Detailed Description
The technical solutions of the embodiments of the present application will be clearly described below with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which are obtained by a person skilled in the art based on the embodiments of the present application, fall within the scope of protection of the present application.
The terms first, second and the like in the description and in the claims, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged, as appropriate, such that embodiments of the present application may be implemented in sequences other than those illustrated or described herein, and that the objects identified by "first," "second," etc. are generally of a type, and are not limited to the number of objects, such as the first object may be one or more. Furthermore, in the description and claims, "and/or" means at least one of the connected objects, and the character "/", generally means that the associated object is an "or" relationship.
The resource allocation method and the resource allocation device provided by the embodiment of the application are described in detail below through specific embodiments and application scenes thereof with reference to the accompanying drawings.
In some embodiments of the present application, a resource allocation method is provided, fig. 1 shows a flowchart of a resource allocation method according to an embodiment of the present application, and as shown in fig. 1, the method includes:
102, obtaining M services to be exposed;
in step 102, the service to be exposed corresponds to N service attributes, where M and N are positive integers;
104, determining a first score of each service attribute in the N service attributes, and calculating to obtain a service score of the service to be exposed according to the first score;
Step 106, sequencing M businesses to be exposed based on the business scores to obtain a value sequence;
and step 108, exposing the service to be exposed according to the value sequence.
In the embodiment of the application, when the exposure opportunity exists, the service attributes of a plurality of services which can be exposed are confirmed, the score of the service to be exposed is determined based on the score of the service attributes, and the score is recorded as the service score of the service to be exposed.
The exposure opportunity refers to a presentation opportunity of a service, and one exposure opportunity may be a display area on a display interface, such as a content area on a web page, a "picture-in-picture" area during video playing, or an application recommendation bit in an application store, or an audio clip in broadcast audio.
The service to be exposed may be a piece of news content, an advertisement, a game or an Application (APP).
Thus, when there is an exposure opportunity, i.e. there is a window showing the above-mentioned service to be exposed to the user, an exposure opportunity is allocated to a service to be exposed, i.e. a showing resource is allocated to the service at a time.
Each service to be exposed corresponds to N service attributes, where the service attributes include attributes of the current service, such as an advertisement attribute, a content attribute, a distribution attribute, and the like, where one service to be exposed may have only one attribute, such as "a game" as an attribute of "a mobile game", and one service to be exposed may also have multiple attributes, such as "a game+an advertisement" as an attribute of "a hand-play advertisement".
Further, the first score of each business attribute is estimated through a real-time estimation model. In the estimating process, the service policy of the platform for providing the exposure opportunity can be referred, and the habit of the user of the exposure opportunity is referred to estimate the service value, so as to obtain a first score.
The application regards the services of various service types, namely the services with different service attributes, as equal services to be exposed, so that the service allocated to each exposure opportunity is not a fixed service type, and the content of service exposure is richer.
Meanwhile, the service score is obtained by combining multiple factors such as user preference, platform strategy and the like, and the exposure efficiency of one service can be intuitively expressed through the service score. Therefore, based on the service score of each service to be exposed, the current plurality of services to be exposed are sequenced, and the current exposure opportunity is distributed according to the sequenced value sequence, so that the service distributed to each exposure opportunity has higher value to both the platform and the user, and the efficiency of resource distribution can be effectively improved.
In some embodiments of the present application, calculating a service score of a service to be exposed according to a first score of each service attribute in the N service attributes includes:
normalizing the N first scores to obtain N normalized second scores;
acquiring N weight ratios, wherein the N weight ratios are in one-to-one correspondence with N second scores;
calculating the product of the second score of each service attribute and the corresponding weight ratio to obtain a third score of the service attribute;
and calculating the sum of the N third scores to obtain the service score.
