CN108764348B

CN108764348B - Data acquisition method and system based on multiple data sources

Info

Publication number: CN108764348B
Application number: CN201810539389.5A
Authority: CN
Inventors: 王春龙
Original assignee: Koukouxiangchuan Beijing Network Technology Co ltd
Current assignee: Koukouxiangchuan Beijing Network Technology Co ltd
Priority date: 2018-05-30
Filing date: 2018-05-30
Publication date: 2020-07-10
Anticipated expiration: 2038-05-30
Also published as: CN108764348A

Abstract

The invention discloses a data acquisition method and a system based on a plurality of data sources, relating to the field of electronic information, wherein the method comprises the following steps: respectively acquiring a plurality of data characteristic values acquired by a plurality of data sources aiming at the data characteristics of an acquired object in the data acquisition process; dividing a plurality of data characteristic values into at least one group, and determining the grouping score of the group according to the characteristic weight value of a data source corresponding to each group aiming at the acquisition object; and according to the grouping scores of the groups, determining the acquisition result of the data characteristics of the acquisition object in the data acquisition process, and correcting the characteristic weight value of each data source for the acquisition object so as to use the corrected characteristic weight value of each data source for the acquisition object in the next data acquisition process. According to the method, the characteristic weight value of the data source corresponding to each group aiming at the acquisition object and the acquisition result of the data characteristic of the acquisition object in the data acquisition process can be more accurately acquired.

Description

Data acquisition method and system based on multiple data sources

Technical Field

The invention relates to the field of electronic information, in particular to a data acquisition method and a data acquisition system based on a plurality of data sources.

Background

With the development of scientific technology, the multi-sensor information fusion target identification technology is widely applied to the fields of military affairs, computer vision, remote sensing images and the like, and has wide practical application significance. The target identification technology based on feature level fusion can fuse feature information provided by various sensors under various complex and uncertain conditions, reduce data volume bandwidth and improve identification precision and efficiency. Where statistical features are one of the basic concepts of statistics, when studying a population using mathematical statistics, one is concerned with the fact that not the individual individuals that make up the population themselves. The statistical characteristics are divided into a number characteristic and an attribute characteristic, wherein the number characteristic is divided into a metering characteristic and a counting characteristic, and the number characteristic can be directly expressed by numerical values, for example, the size and the size of an element, the height of a wheat strain and the like are all metering characteristics.

Currently, commonly used feature level fusion methods are roughly classified into five categories: a probabilistic statistical method, a logical reasoning method, a neural network method, a fusion method based on feature extraction, and a fusion method based on search. Several algorithms in the probabilistic statistical method are briefly described below. Wherein, (1) weighted average method: assuming that n sensors are provided, after feature extraction is performed by the same method, a weighted average value of a feature value x of a certain dimension is used as a feature value after the dimension is fused, wherein the weight can be regarded as measurement of accuracy of different sensors. (2) Bayes estimation method: bayes (bayesian) estimation method is a method for representing various uncertain information provided by multiple sensors as probabilities and processing the probabilities by using Bayes conditional probability formula in probability theory when the Bayes estimation method is used for information fusion of multiple sensors. Under the condition that the prior probability is known, the Bayes criterion is the optimal fusion criterion, and an accurate fusion result can be given. (3) The Kalman filtering method is an optimized autoregressive data processing method, and the Kalman filtering method is suitable for fusing dynamic low-level redundant sensor information in real time. The method uses the statistical characteristics of the measurement model to recur optimal estimation fusion data under the condition of determining the statistical significance. If the system has a linear dynamic model, and the system noise and the sensor noise are white noise models with Gaussian distribution, the method provides the optimal estimation in the unique solvent meaning for data fusion, and the system processing does not need a large amount of data storage and calculation due to the recursion characteristic of Kalman.

However, the inventor finds out in the process of implementing the invention that: although the weighted average method is simple and intuitive, each sensor must be analyzed in detail in advance to obtain its weight. And the accuracy of each sensor is different in different feature dimensions, so the acquisition of the weight becomes a major difficulty. In addition, regarding the bayesian estimation method, it is difficult for each sensor to obtain the required prior probability in practical application, which greatly limits the application of the bayesian criterion. Regarding the kalman filtering method, there is no strict set of filtering formulas for many nonlinear systems. Therefore, a data acquisition method which is simple and practical and can accurately acquire the characteristic weight values of a plurality of sensors for a certain acquisition object in the data acquisition process and the characteristic values of the acquired plurality of data after the characteristic values are fused is lacked in the prior art.

Disclosure of Invention

In view of the above, the present invention has been developed to provide a method and system for data acquisition based on multiple data sources that overcomes or at least partially solves the above-mentioned problems.

According to one aspect of the invention, a data acquisition method based on a plurality of data sources is provided, which comprises the following steps: respectively acquiring a plurality of data characteristic values acquired by a plurality of data sources aiming at the data characteristics of an acquired object in the data acquisition process; dividing a plurality of data characteristic values into at least one group, and determining the grouping score of the group according to the characteristic weight value of a data source corresponding to each group aiming at the acquisition object; and according to the grouping scores of the groups, determining the acquisition result of the data characteristics of the acquisition object in the data acquisition process, and correcting the characteristic weight value of each data source for the acquisition object so as to use the corrected characteristic weight value of each data source for the acquisition object in the next data acquisition process.

Optionally, the step of dividing the plurality of data characteristic values into at least one group specifically includes:

and clustering the plurality of data characteristic values according to a preset clustering rule, and dividing the plurality of data characteristic values into at least one group according to a clustering result.

Optionally, the step of determining the grouping score of each group according to the characteristic weight value of the data source corresponding to the group for the collection object specifically includes:

and aiming at each group, respectively determining each characteristic weight value of each data source corresponding to the group aiming at the acquisition object, calculating each characteristic weight value of each data source aiming at the acquisition object according to a preset operation rule, and obtaining the group score of the group according to an operation result.

Optionally, the step of correcting the characteristic weight value of each data source for the acquisition object specifically includes:

if the grouping score of the grouping corresponding to the data source is higher than a first preset threshold value, increasing the characteristic weight value of the data source for the acquisition object;

and if the grouping score of the grouping corresponding to the data source is lower than a second preset threshold, reducing the characteristic weight value of the data source for the acquisition object.

Optionally, the step of respectively obtaining a plurality of data characteristic values acquired by a plurality of data sources for the data characteristic of the acquired object in the data acquisition process specifically includes: respectively acquiring a plurality of data characteristic values acquired by a plurality of data sources aiming at the data characteristics of an acquired object in the (n +1) th data acquisition process; wherein n is a positive integer not less than 0;

and the step of determining the grouping score of each group according to the characteristic weight value of the data source corresponding to each group for the collection object specifically comprises: determining grouping scores of the groups according to the characteristic weight values of the data characteristics of the data source corresponding to each group in the nth data acquisition process aiming at the acquisition object;

the step of correcting the characteristic weight value of each data source for the acquisition object specifically includes: determining a characteristic weight value of each data source for the data characteristic of the acquisition object in the (n +1) th data acquisition process according to the following formula;

wn +1 ═ w n + m)/(n + 1); wn +1 is a characteristic weight value of the data characteristic of the acquisition object in the (n +1) th data acquisition process of the data source, Wn is a characteristic weight value of the data characteristic of the acquisition object in the nth data acquisition process of the data source, and the value of m is determined according to the grouping score of the group corresponding to the data source.

