

In addition, although the various steps of the method in the present application are described in a specific order in the drawings, this does not require or imply that these steps must be performed in the specific order, or that all the steps shown must be performed to achieve the desired result. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step for execution, and/or one step may be decomposed into multiple steps for execution, etc.

Through the description of the above embodiments, those skilled in the art can easily understand that the example embodiments described here can be implemented by software, or can be implemented by combining software with necessary hardware. Therefore, the technical solution according to the embodiments of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, U disk, mobile hard disk, etc.) or on the network , Including several instructions to make a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) execute the method according to the embodiment of the present application.

Fig. 5 shows an architecture diagram of a system for automatically adjusting user priority according to an exemplary embodiment of the present application. The system architecture includes a database 310, a user terminal 320, and a background control terminal 330. Wherein, the database 310 obtains an identification of a user whose user tag is the initial tag from the user terminal 320, and based on the user identification, sends a return visit voice to the user. After receiving the return visit voice sent by the user, the user terminal 320 responds to The content of the return visit voice is verbally responded, and the database 310 obtains the user's reply voice for the return visit voice, and based on natural language processing NLP technology, obtains the text information corresponding to the reply voice, based on a preset keyword table, Search for keywords that match the keyword table in the text information. When the database 310 searches for the keyword from the text information, the user tag is updated from the initial tag to the first tag. When the keyword cannot be searched from the text information, the user tag is updated. The user tag is updated from the initial tag to the second tag, and the user's priority level is adjusted accordingly. The background control terminal 330 can retrieve the database 310 to view the user, and give the user a corresponding priority according to the user's priority. The terminal 320 allocates corresponding resources, and can also supplement and modify the database 310 or update the voice content of the return visit.

Through the above description of the system architecture, those skilled in the art can easily understand that the system architecture described here can realize the functions of each module in the apparatus for automatically adjusting user priority shown in FIG. 4.

In an exemplary embodiment of the present application, an electronic device capable of implementing the above method is also provided.

Those skilled in the art can understand that various aspects of the present application can be implemented as a system, a method, or a program product. Therefore, each aspect of this application can be specifically implemented in the following forms, namely: complete hardware implementation, complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software implementations, which can be collectively referred to herein as "Circuit", "Module" or "System".

The electronic device 400 according to this embodiment of the present application will be described below with reference to FIG. 6. The electronic device 400 shown in FIG. 6 is only an example, and should not bring any limitation to the function and scope of use of the embodiments of the present application.

As shown in FIG. 6, the electronic device 400 is represented in the form of a general-purpose computing device. The components of the electronic device 400 may include, but are not limited to: the aforementioned at least one processing unit 410, the aforementioned at least one storage unit 420, and a bus 430 connecting different system components (including the storage unit 420 and the processing unit 410).

Wherein, the storage unit stores program code, and the program code can be executed by the processing unit 410, so that the processing unit 410 executes the various exemplary methods described in the "Exemplary Method" section of this specification. Steps of implementation. For example, the processing unit 410 may perform the steps shown in FIG. 1:

Step S100 obtains an identifier of a user whose user tag is the initial tag;

Step S110, based on the user's identity, send a return visit voice to the user;

Step S120: Obtain the reply voice of the user for the return visit voice;

Step S130 is based on natural language processing NLP technology to obtain text information corresponding to the reply voice;

Step S140, based on a preset keyword table, search for keywords that match the keyword table in the text information;

The storage unit 420 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 4201 and/or a cache storage unit 4202, and may further include a read-only storage unit (ROM) 4203.

The storage unit 420 may also include a program/utility tool 4204 having a set (at least one) program module 4205. Such program module 4205 includes but is not limited to: an operating system, one or more application programs, other program modules, and program data, Each of these examples or some combination may include the implementation of a network environment.

The bus 430 may represent one or more of several types of bus structures, including a storage unit bus or a storage unit controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local area using any bus structure among multiple bus structures. bus.

The electronic device 400 may also communicate with one or more external devices 500 (such as keyboards, pointing devices, Bluetooth devices, etc.), and may also communicate with one or more devices that enable a user to interact with the electronic device 400, and/or communicate with Any device (such as a router, modem, etc.) that enables the electronic device 400 to communicate with one or more other computing devices. This communication can be performed through an input/output (I/O) interface 450. In addition, the electronic device 400 may also communicate with one or more networks (for example, a local area network (LAN), a wide area network (WAN), and/or a public network, such as the Internet) through the network adapter 460. As shown in the figure, the network adapter 460 communicates with other modules of the electronic device 400 through the bus 430. It should be understood that although not shown in the figure, other hardware and/or software modules can be used in conjunction with the electronic device 400, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives And data backup storage system, etc.