In the embodiment of the application, one service to be exposed may have N service attributes, where the score of each service attribute is the first score. Specifically, the score of the business attribute refers to the score after comprehensively considering the user value and the platform value. For example, for a service of the content distribution class (i.e., the service attribute is service distribution), its value is typically expressed in terms of content Click-Through-Rate (CTR), while for a service of the advertisement class (i.e., the service attribute is advertisement), its value is typically expressed in terms of the last exposure benefit (EFFECTIVE COST PER MILLE, ECPM).
That is, the first score is represented differently for different business attributes, and the value is also greatly different. Therefore, in order to uniformly quantify the scores of the different types of service attributes, normalization processing can be performed on N first scores corresponding to N service attributes of one service to be exposed, and the normalized first scores are mapped to the same dimension, so that the true value of the different service attributes can be accurately quantified.
Further, after the normalization processing is performed on the N first scores, N second scores mapped to the same dimension are obtained, and N weight ratios corresponding to the N second scores one by one are obtained. Specifically, when determining the first score of the business attribute, different business attributes are scored based on platform strategies and user habits through a preset prediction model. As platform policies change and user portraits evolve, resulting in different business attributes, the value it has may also change in different platforms and different user eyes, thus resulting in prediction errors.
The application sets the corresponding weight ratio for each service attribute, and the weight ratio characterizes the importance degree of one service attribute in the current platform and the current user eyes. Therefore, by calculating the product of the weight ratio and the second score, superposition of prediction deviation can be effectively avoided, and accuracy of value calculation is improved.
After calculating the product of the second score of each service attribute and the corresponding weight ratio, adding the N second scores of the N service attributes to obtain a third score, namely the service score of the current service to be exposed. And sequencing the M services to be exposed based on the third scores of the M services to be exposed, wherein the service to be exposed with the highest third score is the service to be exposed with the highest sequencing, so that in the current exposure opportunity, the M services to be exposed are exposed according to the sequenced value sequence, the exposed services are relatively higher-value services for the current platform and the current user, and the service exposure efficiency is improved.
Specifically, the formula may be calculated as follows:
score=a1×F(object_1_scoren)+a2×F(object_2_scoren)……+an×F(object_n_sco
ren);
Wherein score is a service score of a service to be exposed, an is a weight ratio corresponding to a service attribute, object_n_ scoren is a first score of the service attribute, F (object_1_score) is a second score obtained by normalizing the first score, and an ×f (object_n_ scoren) is a third score.
Wherein F (x) is set as a normalized change function for uniformly mapping the distribution of the original first score into the interval of [0,1] to thereby realize uniform dimension, and thus 0≤F (object_1_score). Ltoreq.1.
In some embodiments of the present application, obtaining N weight ratios includes:
acquiring N preset weight ratios, and acquiring user characteristic information of a current user and platform policy information of a current platform, wherein the N preset weight ratios are in one-to-one correspondence with N service attributes;
and adjusting N preset weight ratios according to one or more of the user characteristic information and the platform strategy information to obtain N weight ratios.
In the embodiment of the application, a preset weight ratio can be prestored for each service attribute, and the weight ratio is the evaluation of the importance of each service under a general strategy. Further, platform policy information of the current platform and user characteristics of the current user are obtained. The preset weight ratio is adjusted through the platform strategy information and the user characteristic information, so that the weight ratio is more close to the current platform demand and user preference, and the finally exposed service has higher value for the platform and the user.
The preset weight ratio is to take the current status of the service attribute of the current service to be exposed as a starting point, and perform a plurality of groups of AB tests (AB test), so that the weight ratio of the service attribute gradually converges from a wide interval to a group of parameters { a1,a2……an }, wherein each parameter is the preset weight ratio of the service attribute.
In particular, the platform policy information includes unified regulation of exposure traffic by the platform, e.g., the platform policy information may include exposure limits for traffic of the same traffic attributes. For example, the current page includes two exposure opportunities, one of which has been assigned to a service with a "game" attribute. And the platform policy is that the same service type is not expected to be continuously exposed, and in a second exposure opportunity, the weight value corresponding to the service attribute of the game is dynamically reduced, so that the probability of occurrence of the game service is reduced, a plurality of exposure opportunities can be distributed to more service types, and the service exposure types are enriched.