Optionally, before the method is executed, the method further includes:

and presetting initial characteristic weight values of the data sources aiming at the acquisition object, and taking the initial characteristic weight values as characteristic weight values of the data sources aiming at the data characteristics of the acquisition object in the 0 th data acquisition process.

Optionally, wherein when the data feature of the acquisition object includes a plurality of dimensions, the feature weight value of each data source for the acquisition object includes: a plurality of feature weight values respectively corresponding to different dimensions of the acquisition object;

the step of respectively obtaining a plurality of data characteristic values acquired by a plurality of data sources for the data characteristic of the acquired object in the data acquisition process specifically includes: respectively acquiring a plurality of data characteristic values acquired by a plurality of data sources in the data acquisition process aiming at the data characteristics of the preset dimensionality of the acquired object;

the step of determining the grouping score of each group according to the characteristic weight value of the data source corresponding to each group for the collection object specifically includes: determining the grouping scores of the groups according to the characteristic weight values of the data source corresponding to each group aiming at the preset dimensionality of the acquisition object;

the step of determining the acquisition result of the data characteristic of the acquisition object in the data acquisition process, and correcting the characteristic weight value of each data source for the acquisition object specifically includes:

and determining the acquisition result of the data characteristics of the preset dimensionality of the acquisition object in the data acquisition process, and correcting the characteristic weight value of each data source aiming at the preset dimensionality of the acquisition object.

Optionally, wherein the acquiring the object comprises: temperature, humidity, heartbeat, and/or entity; the data source includes: a camera sensor, and/or a voice control sensor.

According to another aspect of the present invention, there is provided a data acquisition method based on a plurality of data sources, comprising: respectively acquiring a plurality of store characteristic values acquired by a plurality of data sources aiming at store characteristics of stores in the data acquisition process;

dividing the plurality of store characteristic values into at least one group, and determining the grouping score of the group according to the characteristic weight value of the data source corresponding to each group for the store;

according to the grouping scores of the groups, determining the collection results of store characteristics of the stores in the data collection process, and correcting the characteristic weight values of the data sources for the stores so as to use the corrected characteristic weight values of the data sources for the stores in the next data collection process.

Optionally, the step of dividing the store characteristic values into at least one group specifically includes:

and clustering the characteristic values of the plurality of stores according to a preset clustering rule, and dividing the characteristic values of the plurality of stores into at least one group according to a clustering result.

Optionally, the step of determining the grouping score of each group according to the characteristic weight value of the data source corresponding to the group for the store specifically includes:

and respectively determining each characteristic weight value of each data source corresponding to each group aiming at the store for each group, calculating each characteristic weight value of each data source aiming at the store according to a preset calculation rule, and obtaining the grouping score of the group according to the calculation result.

Optionally, the step of modifying the characteristic weight values of the data sources for the stores specifically includes:

if the grouping score of the grouping corresponding to the data source is higher than a first preset threshold value, increasing the characteristic weight value of the data source for the store;

and if the grouping score of the group corresponding to the data source is lower than a second preset threshold, reducing the characteristic weight value of the data source for the store.

Optionally, the step of respectively acquiring a plurality of store characteristic value acquisition target store characteristic store characteristics acquired by a plurality of data sources for store characteristics of stores in the data acquisition process specifically includes: respectively acquiring a plurality of store characteristic values acquired by a plurality of data sources aiming at store characteristics of stores in the (n +1) th data acquisition process; wherein n is a positive integer not less than 0;

and the step of determining the grouping score of each group according to the characteristic weight value of the data source corresponding to the group for the store specifically comprises: determining grouping scores of the groups according to the characteristic weight values of the store characteristics of the stores in the nth data acquisition process of the data source corresponding to each group;

the step of correcting the characteristic weight values of the data sources for the stores specifically includes: determining a characteristic weight value of each data source for store characteristics of the store in the (n +1) th data acquisition process according to the following formula;

wn +1 ═ w n + m)/(n + 1); wn +1 is a characteristic weight value of the data source for store characteristics of the stores in the n +1 th data acquisition process, Wn is a characteristic weight value of the data source for the store characteristics of the stores in the n th data acquisition process, and the value of m is determined according to the grouping score of the group corresponding to the data source.

Optionally, when the store characteristics of the store include multiple dimensions, the step of respectively obtaining multiple store characteristic values acquired by multiple data sources for the store characteristics of the store in the data acquisition process specifically includes: respectively acquiring a plurality of store characteristic values acquired by a plurality of data sources aiming at store characteristics of an acquisition object of a store in the data acquisition process;

the step of determining the grouping score of each group according to the characteristic weight value of the data source corresponding to the group for the store specifically includes: determining a grouping score of each group according to the characteristic weight value of the data source corresponding to the group for the dimension in the store;

the step of determining the acquisition result of the store characteristics of the store in the data acquisition process, and correcting the characteristic weight values of the stores for each data source specifically includes:

and determining the acquisition result of the store characteristics of the dimension in the store in the data acquisition process, and correcting the characteristic weight value of each data source for the dimension in the store.

Optionally, wherein the store characteristics of the store comprise at least one dimension of: store type dimension, merchandise dimension in store, and/or electronic ticket dimension;

the data source includes: a merchant-provided data source, a user-provided data source, and an APP-provided data source.

According to another aspect of the present invention, there is provided a data acquisition system based on a plurality of data sources, comprising: the first acquisition module is suitable for respectively acquiring a plurality of data characteristic values acquired by a plurality of data sources aiming at the data characteristics of an acquired object in the data acquisition process;

the first determining module is suitable for dividing the plurality of data characteristic values into at least one group, and determining the grouping score of the group according to the characteristic weight value of the data source corresponding to each group aiming at the acquisition object;

and the first correcting module is suitable for determining the acquisition result of the data characteristics of the acquisition object in the data acquisition process according to the grouping scores of all the groups, and correcting the characteristic weight value of each data source aiming at the acquisition object so as to use the corrected characteristic weight value of each data source aiming at the acquisition object in the next data acquisition process.

Optionally, the first determining module is specifically adapted to:

Optionally, the first modification module is specifically adapted to:

Optionally, the first obtaining module is specifically adapted to: respectively acquiring a plurality of data characteristic values acquired by a plurality of data sources aiming at the data characteristics of an acquired object in the (n +1) th data acquisition process; wherein n is a positive integer not less than 0;

and the first determination module is specifically adapted to: determining grouping scores of the groups according to the characteristic weight values of the data characteristics of the data source corresponding to each group in the nth data acquisition process aiming at the acquisition object;

the first correction module is specifically adapted to: determining a characteristic weight value of each data source for the data characteristic of the acquisition object in the (n +1) th data acquisition process according to the following formula;

wn +1 ═ w n + m)/(n + 1); wn +1 is a characteristic weight value of the data source for the data characteristics of the acquisition object in the (n +1) th data acquisition process, Wn is a characteristic weight value of the data source for the data characteristics of the acquisition object in the n-th data acquisition process, and the value of m is determined according to the grouping score of the group corresponding to the data source.