Through the description of the above embodiments, those skilled in the art can easily understand that the example embodiments described here can be implemented by software, or can be implemented by combining software with necessary hardware. Therefore, the technical solution according to the embodiments of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, U disk, mobile hard disk, etc.) or on the network , Including several instructions to make a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) execute the method according to the embodiment of the present application.

In the exemplary embodiment of the present application, a computer-readable storage medium is also provided. The computer-readable storage medium may be non-volatile or volatile. The program product of the method. In some possible implementation manners, various aspects of the present application can also be implemented in the form of a program product, which includes program code. When the program product runs on a terminal device, the program code is used to make the The terminal device executes the steps according to various exemplary embodiments of the present application described in the above-mentioned "Exemplary Method" section of this specification.

Referring to FIG. 7, a program product 600 for implementing the above method according to an embodiment of the present application is described. It can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be installed in a terminal device, For example, running on a personal computer. However, the program product of this application is not limited to this. In this document, the readable storage medium can be any tangible medium that contains or stores a program, and the program can be used by or in combination with an instruction execution system, device, or device.

The program product can use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or a combination of any of the above. More specific examples (non-exhaustive list) of readable storage media include: electrical connections with one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable Type programmable read only memory (EPROM or flash memory), optical fiber, portable compact disk read only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.

The computer-readable signal medium may include a data signal propagated in baseband or as a part of a carrier wave, and readable program code is carried therein. This propagated data signal can take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. The readable signal medium may also be any readable medium other than a readable storage medium, and the readable medium may send, propagate, or transmit a program for use by or in combination with the instruction execution system, apparatus, or device.

The program code contained on the readable medium can be transmitted by any suitable medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

The program code used to perform the operations of the present application can be written in any combination of one or more programming languages. The programming languages include object-oriented programming languages—such as Java, C++, etc., as well as conventional procedural programming languages. Programming language-such as "C" language or similar programming language. The program code can be executed entirely on the user's computing device, partly on the user's device, executed as an independent software package, partly on the user's computing device and partly executed on the remote computing device, or entirely on the remote computing device or server Executed on. In the case of a remote computing device, the remote computing device can be connected to a user computing device through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (for example, using Internet service providers). Business to connect via the Internet).

In addition, the above-mentioned drawings are merely schematic illustrations of the processing included in the method according to the exemplary embodiments of the present application, and are not intended for limitation. It is easy to understand that the processing shown in the above drawings does not indicate or limit the time sequence of these processings. In addition, it is easy to understand that these processes can be executed synchronously or asynchronously in multiple modules, for example.

After considering the specification and practicing the invention disclosed herein, those skilled in the art will easily think of other embodiments of the present application. This application is intended to cover any variations, uses, or adaptive changes of this application. These variations, uses, or adaptive changes follow the general principles of this application and include common knowledge or customary technical means in the technical field that are not disclosed in this application. . The description and the embodiments are only regarded as exemplary, and the true scope and spirit of the application are pointed out by the claims.

Claims

A method for automatically adjusting user priority, wherein the method includes:

Acquiring an identifier of a user whose user tag is the initial tag;

Sending a return visit voice to the user based on the identity of the user;

Acquiring the user's reply voice for the return visit voice;

Obtain the text information corresponding to the reply voice based on natural language processing NLP technology;

Searching for keywords matching the keyword table in the text information based on a preset keyword table;

When the keyword is searched out from the text information, the user tag is updated from the initial tag to the first tag, and when the keyword cannot be searched out from the text information, the user tag is updated The user label is updated from the initial label to the second label;

The priority of the user whose user label is the first label is increased, and the priority of the user whose user label is the second label is lowered.
The method according to claim 1, wherein, before said obtaining the identification of the user whose user tag is the initial tag, the method comprises:

For each user whose user tag is the initial tag, obtain the attribute data of the user;

Based on the attribute data of the user, the priority corresponding to the user is determined.
The method according to claim 2, wherein the attribute data of the user includes a description of the user's problem, and before determining the priority corresponding to the user, the method includes:

Get the user’s problem description;

Extract the problem keywords in the problem description;

Based on the question keyword and the preset question keyword table, the question matching value of the user is obtained.
The method according to claim 3, wherein the attribute data of the user further includes age data and gender data of the user, and the determining the priority corresponding to the user based on the attribute data of the user includes:

Determining the age matching value of the user based on the age data of the user;

Determining the gender matching value of the user based on the gender data of the user;

The user’s score is determined according to the following formula: R=(A*a+B)+C/(A'*B'), where A is the user’s age matching value and B is the user’s question matching value , C is the gender matching value of the user, a is the age correction coefficient, A'is the standard age matching value, and B'is the standard question matching value;

Based on the score of the user, the priority corresponding to the user is determined.
The method according to claim 1, wherein the sending a return visit voice to the user based on the user's identity comprises:

Determining the priority of the user based on the match between the user's identification and a preset priority table, the priority table describing the user priority corresponding to the user's identification;

Determining an interval time for sending a return visit voice to the user based on the match between the user priority and a preset interval time table, the return visit time table describing the interval time corresponding to the user priority;

Send a return visit voice to the user after the interval time at the current time point.
The method according to claim 1, wherein the searching for a keyword matching the keyword table in the text information based on a preset keyword table further comprises:

The preset keyword table includes a plurality of keywords, and each keyword is set to a corresponding increase level,

When the keyword is searched out from the text information, the user tag is updated from the initial tag to the first tag, and the user tag is assigned according to the up-level corresponding to the keyword searched for The user of the first label correspondingly increases the level.
The method according to claim 6, wherein after increasing the priority of the user whose user tag is the first tag and lowering the priority of the user whose user tag is the second tag, the method further comprises:

Obtain the adjusted priority list of all users according to the priority of the users after the adjustment is increased or decreased.
An electronic device that automatically adjusts user priority, including:

Memory, configured to store executable instructions;

The processor is configured to execute executable instructions stored in the memory, where the processor is configured to execute the following processing when executing the executable instructions:

Acquiring an identifier of a user whose user tag is the initial tag;

Sending a return visit voice to the user based on the identity of the user;

Acquiring the user's reply voice for the return visit voice;

Obtain the text information corresponding to the reply voice based on natural language processing NLP technology;

Searching for keywords matching the keyword table in the text information based on a preset keyword table;

When the keyword is searched out from the text information, the user tag is updated from the initial tag to the first tag, and when the keyword cannot be searched out from the text information, the user tag is updated The user label is updated from the initial label to the second label;

The priority of the user whose user label is the first label is increased, and the priority of the user whose user label is the second label is lowered.
8. The electronic device according to claim 8, wherein, before the obtaining the identification of the user whose user tag is the initial tag, the processor is configured to perform the following processing when executing the executable instruction:

For each user whose user tag is the initial tag, obtain the attribute data of the user;

Based on the attribute data of the user, the priority corresponding to the user is determined.
The electronic device according to claim 9, wherein the attribute data of the user includes a description of the user's problem, and before the priority corresponding to the user is determined, the processor is configured to execute the executable instruction when the executable instruction is executed. The following processing:

Get the user’s problem description;

Extract the problem keywords in the problem description;

Based on the question keyword and the preset question keyword table, the question matching value of the user is obtained.
The electronic device according to claim 10, wherein the attribute data of the user further includes age data and gender data of the user, and the processor is configured to perform the following processing when executing the executable instruction Said determining the priority corresponding to the user based on the attribute data of the user:

Determining the age matching value of the user based on the age data of the user;

Determining the gender matching value of the user based on the gender data of the user;

The user’s score is determined according to the following formula: R=(A*a+B)+C/(A'*B'), where A is the user’s age matching value and B is the user’s question matching value , C is the gender matching value of the user, a is the age correction coefficient, A'is the standard age matching value, and B'is the standard question matching value;

Based on the score of the user, the priority corresponding to the user is determined.
The electronic device according to claim 8, wherein the processor is configured to perform the following processing when executing the executable instruction to realize the sending a return visit voice to the user based on the user's identification:

Determining the priority of the user based on the match between the user's identification and a preset priority table, the priority table describing the user priority corresponding to the user's identification;

Determining an interval time for sending a return visit voice to the user based on the matching of the user priority with a preset interval time table, the return visit time table describing the interval time corresponding to the user priority;