By way of further example, platform policies include "content prioritization," i.e., platforms have higher priority settings for traffic of the content distribution class. At this time, the weight value of the service attribute of "content distribution" may be dynamically increased so that exposure opportunities are more allocated to the content distribution class service.
By way of further example, the platform policy includes setting different weights for different business attributes based on where exposure opportunities are located in the page. For example, in the exposure opportunity of the "version head" position of the web page, the weight value with the service attribute of "news" is dynamically increased.
And the user characteristic information comprises the historical behaviors of the user, and the corresponding user characteristic portrait is generated through the historical behaviors of the user. The historical behavior of the user comprises the click times, the watching time length or the playing time length of the business of different business types of the user. The more times a user clicks a service with a certain service attribute, the more interest the user has in the service with the service attribute, in other words, the user wants to see the service with the service attribute, and at this time, the weight value of the corresponding service attribute can be increased, so that the user can acquire more services with the service attribute.
In some embodiments, the user characteristic information includes programs that have been recently used by the user or websites that have been recently accessed by the user, and the weighting values of the business attributes associated with these historical behaviors are increased based on the type of programs that have been recently used by the user or websites that have been accessed by the user. If the user has recently accessed a game attack website, the weight value of the service attribute of 'game' is dynamically increased.
In other embodiments, the user characteristic information also includes a label setting that the user is "not interested," "complaint," or "no longer focused" on certain services. If the user sets a service, the user is not interested in one or more service attributes of the service, and even feels dislike, and the weight value of the corresponding service attribute can be reduced, so that the number of times that the user sees the service is reduced.
It can be understood that the "current user" for which the user information is directed may be a user account logged in to the platform, or may be a device identifier of an electronic device connected to the platform, or may be a network identifier accessing the platform. The application is not limited in this regard.
According to the application, the preset weight ratio of different service attributes is dynamically adjusted based on the platform strategy of the current platform and the user characteristics of the current user, so that the maximum value can be generated for both the platform and the user in each exposure, and the exposure efficiency is improved.
In some embodiments of the present application, sorting the M services to be exposed based on the service scores to obtain a value sequence includes:
and (3) based on the service scores, performing descending order arrangement on M services to be exposed to obtain a value sequence.
In the embodiment of the application, the larger the service score is, the more valuable a service to be exposed has to the platform and the user is. Therefore, the calculated service scores are arranged in a descending order, and the value of the service to be exposed which is the earlier in the obtained value sequence is higher, so that the M services to be exposed are exposed according to the sequence of the value sequence, more exposure opportunities can be distributed to the service with higher value, and the resource distribution efficiency is effectively improved.
In some embodiments of the application, business attributes include content distribution, advertising, merchandise, news, games, and applications.
In the embodiment of the application, the service attribute comprises content distribution, and the content distribution is specifically content trend, such as information, public classes, comments and the like, and the service with the content distribution attribute is in the display and sharing of content creation.
Advertisements include video advertisements, text advertisements, etc., and businesses with advertising properties are in the promotion and introduction of products or services.
The commodity comprises commodity introduction, commodity evaluation, commodity purchasing connection and the like, and the service with commodity attribute is to provide a commodity acquisition mode or a commodity purchasing mode.
News includes news flash, official announcement, real-time news, etc., and the business with news attribute is to show real-time news, and it has stronger timeliness.
Games include cell phone games, stand-alone games, network games, game-related services, and the like, and services with game attributes are to provide game-related content promotion, such as attack, and the like, and game-related services.
Applications include tool applications, communication applications, financial references, educational applications, and the like, and similar to game attributes, services with application attributes are to provide content promotion and services related to the applications.
By classifying different types of content to obtain different service attributes and marking the service to be exposed by one or more service attributes, service exposure can be not limited to specific classification any more, and the content of service exposure is richer.