Optionally, wherein the apparatus further comprises a setting module adapted to:

the first obtaining module is specifically adapted to: respectively acquiring a plurality of data characteristic values acquired by a plurality of data sources in the data acquisition process aiming at the data characteristics of the preset dimensionality of the acquired object;

the first determination module is specifically adapted to: determining the grouping scores of the groups according to the characteristic weight values of the data source corresponding to each group aiming at the preset dimensionality of the acquisition object;

the first correction module is specifically adapted to:

According to another aspect of the present invention, there is provided a data acquisition system based on a plurality of data sources, comprising:

the second acquisition module is suitable for respectively acquiring a plurality of store characteristic values acquired by a plurality of data sources aiming at store characteristics of stores in the data acquisition process;

the second determining module is suitable for dividing the plurality of store characteristic values into at least one group, and determining the grouping score of the group according to the characteristic weight value of the data source corresponding to each group for the store;

and the second correcting module is suitable for determining the acquisition result of the store characteristics of the store in the data acquisition process according to the grouping scores of the groups, and correcting the characteristic weight value of each data source for the store so as to use the corrected characteristic weight value of each data source for the store in the next data acquisition process.

Optionally, the second determining module is specifically adapted to:

Optionally, the second modification module is specifically adapted to:

Optionally, the second obtaining module is specifically adapted to: respectively acquiring a plurality of store characteristic values acquired by a plurality of data sources aiming at store characteristics of stores in the (n +1) th data acquisition process; wherein n is a positive integer not less than 0;

and the second determination module is specifically adapted to: determining grouping scores of the groups according to the characteristic weight values of the store characteristics of the stores in the nth data acquisition process of the data source corresponding to each group;

the second correction module is specifically adapted to: determining a characteristic weight value of each data source for store characteristics of the store in the (n +1) th data acquisition process according to the following formula;

Optionally, when the store characteristics of the store comprise a plurality of dimensions, the second obtaining module is specifically adapted to: respectively acquiring a plurality of store characteristic values acquired by a plurality of data sources aiming at store characteristics of an acquisition object of a store in the data acquisition process;

the second determination module is specifically adapted to: determining a grouping score of each group according to the characteristic weight value of the data source corresponding to the group for the dimension in the store;

the second correction module is specifically adapted to:

In accordance with still another aspect of the present invention, there is provided an electronic apparatus including: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;

the memory is used for storing at least one executable instruction, and the executable instruction enables the processor to execute the operation corresponding to the data acquisition method based on the plurality of data sources.

According to still another aspect of the present invention, there is provided another electronic device including: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;

According to still another aspect of the present invention, a computer storage medium is provided, where at least one executable instruction is stored in the storage medium, and the executable instruction causes a processor to perform operations corresponding to the data acquisition method based on multiple data sources as described above.

According to yet another aspect of the present invention, another computer storage medium is provided, where at least one executable instruction is stored in the storage medium, and the executable instruction causes a processor to perform operations corresponding to the data acquisition method based on multiple data sources as described above.

According to the data acquisition method and system based on a plurality of data sources provided by the invention, by acquiring a plurality of data characteristic values acquired by the plurality of data sources aiming at the data characteristics of an acquisition object in the data acquisition process, dividing a plurality of data characteristic values into at least one group according to a clustering rule, determining the grouping score of the group according to the characteristic weight value of a data source corresponding to each group for an acquisition object, thereby mutually associating the characteristic weight value of the data source corresponding to each group aiming at the acquisition object with the group score of the group, finally determining the acquisition result of the data characteristic of the acquisition object in the data acquisition process according to the group score of each group, correcting the characteristic weight value of each data source aiming at the acquisition object, so as to use the corrected characteristic weight value of each data source for the acquisition object in the next data acquisition process. According to the method, the characteristic weight value of the data source corresponding to each group can be iterated continuously aiming at the acquired object, so that the characteristic weight value can be acquired more accurately, the final data acquisition result can be determined according to a voting mechanism, and the acquisition result of the data characteristic of the acquired object in the data acquisition process can be determined more accurately according to the accurate characteristic weight value instead of a method of simply calculating an average value.

The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.

Drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:

fig. 1 is a flowchart illustrating a data collection method based on multiple data sources according to an embodiment of the present invention;

FIG. 2 is a flow chart of a data collection method based on multiple data sources according to an embodiment of the present invention;

FIG. 3 is a block diagram of another flow diagram of a method for data collection based on multiple data sources according to an embodiment of the present invention;

FIG. 4 is a flow chart of a data collection method based on multiple data sources according to a second embodiment of the present invention;

FIG. 5 is a block diagram of a data acquisition system based on multiple data sources according to a third embodiment of the present invention;

FIG. 6 is a block diagram of another data acquisition system based on multiple data sources according to a fourth embodiment of the present invention;

fig. 7 is a schematic structural diagram of an electronic device according to a fifth embodiment of the present invention;

fig. 8 is a schematic structural diagram of another electronic device according to a sixth embodiment of the present invention.

Detailed Description

Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

Example one

Fig. 1 shows a flowchart of a data acquisition method based on multiple data sources according to an embodiment of the present invention. As shown in fig. 1, the method includes:

step S110: the method comprises the steps of presetting initial characteristic weight values of all data sources aiming at a collection object, and taking the initial characteristic weight values as characteristic weight values of the data sources aiming at the data characteristics of the collection object in the 0 th data collection process.

The initial feature weight value may be set to an equal value, for example, to a value of 0.5, 1, 2, or to another specific value. In addition to the above manner, the initial characteristic weight value may be flexibly set according to the parameter value and the sensitivity of each data source, and a person skilled in the art may flexibly select the initial characteristic weight value, which is not limited herein.

This step is an optional step, and in other embodiments, this step may be omitted. For example, this step may be omitted when the respective data sources themselves already have the initial characteristic weight values.

Step S120: respectively acquiring a plurality of data characteristic values acquired by a plurality of data sources aiming at the data characteristics of the acquired object in the data acquisition process.

Wherein the data source includes but is not limited to at least one of the following: a camera sensor, and/or a voice control sensor. The sensor is a detection device which can sense the measured information and convert the sensed information into an electric signal or other required information output forms according to a certain rule so as to meet the requirements of information transmission, processing, storage, display, recording, control and the like. The sensor features include: miniaturization, digitalization, intellectualization, multifunction, systematization and networking. The method is the first link for realizing automatic detection and automatic control. Wherein, the above-mentioned acquisition object includes but is not limited to at least one of the following: temperature, humidity, heartbeat, and/or entity. For example, when the acquisition object is a commodity in an entity, for a certain characteristic dimension of the commodity, for example, for a price dimension, a plurality of price values acquired by a plurality of data sources for the price characteristic of the commodity in the acquisition process may be acquired respectively. In order to more clearly and fully illustrate the technical solution of the present invention, fig. 2 shows a flowchart of a data acquisition method based on multiple data sources according to an embodiment of the present invention. As shown in fig. 2, assuming that the plurality of data sources are a plurality of sensors, i, j, and k, respectively, the characteristic values of the data acquired by the three sensors can be acquired for the data characteristic of a certain acquisition object.

