WO2017215248A1

WO2017215248A1 - Method, system and device for selecting target user

Info

Publication number: WO2017215248A1
Application number: PCT/CN2016/113225
Authority: WO
Inventors: 张奎
Original assignee: 广州视睿电子科技有限公司
Priority date: 2016-06-14
Filing date: 2016-12-29
Publication date: 2017-12-21
Also published as: CN106126880A

Abstract

A method, system and device for selecting a target user. The method comprises: acquiring a selection instruction sent by a control apparatus, and reading attribute information representing the association relationship between each user and a pre-set constraint condition in response to the selection instruction (S1); selecting a target user from the various users according to the attribute information (S2); and acquiring a unique identifier corresponding to a receiving apparatus of the target user, and sending a notification message to the receiving apparatus of the target user according to the unique identifier (S3), wherein various receiving apparatuses are provided with unique identifiers distinguishable from one another, and each identifier corresponds to a unique user. The method, system and device for selecting a target user can reduce the subjective effect caused by a subject, thereby improving the accuracy of target selection.

Description

Target user selection method, system and device

Technical field

The present invention relates to the field of communications technologies, and in particular, to a method, system, and device for selecting a target user.

Background technique

In practical applications, it is often necessary to extract one or more target objects with certain target attributes from a series of candidate sets, and then speculate the characteristics of the objects in the entire set according to the characteristics of the selected target objects. Existing selection methods are generally selected by hand. For example, when conducting product quality checks, especially when the number of products is large, it is impossible to check the quality of each product. Generally, quality inspectors randomly select some quality samples from the products. For example, in the classroom, teachers often select students to answer questions. However, the existing target selection method is subjectively influenced by the selected subject, which makes it difficult to objectively reflect the characteristics of the selected set. For example, in the above-mentioned example of product quality inspection, products that are generally located near the outside are easier to spot, and products that are located inside or in the corner are not easily spotted. For another example, in the above-mentioned example of teacher questioning, the teacher would prefer to select a student who is close to the stage. Since there is a bias in the selection of the target itself, the accuracy is inevitably worse when speculating the characteristics of the group based on the target selected in this biased manner. In addition, due to the different understanding of the target attributes by different selection subjects, the accuracy of the selection may be poor.

It can be seen from the above two examples that the existing target selection method has a poor effect on selecting a target.

Summary of the invention

Based on this, it is necessary to select a target user's selection method, system and equipment for the problem that the target selection method has poor effect on the existing target selection method.

A method of selecting a target user includes the following steps:

Obtaining a selection instruction sent by the control device, and reading, in response to the selection instruction, attribute information that represents an association relationship between each user and a preset constraint condition;

Selecting a target user from each user according to the attribute information;

Acquiring a unique identifier corresponding to the receiving device of the target user, and sending a notification message to the receiving device of the target user according to the unique identifier; wherein each receiving device is provided with a unique identifier that is distinguished from each other, and each identifier corresponds to a unique user. .

A selection system for target users, including:

a reading device, configured to acquire a selection instruction sent by the control device, and read, in response to the selection instruction, attribute information that represents an association relationship between each user and a preset constraint condition;

a selecting device, configured to select a target user from each user according to the attribute information;

a sending device, configured to acquire a unique identifier corresponding to the receiving device of the target user, and send a notification message to the receiving device of the target user according to the unique identifier; wherein each receiving device is provided with a unique identifier that is distinguished from each other, each The ID corresponds to a unique user.

A selection device for a target user, including:

a control device, a background server, and a receiving device; wherein each receiving device is provided with a unique identifier that is distinguished from each other, and each identifier corresponds to a unique user;

The control device receives the input selection instruction and sends the selection instruction to the background server; wherein the selection instruction carries a constraint condition for selecting the target user;

And the background server reads, according to the selection instruction, attribute information that represents an association relationship between each user and a preset constraint, selects a target user from each user according to the attribute information, and acquires a corresponding device of the target user. Uniquely identifying, and transmitting a notification message to the receiving device of the target user based on the unique identifier.

The method, system and device for selecting the target user can obtain the subjective influence of the selected subject by acquiring the pre-stored user attribute information and selecting the target object from the plurality of candidate objects according to the attribute information, and at the same time, setting the selection condition when selecting, The ability to accurately select the target with the greatest degree of association with the constraint improves the accuracy of the selection.