In some embodiments of the present application, there is provided a resource allocation apparatus, fig. 2 shows a block diagram of a resource allocation apparatus according to an embodiment of the present application, and as shown in fig. 2, a resource allocation apparatus 200 includes:
An obtaining module 202, configured to obtain M services to be exposed, where the services to be exposed correspond to N service attributes, and M and N are positive integers;
a calculating module 204, configured to determine a first score of each service attribute in the N service attributes, and calculate a service score of the service to be exposed according to the first score;
The sorting module 206 is configured to sort the M services to be exposed based on the service scores, to obtain a value sequence;
and the exposure module 208 is used for exposing the service to be exposed according to the value sequence.
In the embodiment of the application, when the exposure opportunity exists, the service attributes of a plurality of services which can be exposed are confirmed, the score of the service to be exposed is determined based on the score of the service attributes, and the score is recorded as the service score of the service to be exposed. The service attributes include attributes of the current service, such as advertisement attributes, content attributes, distribution attributes, and the like, that is, the service of multiple service types is regarded as an equal service to be exposed, so that the service allocated to each exposure opportunity is not a fixed service type, and the content of service exposure is richer.
Meanwhile, the service score is obtained by combining multiple factors such as user preference, platform strategy and the like, and the exposure efficiency of one service can be intuitively expressed through the service score. Therefore, based on the service score of each service to be exposed, the current plurality of services to be exposed are sequenced, and the current exposure opportunity is distributed according to the sequenced value sequence, so that the service distributed to each exposure opportunity has higher value to both the platform and the user, and the efficiency of resource distribution can be effectively improved.
In some embodiments of the present application, the resource allocation apparatus further includes:
The processing module is used for carrying out normalization processing on the N first scores to obtain N second scores after normalization processing;
the acquisition module is also used for acquiring N weight ratios, wherein the N weight ratios are in one-to-one correspondence with the N second components;
The calculation module is further used for calculating products of the second scores of the service attributes and the corresponding weight ratios respectively to obtain third scores of the service attributes, and calculating the sum of the N third scores to obtain service scores.
In the embodiment of the application, one service to be exposed may have N service attributes, where the score of each service attribute is the first score. In order to uniformly quantify the scores of the different types of service attributes, normalization processing can be performed on N first scores corresponding to N service attributes of one service to be exposed, and the normalized first scores are mapped to the same dimension, so that the true value of the different service attributes can be accurately quantified.
After the normalization processing is carried out on the N first scores, N second scores mapped to the same dimension are obtained, and N weight ratios corresponding to the N second scores one by one are obtained. And calculating the product of the second score of each service attribute and the corresponding weight ratio, and adding N second scores of N service attributes to obtain a third score, namely the service score of the current service to be exposed. And sequencing the M services to be exposed based on the third scores of the M services to be exposed, wherein the service to be exposed with the highest third score is the service to be exposed with the highest sequencing, so that in the current exposure opportunity, the M services to be exposed are exposed according to the sequenced value sequence, the exposed services are relatively higher-value services for the current platform and the current user, and the service exposure efficiency is improved.
In some embodiments of the present application, the obtaining module is further configured to obtain N preset weight ratios, and obtain user feature information of a current user and platform policy information of a current platform, where the N preset weight ratios are in one-to-one correspondence with N service attributes;
the resource allocation apparatus further includes:
And the adjusting module is used for adjusting N preset weight ratios according to one or more of the user characteristic information and the platform strategy information to obtain N weight ratios.
In the embodiment of the application, a preset weight ratio can be prestored for each service attribute, and the weight ratio is the evaluation of the importance of each service under a general strategy. Further, a platform policy of the current platform and user characteristics of the current user are obtained. The preset weight ratio is adjusted through the platform strategy and the user characteristics, so that the weight ratio is more close to the current platform demand and user preference, and the finally exposed service has higher value for both the platform and the user.
According to the application, the preset weight ratio of different service attributes is dynamically adjusted based on the platform strategy of the current platform and the user characteristics of the current user, so that the maximum value can be generated for both the platform and the user in each exposure, and the exposure efficiency is improved.