Optionally, when the data feature of the acquisition object includes multiple dimensions, multiple data feature values acquired by multiple data sources for the data feature of the preset dimension of the acquisition object in the data acquisition process may be acquired respectively. The preset dimension may be any one of the plurality of dimensions. As shown in fig. 2, for example, the data feature of the acquired object includes 4 dimensions, that is, feature 1, feature 2, feature 3, and feature 4, a plurality of data feature values acquired by a plurality of data sources in the data acquisition process for the data feature of any preset dimension of the 4 dimensions of the acquired object may be acquired respectively. For another example, for the data feature of the product, when the data feature of the product includes multiple dimensions such as price, weight, and usage time, in this step, multiple data feature values acquired by multiple data sources for the data feature of the dimension of the acquisition object in the data acquisition process may be acquired for the data feature of any dimension.

Step S130: dividing the plurality of data characteristic values into at least one group, and determining the grouping score of the group according to the characteristic weight value of the data source corresponding to each group aiming at the acquisition object.

Specifically, when grouping the plurality of data feature values, the plurality of data feature values may be clustered according to a preset clustering rule, and then the plurality of data feature values may be divided into at least one group according to a clustering result. The clustering rule may be, for example, a numerical range-based clustering rule, a word count-based clustering rule, or a category-based clustering rule. For example, the data feature values with the same data range may be divided into the same group, or the data feature values with the same number of words may be divided into the same group, or the data feature values with the same kind and the same kind may be divided into a group. Fig. 3 is a flow chart of another data collection method based on multiple data sources according to an embodiment of the present invention. As shown in fig. 3, the characteristic values of data acquired by the sensors i and j for the data characteristic of the acquired object in the data acquisition process are abc, and the characteristic value of data acquired by the sensor k is abd, so that the two characteristic values of data can be divided into one group, and the characteristic value of data acquired by the sensor k is divided into another group. As shown in fig. 2 and 3, the grouping operation of the data feature values may be performed by each of the feature fuses.

The grouping score of each group may be in a positive correlation with the characteristic weight value of the data source corresponding to each group for the acquisition object, that is, the higher the characteristic weight value of the data source corresponding to the group for the acquisition object is, the higher the score of the group is. Specifically, when the grouping score of each group is determined according to the feature weight value of the data source corresponding to each group for the acquisition object for the first time, the grouping score of each group may be determined according to the initial feature weight value, and then the grouping score of each group may be determined according to the feature weight value corrected last time when the grouping score is calculated each time, where a specific manner of correcting the feature weight value of each data source for the acquisition object will be described in detail in step S140 below, and details thereof are not repeated. Specifically, when the grouping score is calculated, for each group, each characteristic weight value of each data source corresponding to the group for the collection object may be determined, and then each characteristic weight value of each data source for the collection object is calculated according to a preset calculation rule, and the grouping score of the group is obtained according to a calculation result. The operation rule may be an addition rule, an averaging operation rule, a linear regression calculation rule, or the like, and specifically, the operation rule may be determined according to a clustering manner in the clustering rule, or may be determined according to a specific service scenario, which may be flexibly selected by a person skilled in the art, and the embodiment is not limited herein.

Optionally, when the data feature of the acquisition object includes a plurality of dimensions, the feature weight value of each data source for the acquisition object includes: a plurality of feature weight values respectively corresponding to different dimensions of the acquisition object. For example, as shown in fig. 2, when the data feature of the acquisition object includes 4 dimensions, for a sensor i, the feature weight values for the acquisition object include feature weight values corresponding to 4 different dimensions of the acquisition object, that is, the feature weight values for feature 1, feature 2, feature 3, and feature 4 are: w_(i,1)、W_(i,2)、W_(i,3)、W_(i,4)For the feature weight values of the other sensors in fig. 2 respectively corresponding to different dimensions of the acquisition object, reference may be made to the contents shown in fig. 2, which is not described herein again. Therefore, when the data characteristics of the collection object include a plurality of dimensions, the grouping score of each group can be determined according to the characteristic weight value of the data source corresponding to the group for the preset dimension of the collection object. The predetermined dimension may be any one of the above-mentioned dimensions. In the process of acquiring data by each data source, the sensitivity and the accuracy of the acquired data of the data sources with different dimensions are correspondingly changed aiming at the data characteristics with different dimensions, so that when the data characteristics of the acquired object comprise a plurality of dimensions, the accuracy of determining the score can be improved by adopting a mode of determining the grouped score of each data source corresponding to each group aiming at the characteristic weight value of the preset dimension of the acquired object according to the data source corresponding to each group, and a more accurate data acquisition result is acquired.

By implementing the step, the characteristic weight value of the data source corresponding to each group for the acquisition object and the grouping score of the group can be correlated, so that the acquisition result of the data characteristic of the acquisition object in the data acquisition process can be determined according to the characteristic weight value of the data source corresponding to each group for the acquisition object.

Step S140: and according to the grouping scores of the groups, determining the acquisition result of the data characteristics of the acquisition object in the data acquisition process, and correcting the characteristic weight value of each data source for the acquisition object so as to use the corrected characteristic weight value of each data source for the acquisition object in the next data acquisition process.

Optionally, when the characteristic weight value of each data source for the acquisition object includes: a plurality of feature weight values respectively corresponding to different dimensions of the acquisition object; in this step, the acquisition result of the data characteristic of the preset dimension of the acquisition object in the data acquisition process may be determined, and the characteristic weight value of each data source for the preset dimension of the acquisition object may be corrected.

Specifically, for example, in a voting event, when there are a plurality of candidate objects, according to the voting mechanism, since the object with the highest number of acquired votes has the highest credibility, the object with the highest number of acquired votes is usually selected as the selected object. Similarly, in each obtained group, for the group corresponding to the characteristic weight value with a larger value, the reliability of the data characteristic value acquired by each corresponding data source for the data characteristic of the acquisition object is higher, so that the data characteristic value acquired by the data source corresponding to the group for the data characteristic of the acquisition object can be selected as the acquisition result of the data characteristic of the acquisition object in the data acquisition process. According to the principle, the data characteristic value of the data source corresponding to the group with the highest obtained group score for the data characteristic of the acquisition object can be selected in the step to serve as the acquisition result of the data characteristic of the acquisition object in the data acquisition process. As shown in fig. 3, for the feature s, since the grouping score of the data feature value group acquired by the sensor i and the sensor j for the data feature of the acquisition object is greater than the grouping score of the data feature value group acquired by the sensor k for the data feature of the acquisition object, the data feature value abc can be determined as the acquisition result of the data feature of the acquisition object in the data acquisition process of this time.

Further, when the characteristic weight value of each data source for the acquisition object is corrected, if the grouping score of the group corresponding to the data source is higher than a first preset threshold, which indicates that the accuracy of the data characteristic value acquired for the data characteristic of the acquisition object is high in the data acquisition process of the data source corresponding to the group, the characteristic weight value of the data source for the acquisition object is increased. Correspondingly, if the grouping score of the group corresponding to the data source is lower than the second preset threshold, which indicates that the accuracy of the data characteristic value acquired by the data source corresponding to the group for the data characteristic of the acquired object is low in the data acquisition process of the data source corresponding to the group, the characteristic weight value of the data source for the acquired object is reduced, and the characteristic weight value of each data source for the acquired object can be corrected by increasing or reducing the characteristic weight value of the data source for the acquired object. The first preset threshold and the second preset threshold may be the same or different, and those skilled in the art may specifically set the threshold according to a specific service condition.