DRAWINGS

1 is a flow chart of a method for selecting a target user of the present invention;

2 is a schematic structural diagram of a selection system of a target user according to the present invention;

FIG. 3 is a schematic structural diagram of a selection device of a target user according to the present invention.

detailed description

Embodiments of the method, system and device for selecting a target user of the present invention will be described below with reference to the accompanying drawings.

1 is a flow chart of a method of selecting a target user of the present invention. As shown in FIG. 1, the selection method of the target user may include the following steps:

S1: acquiring a selection instruction sent by the control device, and reading, in response to the selection instruction, attribute information that represents an association relationship between each user and a preset constraint condition;

S2, selecting a target user from each user according to the attribute information;

S3: Obtain a unique identifier corresponding to the receiving device of the target user, and send a notification message to the receiving device of the target user according to the unique identifier; wherein each receiving device is provided with a unique identifier that is distinguished from each other, and each identifier corresponds to one Unique user.

In order to facilitate understanding, the following is an example of a teacher in the teaching system selecting a student to answer a question. However, those skilled in the art will appreciate that the invention is not limited to this example.

In step S1, constraints can be set according to actual needs. For example, the constraint may be a constraint related to fairness, even if the average number of times each student answers the question is as equal as possible; it may be a constraint that maximizes or minimizes the value corresponding to a certain feature, for example, making a grade Poor students answer the questions as many times as possible; they can also be other constraints, so I won't go into details here. Taking the fairness constraint as an example, the attribute information of each student associated with the constraint may be pre-stored. The attribute information may be the ranking of each student's class, the number of responses per student, the correct rate of the answer, and the proportion of completed work on time.

In step S2, a probability value selected by each user is calculated according to the attribute information; and a target user is selected from each user according to the probability value. The weights of each of the attribute information may be assigned in advance, and the weights may be set according to the degree of influence of each data. The probability that each user is selected may be calculated according to the attribute information and the preset weight. Each attribute in the attribute information may include a number of the user, a number of times the user history is selected, a history number of the user correctly responding to the selection instruction, and the like, and may also include other attributes. The probability that the i-th user is selected can be calculated as follows:

among them,

Where A _ij is the jth term attribute of the i th user, W _ij is the weight of A _ij , and P _i is the probability that the i th user is selected.

In the above teaching system, the attributes may include the student's ranking, the number of student responses, and the correct answer rate, and may also include the proportion of the student completing the assignment on time. Suppose there are n students, the i-th student has _Ai1 (1≤i≤n), and the i-th student has _Ais2 (1≤i≤n), and the correct answer rate is A _i3 (1) ≤ i ≤ n), the ratio of completion of work on time is A _i4 (1 ≤ i ≤ n). The four items of data are assigned weights W _i1 , W _i2 , W _{i3 ,} and W _{i4 , respectively} .

The maximum probability may be selected from the probabilities; if the number of maximum probabilities is 1, the user corresponding to the maximum probability is set as the selected target; if the number of maximum probabilities is greater than 1, one of the maximum probabilities is randomly selected, and Set the corresponding user as the target user.

For example, assuming that there are a total of two students, the probability that the first student is selected is P1=40%, and the probability that the second student is selected is P2=60%, then the second student can be selected as the target. Suppose there are 3 students, the probability that the first student is selected P1=40%, the probability that the second student and the third student are selected P2=P3=60%, then, from the second student and the third One of the students was randomly selected as the selection target.

In order to make each selection more accurate, the user's attribute information can be updated periodically. For example, attribute information can be updated based on the results (correct or incorrect) of the student's answer to the question. It is also possible to update other attribute information such as rankings, job completions, etc. into the system. An update command may be set as a condition for triggering an update, and the update command may carry update information, which may be sent by the control device. When the update instruction is received, the corresponding attribute information may be updated according to the update instruction.