In some embodiments of the present application, the sorting module is further configured to sort the M services to be exposed in a descending order based on the service score, to obtain a value sequence.
In the embodiment of the application, the larger the service score is, the more valuable a service to be exposed has to the platform and the user is. Therefore, the calculated service scores are arranged in a descending order, and the value of the service to be exposed which is the earlier in the obtained value sequence is higher, so that the M services to be exposed are exposed according to the sequence of the value sequence, more exposure opportunities can be distributed to the service with higher value, and the resource distribution efficiency is effectively improved.
In some embodiments of the application, business attributes include content distribution, advertising, merchandise, news, games, and applications.
In the embodiment of the application, the service attribute comprises content distribution, the content distribution is specifically content trend, such as consultation, evaluation and the like, the advertisement comprises video advertisement, text advertisement and the like, the commodity comprises commodity introduction, commodity purchase connection and the like, the news comprises news flash, official announcement, actual news and the like, the game comprises mobile game, game connection, game recharging and the like, and the application comprises tool application, communication application, financial reference, education application and the like.
By classifying different types of content to obtain different service attributes and marking the service to be exposed by one or more service attributes, service exposure can be not limited to specific classification any more, and the content of service exposure is richer.
The resource allocation device in the embodiment of the application can be a device, and also can be a component, an integrated circuit or a chip in the terminal. The device may be a mobile electronic device or a non-mobile electronic device. By way of example, the mobile electronic device may be a mobile phone, a tablet computer, a notebook computer, a palm computer, a vehicle-mounted electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook or a Personal Digital Assistant (PDA), etc., and the non-mobile electronic device may be a server, a network attached storage (Network Attached Storage, NAS), a personal computer (personal computer, PC), a Television (TV), a teller machine, a self-service machine, etc., and the embodiments of the present application are not limited in particular.
The resource allocation device in the embodiment of the application can be a device with an operating system. The operating system may be an Android operating system, an iOS operating system, or other possible operating systems, and the embodiment of the present application is not limited specifically.
The resource allocation device provided by the embodiment of the application can realize each process realized by the embodiment of the method, and in order to avoid repetition, the description is omitted.
Optionally, an embodiment of the present application further provides an electronic device, fig. 3 shows a block diagram of a structure of the electronic device according to an embodiment of the present application, as shown in fig. 3, an electronic device 300 includes a processor 302, a memory 304, and a program or an instruction stored in the memory 304 and capable of running on the processor 302, where the program or the instruction implements each process of the foregoing method embodiment when executed by the processor 302, and the process may achieve the same technical effect, and is not repeated herein.
The electronic device in the embodiment of the application includes the mobile electronic device and the non-mobile electronic device.
Fig. 4 is a schematic hardware structure of an electronic device implementing an embodiment of the present application.
The electronic device 400 includes, but is not limited to, a radio frequency unit 401, a network module 402, an audio output unit 403, an input unit 404, a sensor 405, a display unit 406, a user input unit 407, an interface unit 408, a memory 409, and a processor 410.
Those skilled in the art will appreciate that the electronic device 400 may also include a power source (e.g., a battery) for powering the various components, which may be logically connected to the processor 410 by a power management system to perform functions such as managing charge, discharge, and power consumption by the power management system. The electronic device structure shown in fig. 4 does not constitute a limitation of the electronic device, and the electronic device may include more or less components than shown, or may combine certain components, or may be arranged in different components, which are not described in detail herein.
The processor 410 is configured to obtain M services to be exposed, where the services to be exposed correspond to N service attributes, where M and N are positive integers, determine a first score of each service attribute of the N service attributes, calculate a service score of the services to be exposed according to the first score, sort the M services to be exposed based on the service scores to obtain a value sequence, and expose the services to be exposed according to the value sequence.
Optionally, the processor 410 is further configured to normalize the N first scores to obtain N second scores after normalization, obtain N weight ratios, where the N weight ratios are in one-to-one correspondence with the N second scores, calculate products of the second scores and the corresponding weight ratios of each service attribute to obtain third scores of the service attributes, and calculate sums of the N third scores to obtain the service scores.