Specifically, in the above process of completing the correction of the characteristic weight value of each data source for the collection object by increasing or decreasing the characteristic weight value of the data source for the collection object, the characteristic weight value of each data source for the collection object may be corrected more accurately according to a specific formula, so that the characteristic weight value of each data source for the collection object is iterated continuously to determine the grouping score of each group according to the last corrected characteristic weight value of the data source corresponding to each group for the collection object in each data collection process. The above formula will be explained in detail below: it is assumed that in step S120, a plurality of data feature values acquired by a plurality of data sources for the data feature of the acquisition object in the (n +1) th data acquisition process are respectively acquired; wherein n is a positive integer not less than 0; then in step S130, the number corresponding to each packet may be respectively determinedDetermining the grouping score of the group according to the characteristic weight value of the data characteristic of the acquisition object in the nth data acquisition process of the data source; then, when the characteristic weight value of each data source for the acquisition object is corrected, the following steps may be performed: according to the formula W_n+1＝(W_n+ m)/(n +1) to determine the characteristic weight value of each data source for the data characteristic of the acquired object in the (n +1) th data acquisition process; wherein, W_n+1A characteristic weight value W of the data source for the data characteristic of the acquisition object in the (n +1) th data acquisition process_nAnd determining the value of m for the characteristic weight value of the data source for the data characteristic of the acquired object in the nth data acquisition process according to the grouping score of the group corresponding to the data source. Specifically, m may be a positive number, a negative number, 0, or the like, the size of the specific numerical value may be determined according to a comparison result between the grouping score corresponding to the data source and a first preset threshold and a second preset threshold, if the grouping score is higher than the first preset threshold, m may be set to be a positive value (for example +1), and the value m may be set to be a value proportional to a difference between the grouping score and the first preset threshold; if the grouping score is lower than the second preset threshold, m may be set to a negative value or the like (e.g., 0 or-1), and likewise, the absolute value of m may be set to a value proportional to the difference between the grouping score and the second preset threshold. According to the above formula W_n+1＝(W_n+ m)/(n +1), the feature weight values of the data features of the acquisition object in the (n +1) th data acquisition process of each data source can be determined, and therefore correction of the feature weight values of the data features of the acquisition object in the n-th data acquisition process of each data source is completed. As shown in fig. 3, for the feature s, the operation process of correcting the feature weight value of each data source for the acquisition object according to the above formula may be completed by the data source feature weight calculator. For example, for the data source i, the characteristic weight value for the acquisition object in the data acquisition process may be represented by the formula W'_(i,1)＝(W_(i,1)+ m)/(n +1) with W'_(i,1)The corrected data source i in the data acquisition process (i.e. the (n +1) th time) is the characteristic weight value, W, of the characteristic 1_(i,1)And the characteristic weight value of the data source i corrected in the last data acquisition process for the characteristic 1 is obtained. The characteristic weight values for the acquisition object in the data acquisition process for other data sources j and k may also be corrected according to the formula in fig. 3, which is not described herein again.

According to the above formula W_n+1＝(W_n+ m)/(n +1), after data acquisition of each data source is completed, the weight of each data source for the data characteristic of the acquired object can be dynamically changed, and the data characteristic value of the data source for the acquired object is iterated continuously, so that the weight value approaches to the theoretical weight value infinitely, and the data acquisition result of the data source for the data characteristic of the acquired object at the next time is more accurate.

According to the data acquisition method based on multiple data sources provided by this embodiment, initial feature weight values of each data source for an acquisition object are preset, then multiple data feature values acquired by the multiple data sources for the data features of the acquisition object in the data acquisition process are obtained, the multiple data feature values are divided into at least one group according to a clustering rule, a grouping score of each group is determined for the group according to the feature weight value of the data source corresponding to each group for the acquisition object, so that the feature weight value of the data source corresponding to each group for the acquisition object and the grouping score of the group are associated with each other, an acquisition result of the data features of the acquisition object in the data acquisition process is determined according to the grouping score of each group, and the feature weight value of each data source for the acquisition object is corrected, so as to use the corrected characteristic weight value of each data source for the acquisition object in the next data acquisition process. According to the method, the characteristic weight value of the data source corresponding to each group can be iterated continuously aiming at the acquired object, so that the characteristic weight value can be acquired more accurately, the final data acquisition result can be determined according to a voting mechanism, and the acquisition result of the data characteristic of the acquired object in the data acquisition process can be determined more accurately according to the accurate characteristic weight value instead of a method of simply calculating an average value.

Example two

Fig. 4 shows a flowchart of a data acquisition method based on multiple data sources according to a second embodiment of the present invention. As shown in fig. 4, the method includes:

step S410, a plurality of store characteristic values acquired by a plurality of data sources for store characteristics of stores in the data acquisition process are respectively acquired.

Wherein the data source includes but is not limited to at least one of the following: a merchant-provided data source, a user-provided data source, and an APP-provided data source. The data source provided by the merchant may be store information filled by the merchant, the data source provided by the user may be store information filled by the user from the client, and the data source provided by the APP may be store information filled by waiter APP according to the store of the client. Additionally, store characteristics of the store include, but are not limited to, at least one of the following dimensions: store type dimension, merchandise dimension in the store, and/or electronic ticket dimension. For example, for store type dimensions, a plurality of store characteristic values acquired by a plurality of data sources for store characteristics of stores in the data acquisition process may be acquired, for example, the data sources may be restaurant stores, clothing stores, furniture stores, and the like.

Further, when the store characteristics of the store include a plurality of dimensions, in this step, a plurality of store characteristic values acquired by a plurality of data sources for the store characteristics of the collection object of the store in the data collection process may be acquired respectively. The collected object may be store features of any dimension. For example, for store type characteristics including a plurality of dimensions such as store names, store addresses, store longitudes and latitudes, a plurality of store characteristic values acquired by a plurality of data sources for the store characteristics of any dimension in the data acquisition process may be acquired respectively.

Step S420, dividing the plurality of store characteristic values into at least one group, and determining a grouping score of the group according to the characteristic weight value of the data source corresponding to each group for the store.

When the stores are clustered, the store characteristic values can be clustered according to a preset clustering rule, and the store characteristic values are divided into at least one group according to a clustering result. The clustering rule may be, for example, a numerical range-based clustering rule, a word number-based clustering rule, or a category-based clustering rule. For example, for name characteristics of a store, in the data acquisition process, a data source provided by a merchant is referred to as a data source 1, and the acquired characteristic value is braised chicken; the data source provided by the user, referred to as data source 2 for short, is the braised chicken with little yellow color; the data source provided by APP is referred to herein as data source 3, and the characteristic value obtained by APP is braised chicken. As the characteristic values obtained by the data source 1 and the data source 3 are all braised chicken, the characteristic values 'braised chicken' obtained by the data source 1 and the data source 3 can be divided into one group according to the clustering rule, and the characteristic value 'braised chicken' obtained by the data source 2 is divided into another group. For another example, for the address characteristics of the store, in the data acquisition process, the characteristic value acquired by the data source 1 is "western lake region in hangzhou city", the characteristic value acquired by the data source 2 is "western lake region college road in hangzhou city", the characteristic value acquired by the data source 3 is also "western lake region college road in hangzhou city", the characteristic values "western lake region college road in hangzhou city" acquired by the data source 2 and the data 3 may be divided into one group according to the clustering rule, and the characteristic value "western lake region in hangzhou city" acquired by the data source 1 is divided into another group. As for other store characteristics, the plurality of store characteristic values may be divided into at least one group according to the clustering rule, and will not be described in detail here.