Corresponding to the selection method of the target user, the present invention further provides a selection system of the target user, as shown in FIG. 2, which may include:

The reading device 110 is configured to acquire a selection instruction sent by the control device, and read, in response to the selection instruction, attribute information that represents an association relationship between each user and a preset constraint condition;

The selecting device 120 is configured to select a target user from each user according to the attribute information;

The sending device 130 is configured to acquire a unique identifier corresponding to the receiving device of the target user, and send a notification message to the receiving device of the target user according to the unique identifier; wherein each receiving device is provided with a unique identifier that is distinguished from each other. The identifier corresponds to a unique user.

The reading device 110 can set constraints according to actual needs. For example, the constraint may be a constraint related to fairness, even if the average number of times each student answers the question is as equal as possible; it may be a constraint that maximizes or minimizes the value corresponding to a certain feature, for example, making a grade Poor students answer the questions as many times as possible; they can also be other constraints, so I won't go into details here. Taking the fairness constraint as an example, the attribute information of each student associated with the constraint may be pre-stored. The attribute information may be the ranking of each student's class, the number of responses per student, the correct rate of the answer, and the proportion of completed work on time.

The selecting means 120 may calculate a probability value selected by each user according to the attribute information; select a target user from among the users according to the probability value. The weights of each of the attribute information may be assigned in advance, and the weights may be set according to the degree of influence of each data. The probability that each user is selected may be calculated according to the attribute information and the preset weight. Each attribute in the attribute information may include a number of the user, a number of times the user history is selected, a history number of the user correctly responding to the selection instruction, and the like, and may also include other attributes. The probability that the i-th user is selected can be calculated as follows:

among them,

The present invention also provides a selection device for the target user, as shown in FIG. 3, which may include:

The control device 210, the background server 220, and the receiving device 230; wherein each receiving device 230 is provided with a unique identifier that is distinguished from each other, and each identifier corresponds to a unique user;

The control device 210 receives the input selection instruction, and sends the selection instruction to the background server 220; wherein the selection instruction carries a constraint condition for selecting a target user;

The background server 220 reads attribute information indicating an association relationship between each user and a preset constraint condition in response to the selection instruction, selects a target user from each user according to the attribute information, and acquires a receiving device 230 of the target user. Corresponding unique identifier, and will notify the notification according to the unique identifier The information is sent to the receiving device 230 of the target user.

The control device and/or the receiving device in the above embodiment may be a wearable device (for example, a smart bracelet or smart glasses), or may be a terminal device (for example, a mobile phone, a tablet computer, a notebook computer, etc.) installed with a corresponding application program. ).

The control device and the receiving device can be connected to the background server through WIFI.

In order to make the selected target more intuitively view the selection result, a plurality of signal indicators may be set, each signal indicator corresponding to each receiving device, and when the receiving device receives the notification message sent by the background server, the corresponding signal The indicator light is on.

In one embodiment, the background server 220 can set constraints based on actual needs. For example, the constraint may be a constraint related to fairness, even if the average number of times each student answers the question is as equal as possible; it may be a constraint that maximizes or minimizes the value corresponding to a certain feature, for example, making a grade Poor students answer the questions as many times as possible; they can also be other constraints, so I won't go into details here. Taking the fairness constraint as an example, the attribute information of each student associated with the constraint may be pre-stored. The attribute information may be the ranking of each student's class, the number of responses per student, the correct rate of the answer, and the proportion of completed work on time.

After receiving the selection instruction sent by the control device 210, the background server 220 may calculate a probability value that each user is selected according to the attribute information; and select a target user from each user according to the probability value. The weights of each of the attribute information may be assigned in advance, and the weights may be set according to the degree of influence of each data. The probability that each user is selected may be calculated according to the attribute information and the preset weight. Each attribute in the attribute information may include a number of the user, a number of times the user history is selected, a history number of the user correctly responding to the selection instruction, and the like, and may also include other attributes. The probability that the i-th user is selected can be calculated as follows:

among them,

The background server 220 may select a maximum probability from the probabilities; if the number of maximum probabilities is 1, the user corresponding to the maximum probability is set as a selected target; if the number of maximum probabilities is greater than 1, randomly select from the maximum probabilities One and set the corresponding user as the target user. The background server 220 can send a notification message to the receiving device 230 of the target user.

In order to make each selection more accurate, the background server 220 can periodically update the attribute information of the user. For example, attribute information can be updated based on the results (correct or incorrect) of the student's answer to the question. It is also possible to update other attribute information such as rankings, job completions, etc. into the system. An update command may be set as a condition for triggering an update, and the update command may carry update information, which may be sent by the control device. When the update instruction is received, the corresponding attribute information may be updated according to the update instruction.