Optionally, the processor 410 is further configured to obtain N preset weight ratios, and obtain user feature information of the current user and platform policy information of the current platform, where the N preset weight ratios are in one-to-one correspondence with the N service attributes, and adjust the N preset weight ratios according to one or more items of the user feature and the platform policy information to obtain the N weight ratios.
Optionally, the processor 410 is further configured to sort the M services to be exposed in a descending order based on the size of the service score, to obtain a value sequence.
Optionally, the business attributes include content distribution, advertising, merchandise, news, games, and applications.
In the embodiment of the application, when the exposure opportunity exists, the service attributes of a plurality of services which can highlight are confirmed, the score of the service to be exposed is determined based on the score of the service attributes, and the score is recorded as the service score of the service to be exposed. The service attributes include attributes of the current service, such as advertisement attributes, content attributes, distribution attributes, and the like, that is, the service of multiple service types is regarded as an equal service to be exposed, so that the service allocated to each exposure opportunity is not a fixed service type, and the content of service exposure is richer.
Meanwhile, the service score is obtained by combining multiple factors such as user preference, platform strategy and the like, and the exposure efficiency of one service can be intuitively expressed through the service score. Therefore, based on the service score of each service to be exposed, the current plurality of services to be exposed are sequenced, and the current exposure opportunity is distributed according to the sequenced value sequence, so that the service distributed to each exposure opportunity has higher value to both the platform and the user, and the efficiency of resource distribution can be effectively improved.
It should be appreciated that in embodiments of the present application, the input unit 404 may include a graphics processor (Graphics Processing Unit, GPU) 4041 and a microphone 4042, with the graphics processor 4041 processing image data of still pictures or video obtained by an image capture device (e.g., a camera) in a video capture mode or an image capture mode.
The display unit 406 may include a display panel 4061, and the display panel 4061 may be configured in the form of a liquid crystal display, an organic light emitting diode, or the like. The user input unit 407 includes a touch panel 4071 and other input devices 4072. The touch panel 4071 is also referred to as a touch screen. The touch panel 4071 may include two parts, a touch detection device and a touch controller. Other input devices 4072 may include, but are not limited to, a physical keyboard, function keys (e.g., volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, and so forth, which are not described in detail herein. Memory 409 may be used to store software programs as well as various data including, but not limited to, application programs and an operating system. The processor 410 may integrate an application processor that primarily handles operating systems, user interfaces, applications, etc., with a modem processor that primarily handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 410.
The embodiment of the application also provides a readable storage medium, on which a program or an instruction is stored, which when executed by a processor, implements each process of the above method embodiment, and can achieve the same technical effects, and in order to avoid repetition, the description is omitted here.
Wherein the processor is a processor in the electronic device described in the above embodiment. The readable storage medium includes a computer readable storage medium such as a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk or an optical disk, and the like.
The embodiment of the application further provides a chip, which comprises a processor and a communication interface, wherein the communication interface is coupled with the processor, and the processor is used for running programs or instructions to realize the processes of the embodiment of the method, and can achieve the same technical effects, so that repetition is avoided, and the description is omitted here.
It should be understood that the chips referred to in the embodiments of the present application may also be referred to as system-on-chip chips, chip systems, or system-on-chip chips, etc.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element. Furthermore, it should be noted that the scope of the methods and apparatus in the embodiments of the present application is not limited to performing the functions in the order shown or discussed, but may also include performing the functions in a substantially simultaneous manner or in an opposite order depending on the functions involved, e.g., the described methods may be performed in an order different from that described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a computer software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) comprising instructions for causing a terminal (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method according to the embodiments of the present application.
The embodiments of the present application have been described above with reference to the accompanying drawings, but the present application is not limited to the above-described embodiments, which are merely illustrative and not restrictive, and many forms may be made by those having ordinary skill in the art without departing from the spirit of the present application and the scope of the claims, which are to be protected by the present application.