After dividing a plurality of store characteristic values into at least one group, determining the grouping score of the group according to the characteristic weight value of the data source corresponding to each group for the store. The grouping score of each group may be in a positive correlation with the characteristic weight value of the data source corresponding to each group for the store, that is, the higher the characteristic weight value of the data source corresponding to the group for the store is, the higher the score of the group is. Specifically, when the grouping score of each group is determined according to the feature weight value of the data source corresponding to each group for the store feature for the first time, the grouping score of each group may be determined according to the initial feature weight value, which may be set artificially, and then the grouping score may be determined according to the feature weight value corrected for the last time when the grouping score is calculated each time, where a specific manner of correcting the feature weight value of each data source for the acquisition object will be described in detail in step S230 below, and will not be described again. Specifically, when calculating the grouping score, for each group, each feature weight value of each data source corresponding to the group for the store feature may be determined, and then each feature weight value of each data source for the store feature may be calculated according to a preset calculation rule, so as to obtain the grouping score of the group according to the calculation result. The operation rule may be an addition rule, an averaging operation rule, a linear regression calculation rule, or the like, and specifically, the operation rule may be determined according to a clustering manner in the clustering rule, or may be determined according to a specific service scenario in a store, which may be flexibly selected by a person skilled in the art, and the embodiment is not limited herein.

Optionally, when the store characteristics of the store include multiple dimensions, in the process of acquiring data by each data source, for the data characteristics of different dimensions, sensitivity and accuracy of the acquired data may change correspondingly, so that the grouping score of each group may be determined according to the characteristic weight value of the data source corresponding to each group for the dimension in the store, thereby improving accuracy of determining the score, and further obtaining a more accurate acquisition result of the store characteristics of the store in the data acquisition process. For example, when the store characteristics include a plurality of dimensions such as a store name, a store address, a store longitude and latitude, the grouping scores of the groups may be determined according to the characteristic weight values of the data source corresponding to each group for the three dimensions in the store, and the grouping score determining processes of the groups may be performed independently and without interfering with each other according to the data values of the data source corresponding to each group for each dimension in the store.

And step S430, determining the collection result of the store characteristics of the store in the data collection process according to the grouping scores of the groups, and correcting the characteristic weight value of each data source for the store so as to use the corrected characteristic weight value of each data source for the store in the next data collection process.

When the store characteristics of the store comprise a plurality of dimensions, the acquisition result of the store characteristics of the dimension in the store in the data acquisition process can be determined, and the characteristic weight value of each data source for the dimension in the store is corrected, so that the correction accuracy is improved.

Specifically, in the data acquisition process of this time, since the reliability of the store characteristic value of the store acquired by each group increases as the group score increases, according to the above principle, the acquisition result of the store characteristic of the store in the data acquisition process of this time can be determined from the store characteristic values acquired for the store characteristic values of the stores in the data acquisition process of this time by the data sources corresponding to the group with the highest group score. For example, if the score of the group of the characteristic value "braised chicken" obtained by the data source 1 and the data source 3 is higher than the score of the group of the characteristic value "small braised chicken" obtained by the data source 2, the acquisition result of the name characteristic of the store in the data acquisition process can be determined to be "braised chicken".

After the acquisition result of the store characteristics of the store in the data acquisition process is determined, the characteristic weight value of each data source for the store is corrected, so that the corrected characteristic weight value of each data source for the store is used in the next data acquisition process. Specifically, if the grouping score of the group corresponding to the data source is higher than a first preset threshold, increasing the characteristic weight value of the data source for the store; and if the grouping score of the group corresponding to the data source is lower than a second preset threshold, reducing the characteristic weight value of the data source for the store. The first preset threshold and the second preset threshold may be set to be equal values or unequal values, and the specific values may be flexibly set by those skilled in the art according to actual service conditions.

Specifically, when the characteristic weight value of each data source for the store is increased or decreased, so that the characteristic weight value of each data source for the store can be corrected, the characteristic weight value of each data source for the store can be corrected more accurately according to a specific formula, so that the characteristic weight value of each data source for the store is iterated continuously, and a grouping score of each group can be determined according to the last corrected characteristic weight value of the data source corresponding to each group for the store in each data acquisition process. Next, the above formula will be described in detail, assuming that in step S210, a plurality of data characteristic values acquired by a plurality of data sources for the data characteristics of the store in the n +1 th data acquisition process are respectively acquired; wherein n is a positive integer not less than 0; in step S220, a grouping score of each group may be determined according to a characteristic weight value of the data source corresponding to the group for the data characteristics of the store in the nth data collection process; the above correction of the characteristic weight value of each data source for the store can be performed according to the following formula W_n+1＝(W_n+ m)/(n +1) determining the characteristic weight value of each data source for the store in the (n +1) th data acquisition process; wherein, W_n+1A characteristic weight value, W, for the data source in the (n +1) th data acquisition process aiming at the store_nFor the characteristic weight value of the data source for the store in the nth data acquisition process, a value of m may be determined according to a grouping score of a group corresponding to the data source, specifically, m may be a positive number, a negative number, 0, and the like, a size of a specific value may be determined according to a comparison result between the grouping score corresponding to the data source and a first preset threshold and a second preset threshold, if the grouping score is higher than the first preset threshold, m may be set to be a positive value (for example +1), and the value of m may be set to be a value proportional to a difference between the grouping score and the first preset threshold; if the grouping score is lower than a second preset threshold, m may be set to a negative valueAnd an equal value (e.g., 0 or-1), and likewise, the absolute value of m may be set to a value proportional to the difference between the grouping score and the second preset threshold. According to the above formula W_n+1＝(W_n+ m)/(n +1), the characteristic weight value of each data source for the store in the (n +1) th data acquisition process can be determined, and therefore the correction of the characteristic weight value of each data source for the store in the nth data acquisition process is completed. According to the formula, after data acquisition of the data source is completed every time, the weight value of the data source for the store can be dynamically changed, and the data characteristic value of the data source for the store is continuously iterated, so that the weight value approaches to the theoretical weight value infinitely, and the data acquisition result of the data source for the data characteristic of the store next time is more accurate.

According to the data acquisition method based on multiple data sources provided by this embodiment, multiple store characteristic values acquired by multiple data sources for store characteristics of stores in the data acquisition process are respectively acquired, the multiple store characteristic values are divided into at least one group, and the group score of the group is respectively determined according to the characteristic weight value of the data source corresponding to each group for the store, so that the acquisition result of the store characteristics of the stores in the data acquisition process is determined according to the group score of each group, and the characteristic weight value of each data source for the stores is corrected, so that the corrected characteristic weight value of each data source for the stores in the data acquisition process of the next time is used. According to the method, the data sources corresponding to the groups can be iterated according to the characteristic weighted values of the stores, so that more accurate characteristic weighted values are obtained, the final data acquisition result is determined according to a voting mechanism, and an average value is not simply calculated, so that the acquisition result of the store characteristics of the stores in the data acquisition process can be more accurately determined according to the accurate characteristic weighted values.