Send a return visit voice to the user after the interval time at the current time point.
The electronic device according to claim 8, wherein the processor is configured to perform the following processing when executing the executable instruction to implement the preset-based keyword table, and search for the text information and the Keywords matched by the keyword table:

The preset keyword table includes multiple keywords, and each keyword is set to a corresponding increase level,

When the keyword is searched out from the text information, the user tag is updated from the initial tag to the first tag, and the user tag is assigned according to the up-level corresponding to the keyword searched out as The user of the first label correspondingly increases the level.
A computer-readable storage medium, which stores computer program instructions that, when executed by a computer, cause the computer to perform the following processing:

Acquiring an identifier of a user whose user tag is the initial tag;

Sending a return visit voice to the user based on the identity of the user;

Acquiring the user's reply voice for the return visit voice;

Obtain the text information corresponding to the reply voice based on natural language processing NLP technology;

Searching for keywords matching the keyword table in the text information based on a preset keyword table;

When the keyword is searched out from the text information, the user tag is updated from the initial tag to the first tag, and when the keyword cannot be searched out from the text information, the user tag is updated The user label is updated from the initial label to the second label;

The priority of the user whose user label is the first label is increased, and the priority of the user whose user label is the second label is lowered.
14. The computer-readable storage medium according to claim 14, wherein, before the obtaining the user identification of the user whose user tag is the initial tag, the computer program instructions, when executed by the computer, cause the computer to perform the following processing:

For each user whose user tag is the initial tag, obtain the attribute data of the user;

Based on the attribute data of the user, the priority corresponding to the user is determined.
The computer-readable storage medium according to claim 15, wherein the attribute data of the user includes a description of the user's problem, and before the priority corresponding to the user is determined, the computer program instructions cause the computer to Perform the following processing:

Get the user’s problem description;

Extract the problem keywords in the problem description;

Based on the question keyword and the preset question keyword table, the question matching value of the user is obtained.
The computer-readable storage medium according to claim 16, wherein the attribute data of the user further includes age data and gender data of the user, and the computer program instructions when executed by the computer cause the computer to perform the following processing to achieve The determining the priority corresponding to the user based on the attribute data of the user:

Determining the age matching value of the user based on the age data of the user;

Determining the gender matching value of the user based on the gender data of the user;

The user’s score is determined according to the following formula: R=(A*a+B)+C/(A'*B'), where A is the user’s age matching value and B is the user’s question matching value , C is the gender matching value of the user, a is the age correction coefficient, A'is the standard age matching value, and B'is the standard question matching value;

Based on the score of the user, the priority corresponding to the user is determined.
The computer-readable storage medium according to claim 14, wherein the computer program instructions, when executed by the computer, cause the computer to perform the following processing to realize the sending of a return visit voice to the user based on the user's identification:

Determining the priority of the user based on the match between the user's identification and a preset priority table, the priority table describing the user priority corresponding to the user's identification;

Determining an interval time for sending a return visit voice to the user based on the matching of the user priority with a preset interval time table, the return visit time table describing the interval time corresponding to the user priority;

Send a return visit voice to the user after the interval time at the current time point.
The computer-readable storage medium according to claim 14, wherein, when the computer program instructions are executed by a computer, the computer executes the following processing to realize the preset keyword table based on searching the text information and all Describe the matched keywords in the keyword table:

The preset keyword table includes multiple keywords, and each keyword is set to a corresponding increase level,

When the keyword is searched out from the text information, the user tag is updated from the initial tag to the first tag, and the user tag is assigned according to the up-level corresponding to the keyword searched out as The user of the first label correspondingly increases the level.
A device for automatically adjusting user priority, which includes:

The first obtaining module is configured to obtain an identification of a user whose user tag is an initial tag;

A sending module, configured to send a return visit voice to the user based on the user's identity;

The second obtaining module is configured to obtain the reply voice of the user for the return visit voice;

The third acquisition module is configured to acquire text information corresponding to the reply voice based on natural language processing NLP technology;

The search module is configured to search for keywords matching the keyword table in the text information based on a preset keyword table;

The update module is configured to update the user tag from the initial tag to the first tag when the keyword is searched from the text information, and when the keyword cannot be searched from the text information When, update the user label from the initial label to the second label;

The priority adjustment module is configured to increase the priority of the user whose user label is the first label, and lower the priority of the user whose user label is the second label.