The selection methods, systems and devices of the above target users have the following advantages:

(1) It can reduce the subjective influence of the selected subject, and the choice is more objective.

(2) The selected constraint is set at the time of selection, and the associated process with the constraint can be accurately selected. The greatest goal is to improve the accuracy of the selection.

(3) Integrating the selection method into the wearable device is convenient to operate.

(4) The indicator light is set to facilitate visual observation of the selection result.

The technical features of the above-described embodiments may be arbitrarily combined. For the sake of brevity of description, all possible combinations of the technical features in the above embodiments are not described. However, as long as there is no contradiction between the combinations of these technical features, All should be considered as the scope of this manual.

The above-described embodiments are merely illustrative of several embodiments of the present invention, and the description thereof is more specific and detailed, but is not to be construed as limiting the scope of the invention. It should be noted that a number of variations and modifications may be made by those skilled in the art without departing from the spirit and scope of the invention. Therefore, the scope of the invention should be determined by the appended claims.

Claims

A method for selecting a target user, comprising the steps of:

Obtaining a selection instruction sent by the control device, and reading, in response to the selection instruction, attribute information that represents an association relationship between each user and a preset constraint condition;

Selecting a target user from each user according to the attribute information;

Acquiring a unique identifier corresponding to the receiving device of the target user, and sending a notification message to the receiving device of the target user according to the unique identifier; wherein each receiving device is provided with a unique identifier that is distinguished from each other, and each identifier corresponds to a unique user. .
The method for selecting a target user according to claim 1, wherein the step of selecting a target user from among the users according to the attribute information comprises:

Calculating a probability value that each user is selected according to the attribute information;

A target user is selected from among the users according to the probability value.
The method for selecting a target user according to claim 2, wherein the step of calculating a probability value selected by each user according to the attribute information comprises:

Read the weight value of each attribute of the attribute information;

A probability value selected by each user is calculated according to the respective attributes and the weight value.
The method for selecting a target user according to claim 3, wherein the probability that each user is selected is calculated according to the following manner:

among them,

Where A ij is the jth term attribute of the i th user, W ij is the weight of A ij , and P i is the probability that the i th user is selected.
The method for selecting a target user according to claim 1, further comprising the steps of:

Receiving an update instruction sent by the control device;

The attribute information of the user is updated according to the update instruction.
The method for selecting a target user according to claim 2, wherein the step of selecting a target user from each user according to the probability selection comprises:

Selecting a maximum probability value from the probability values;

If the number of maximum probability values is 1, the user corresponding to the maximum probability value is set as the selected target;

If the number of maximum probability values is greater than 1, randomly select one of the maximum probability values, and set the corresponding user as the target user.
A selection system for a target user, comprising:

a reading device, configured to acquire a selection instruction sent by the control device, and read, in response to the selection instruction, attribute information that represents an association relationship between each user and a preset constraint condition;

a selecting device, configured to select a target user from each user according to the attribute information;

a sending device, configured to acquire a unique identifier corresponding to the receiving device of the target user, and send a notification message to the receiving device of the target user according to the unique identifier; wherein each receiving device is provided with a unique identifier that is distinguished from each other, each The ID corresponds to a unique user.
A selection device for a target user, comprising:

a control device, a background server, and a receiving device; wherein each receiving device is provided with a unique identifier that is distinguished from each other, and each identifier corresponds to a unique user;

The control device receives the input selection instruction and sends the selection instruction to the background server; wherein the selection instruction carries a constraint condition for selecting the target user;

And the background server reads, according to the selection instruction, attribute information that represents an association relationship between each user and a preset constraint, selects a target user from each user according to the attribute information, and acquires a corresponding device of the target user. Uniquely identifying, and transmitting a notification message to the receiving device of the target user based on the unique identifier.
The selection device of the target user according to claim 8, further comprising:

The signal indicator corresponding to each receiving device respectively, when the receiving device receives the notification message sent by the background server, the corresponding signal indicator lights.
The selection device of the target user according to claim 8, wherein the control device and/or the receiving device is a wearable device.