EXAMPLE III

Fig. 5 is a structural diagram of a data acquisition system based on multiple data sources according to a third embodiment of the present invention, where the system includes:

the first obtaining module 52 is adapted to obtain a plurality of data characteristic values, which are acquired by a plurality of data sources for the data characteristic of the acquired object in the data acquisition process;

the first determining module 53 is adapted to divide the plurality of data feature values into at least one group, and determine a grouping score of the group according to a feature weight value of a data source corresponding to each group for the acquisition object;

the first correcting module 54 is adapted to determine, according to the grouping score of each group, an acquisition result of the data feature of the acquisition object in the data acquisition process, and correct the feature weight value of each data source for the acquisition object, so as to use the corrected feature weight value of each data source for the acquisition object in the next data acquisition process.

Optionally, wherein the first determining module 53 is specifically adapted to:

Optionally, wherein the first modification module 54 is specifically adapted to:

Optionally, wherein the first obtaining module 52 is specifically adapted to: respectively acquiring a plurality of data characteristic values acquired by a plurality of data sources aiming at the data characteristics of an acquired object in the (n +1) th data acquisition process; wherein n is a positive integer not less than 0;

and said first determination module 53 is specifically adapted to: determining grouping scores of the groups according to the characteristic weight values of the data characteristics of the data source corresponding to each group in the nth data acquisition process aiming at the acquisition object;

the first modification module 54 is specifically adapted to: determining a characteristic weight value of each data source for the data characteristic of the acquisition object in the (n +1) th data acquisition process according to the following formula;

W_n+1＝(W_n+ m)/(n + 1); wherein, W_n+1A characteristic weight value, W, of the data source for the data characteristics of the acquisition object in the (n +1) th data acquisition process_nAnd determining the value of m for the characteristic weight value of the data source aiming at the data characteristics of the acquisition object in the nth data acquisition process according to the grouping score of the group corresponding to the data source.

Optionally, wherein the apparatus further comprises a setting module 51 adapted to:

the first obtaining module 52 is specifically adapted to: respectively acquiring a plurality of data characteristic values acquired by a plurality of data sources in the data acquisition process aiming at the data characteristics of the preset dimensionality of the acquired object;

the first determination module 53 is specifically adapted to: determining the grouping scores of the groups according to the characteristic weight values of the data source corresponding to each group aiming at the preset dimensionality of the acquisition object;

the first modification module 54 is specifically adapted to:

Example four

Fig. 6 is a block diagram of another data acquisition system based on multiple data sources according to a fourth embodiment of the present invention, where the system includes:

the second obtaining module 61 is adapted to obtain a plurality of store characteristic values, which are obtained by a plurality of data sources according to store characteristics of stores in the data collecting process;

a second determining module 62, adapted to divide the plurality of store characteristic values into at least one group, and determine a grouping score of each group according to a characteristic weight value of a data source corresponding to the group for the store;

and a second correcting module 63, adapted to determine, according to the grouping score of each group, an acquisition result of the store characteristics of the store in the data acquisition process, and correct the characteristic weight value of each data source for the store, so as to use the corrected characteristic weight value of each data source for the store in the next data acquisition process.

Optionally, wherein the second determining module 62 is specifically adapted to:

Optionally, the second modification module 63 is specifically adapted to:

Optionally, the second obtaining module 61 is specifically adapted to: respectively acquiring a plurality of store characteristic values acquired by a plurality of data sources aiming at store characteristics of stores in the (n +1) th data acquisition process; wherein n is a positive integer not less than 0;

and the second determination module 62 is specifically adapted to: determining grouping scores of the groups according to the characteristic weight values of the store characteristics of the stores in the nth data acquisition process of the data source corresponding to each group;

the second correction module 63 is specifically adapted to: determining a characteristic weight value of each data source for store characteristics of the store in the (n +1) th data acquisition process according to the following formula;

W_n+1＝(W_n+ m)/(n + 1); wherein, W_n+1A characteristic weight value, W, of the data source for store characteristics of the store during the (n +1) th data acquisition_nAnd determining the value of m for the characteristic weight value of the data source aiming at the store characteristics of the store in the nth data acquisition process according to the grouping score of the group corresponding to the data source.

Optionally, when the store characteristics of the store comprise a plurality of dimensions, the second obtaining module 61 is specifically adapted to: respectively acquiring a plurality of store characteristic values acquired by a plurality of data sources aiming at store characteristics of an acquisition object of a store in the data acquisition process;

said second determination module 62 is specifically adapted to: determining a grouping score of each group according to the characteristic weight value of the data source corresponding to the group for the dimension in the store;

the second correction module 63 is specifically adapted to:

EXAMPLE five

Fig. 7 is a schematic structural diagram of an electronic device according to a fifth embodiment of the present invention, and the specific embodiment of the present invention does not limit the specific implementation of the electronic device.

As shown in fig. 7, the electronic device may include: a processor (processor)702, a Communications Interface (Communications Interface)706, a memory (memory)704, and a Communications bus 708.

Wherein:

the processor 702, communication interface 706, and memory 704 communicate with one another via a communication bus 708.

A communication interface 706 for communicating with network elements of other devices, such as clients or other servers.

The processor 702 is configured to execute the program 710, and may specifically execute relevant steps in the above-described data acquisition method embodiments based on multiple data sources.

In particular, the program 710 may include program code that includes computer operating instructions.

The processor 702 may be a central processing unit CPU, or an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits configured to implement an embodiment of the invention. The electronic device comprises one or more processors, which can be the same type of processor, such as one or more CPUs; or may be different types of processors such as one or more CPUs and one or more ASICs.

And a memory 704 for storing a program 710. The memory 704 may comprise high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.

The program 710 may specifically be used to cause the processor 702 to perform the following operations:

respectively acquiring a plurality of data characteristic values acquired by a plurality of data sources aiming at the data characteristics of an acquired object in the data acquisition process;

dividing the plurality of data characteristic values into at least one group, and determining the grouping score of the group according to the characteristic weight value of the data source corresponding to each group aiming at the acquisition object;

and according to the grouping scores of all the groups, determining the acquisition result of the data characteristics of the acquisition object in the data acquisition process, and correcting the characteristic weight value of each data source aiming at the acquisition object so as to use the corrected characteristic weight value of each data source aiming at the acquisition object in the next data acquisition process.

EXAMPLE six

Fig. 8 is a schematic structural diagram of another electronic device according to a sixth embodiment of the present invention. The specific embodiment of the present invention does not limit the specific implementation of the electronic device.

As shown in fig. 8, the electronic device may include: a processor (processor)802, a communication Interface 806, a memory (memory)804, and a communication bus 808.

Wherein:

the processor 802, communication interface 806, and memory 804 are in communication with each other via a communication bus 808.

A communication interface 806 for communicating with network elements of other devices, such as clients or other servers.

The processor 802 is configured to execute the program 810, and may specifically execute relevant steps in the above-described data collection method embodiments based on multiple data sources.

In particular, the program 810 may include program code comprising computer operating instructions.

The processor 802 may be a central processing unit CPU, or an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits configured to implement an embodiment of the invention. The electronic device comprises one or more processors, which can be the same type of processor, such as one or more CPUs; or may be different types of processors such as one or more CPUs and one or more ASICs.

The memory 804 is used for storing the program 810. The memory 804 may comprise high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.

The program 810 may be specifically configured to cause the processor 802 to perform the following operations:

respectively acquiring a plurality of store characteristic values acquired by a plurality of data sources aiming at store characteristics of stores in the data acquisition process;

The algorithms and displays presented herein are not inherently related to any particular computer, virtual machine, or other apparatus. Various general purpose systems may also be used with the teachings herein. The required structure for constructing such a system will be apparent from the description above. Moreover, the present invention is not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.

In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.

Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.

Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.

Furthermore, those skilled in the art will appreciate that while some embodiments described herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.

The various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components in a voice input information based lottery system according to embodiments of the present invention. The present invention may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.

It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.

Claims

1. A method of data acquisition based on a plurality of data sources, comprising:

respectively acquiring a plurality of store characteristic values acquired by a plurality of data sources aiming at store characteristics of stores in the data acquisition process; wherein, the data source includes: a data source provided by a merchant, a data source provided by a user, and a data source provided by an APP; store characteristics of the store include at least one dimension of: store type dimension, merchandise dimension in store, and/or electronic ticket dimension; wherein, store type dimension specifically includes: store name, store address, and store longitude and latitude;

dividing the plurality of store characteristic values into at least one group through each characteristic fusion device in the data fusion device, and determining the grouping score of the group according to the characteristic weight value of the data source corresponding to each group aiming at the store; the method comprises the following steps of clustering the characteristic values of the plurality of stores according to a preset clustering rule, and dividing the characteristic values of the plurality of stores into at least one group according to a clustering result, wherein the clustering rule comprises the following steps: clustering rules based on numerical range, clustering rules based on how many words are, and clustering rules based on category;

according to the grouping scores of all the groups, determining the acquisition results of store characteristics of the stores in the data acquisition process, and correcting the characteristic weight values of all the data sources aiming at the stores so as to use the corrected characteristic weight values of all the data sources aiming at the stores in the data acquisition process of the next time;

the step of respectively acquiring a plurality of store characteristic values acquired by a plurality of data sources according to store characteristics of stores in the data acquisition process specifically includes: respectively acquiring a plurality of store characteristic values acquired by a plurality of data sources aiming at store characteristics of stores in the (n +1) th data acquisition process; wherein n is a positive integer not less than 0; and the step of determining the grouping score of each group according to the characteristic weight value of the data source corresponding to the group for the store specifically comprises: determining grouping scores of the groups according to the characteristic weight values of the store characteristics of the stores in the nth data acquisition process of the data source corresponding to each group; the step of correcting the characteristic weight values of the data sources for the stores specifically includes: determining a characteristic weight value of each data source for store characteristics of the store in the (n +1) th data acquisition process according to the following formula;

W_n+1＝(W_n+ m)/(n + 1); wherein, W_n+1A characteristic weight value, W, of the data source for store characteristics of the store during the (n +1) th data acquisition_nFor the data source, in the nth data acquisition process, for the characteristic weight value of the store characteristic of the store, the value of m is determined according to the comparison result of the grouping score of the group corresponding to the data source with the first preset threshold and the second preset threshold: if the grouping score is higher than a first preset threshold value, m is a positive value, and the value of m is in direct proportion to the difference value of the grouping score and the first preset threshold value; if the grouping score is lower than a second preset threshold value, m is a negative value, and the absolute value of m is in direct proportion to the difference value of the grouping score and the second preset threshold value.

2. The method according to claim 1, wherein the step of determining the grouping score of each group according to the characteristic weight value of the data source corresponding to the group for the store comprises:

3. The method according to claim 1, wherein the step of modifying the characteristic weight values of the respective data sources for the stores specifically comprises:

4. The method according to any one of claims 1 to 3, wherein when the store characteristics of the store include a plurality of dimensions, the step of respectively acquiring a plurality of store characteristic values acquired by a plurality of data sources for the store characteristics of the store during the data acquisition process specifically includes: respectively acquiring a plurality of store characteristic values acquired by a plurality of data sources aiming at store characteristics of an acquisition object of a store in the data acquisition process;

5. A data acquisition system based on a plurality of data sources, comprising:

the second acquisition module is suitable for respectively acquiring a plurality of store characteristic values acquired by a plurality of data sources aiming at store characteristics of stores in the data acquisition process; wherein, the data source includes: a data source provided by a merchant, a data source provided by a user, and a data source provided by an APP; store characteristics of the store include at least one dimension of: store type dimension, merchandise dimension in store, and/or electronic ticket dimension; wherein, store type dimension specifically includes: store name, store address, and store longitude and latitude;

the second determining module is suitable for dividing the plurality of store characteristic values into at least one group through each characteristic fusion device in the data fusion device, and determining the grouping score of the group according to the characteristic weight value of the data source corresponding to each group for the store; wherein the second determination module is specifically adapted to: clustering the characteristic values of the stores according to a preset clustering rule, and dividing the characteristic values of the stores into at least one group according to a clustering result, wherein the clustering rule comprises the following steps: clustering rules based on numerical range, clustering rules based on how many words are, and clustering rules based on category;

the second correcting module is suitable for determining the acquisition result of the store characteristics of the store in the data acquisition process according to the grouping scores of all the groups, and correcting the characteristic weight value of each data source for the store so as to use the corrected characteristic weight value of each data source for the store in the next data acquisition process;

wherein the second obtaining module is specifically adapted to: respectively acquiring a plurality of store characteristic values acquired by a plurality of data sources aiming at store characteristics of stores in the (n +1) th data acquisition process; wherein n is a positive integer not less than 0; and the second determination module is specifically adapted to: determining grouping scores of the groups according to the characteristic weight values of the store characteristics of the stores in the nth data acquisition process of the data source corresponding to each group; the second correction module is specifically adapted to: determining a characteristic weight value of each data source for store characteristics of the store in the (n +1) th data acquisition process according to the following formula; w_n+1＝(W_n+ m)/(n + 1); wherein, W_n+1A characteristic weight value, W, of the data source for store characteristics of the store during the (n +1) th data acquisition_nFor the data source, aiming at the door of the store in the nth data acquisition processThe value of m is determined according to the comparison result of the grouping score of the group corresponding to the data source and a first preset threshold and a second preset threshold: if the grouping score is higher than a first preset threshold value, m is a positive value, and the value of m is in direct proportion to the difference value of the grouping score and the first preset threshold value; if the grouping score is lower than a second preset threshold value, m is a negative value, and the absolute value of m is in direct proportion to the difference value of the grouping score and the second preset threshold value.

6. The system of claim 5, wherein the second determination module is specifically adapted to:

7. The system according to claim 5, wherein the second correction module is specifically adapted to:

8. The system of any of claims 5-7, wherein when the store characteristics of the store comprise a plurality of dimensions, the second acquisition module is specifically adapted to: respectively acquiring a plurality of store characteristic values acquired by a plurality of data sources aiming at store characteristics of an acquisition object of a store in the data acquisition process;

the second correction module is specifically adapted to:

9. An electronic device for data acquisition based on a plurality of data sources, comprising: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;

the memory is used for storing at least one executable instruction, and the executable instruction causes the processor to execute the operation corresponding to the data acquisition method based on a plurality of data sources in any one of claims 1-4.

10. A computer storage medium having stored therein at least one executable instruction for causing a processor to perform operations corresponding to the method for data collection based on multiple data sources of any one of claims 1-4.