CN111581514B - Information distribution method and device - Google Patents

Information distribution method and device Download PDF

Info

Publication number
CN111581514B
CN111581514B CN202010392113.6A CN202010392113A CN111581514B CN 111581514 B CN111581514 B CN 111581514B CN 202010392113 A CN202010392113 A CN 202010392113A CN 111581514 B CN111581514 B CN 111581514B
Authority
CN
China
Prior art keywords
information
search information
search
produced
target
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202010392113.6A
Other languages
Chinese (zh)
Other versions
CN111581514A (en
Inventor
傅馨仪
王玲玲
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Douyin Vision Co Ltd
Douyin Vision Beijing Co Ltd
Original Assignee
Beijing ByteDance Network Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing ByteDance Network Technology Co Ltd filed Critical Beijing ByteDance Network Technology Co Ltd
Priority to CN202010392113.6A priority Critical patent/CN111581514B/en
Publication of CN111581514A publication Critical patent/CN111581514A/en
Application granted granted Critical
Publication of CN111581514B publication Critical patent/CN111581514B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/955—Retrieval from the web using information identifiers, e.g. uniform resource locators [URL]
    • G06F16/9566—URL specific, e.g. using aliases, detecting broken or misspelled links
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Landscapes

  • Engineering & Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The disclosure provides an information distribution method and device, comprising the following steps: acquiring a plurality of pieces of search information to be produced; wherein, the search result corresponding to the search information to be produced does not accord with the preset condition; determining interaction parameters and attribute information respectively corresponding to the plurality of pieces of search information to be produced; determining the importance of each piece of search information to be produced based on the interaction parameters and attribute information respectively corresponding to the pieces of search information to be produced; and determining priority information of the plurality of pieces of search information to be produced based on the importance of each piece of search information to be produced, and sequentially sending the search information to be produced to a user terminal according to the priority information.

Description

Information distribution method and device
Technical Field
The disclosure relates to the technical field of information processing, and in particular relates to an information distribution method and device.
Background
When the user searches information, the user initiates a search request to the server through the user terminal, and the server sends a search result to the user terminal. In order to improve the browsing efficiency of the user, the user can conveniently view the screened search results by screening the search results meeting the preset conditions from the plurality of search results and displaying the screened search results in a special format.
For some search requests without search results meeting preset conditions, the search requests are generally sent to a user side corresponding to the domain to which the search requests belong directly according to the domain to which the search requests belong, and the user side performs production, however, when the number of search requests to be processed is large, due to limited production capacity, some important search requests may not be processed in time, so that when searching for the search results based on the search requests, the user cannot search for the search results meeting the conditions, and the search efficiency is affected.
Disclosure of Invention
The embodiment of the disclosure at least provides an information distribution method and device.
In a first aspect, an embodiment of the present disclosure provides an information allocation method, including:
acquiring a plurality of pieces of search information to be produced; wherein, the search result corresponding to the search information to be produced does not accord with the preset condition;
determining interaction parameters and attribute information respectively corresponding to the plurality of pieces of search information to be produced;
determining the importance of each piece of search information to be produced based on the interaction parameters and attribute information respectively corresponding to the pieces of search information to be produced;
and determining priority information of the plurality of pieces of search information to be produced based on the importance of each piece of search information to be produced, and sequentially sending the search information to be produced to a user terminal according to the priority information.
In a possible implementation manner, when the search information to be produced includes first search information, the interaction parameter corresponding to the search information to be produced includes the number of searches corresponding to the first search information, and the attribute information corresponding to the search information to be produced includes the stability information and/or the production requirement information of the first search information; the first search information is search information without target search results, and the target search results are search results meeting preset conditions;
when the search information to be produced comprises second search information, the interaction parameters corresponding to the search information to be produced comprise the browsing times of the target search results corresponding to the second search information, and the attribute information corresponding to the search information to be produced comprises the stability information and/or the production demand information of the first search information; the second search information is search information with target search results, wherein the target search results do not meet target conditions;
the stability information is used for indicating that the value of the interaction parameter in the preset time length from the current moment to the back of the search information to be produced is higher than the probability that the value of the interaction parameter in the preset time length from the current moment to the front of the search information to be produced is higher; the production demand information is used for representing the demand type of the search result to be produced, which corresponds to the search information to be produced.
In a possible implementation manner, the determining the importance of each piece of the search information to be produced based on the interaction parameters and the attribute information corresponding to the pieces of the search information to be produced respectively includes:
taking the interaction parameter of the search information to be produced as an initial importance degree;
and adjusting the initial importance based on the attribute information and a preset adjustment rule to obtain the importance of the search information to be produced.
In a possible implementation manner, the stability information of the search information to be produced is obtained based on a pre-trained neural network model;
the method further includes training the neural network model according to the following method:
acquiring sample search information, characteristic information corresponding to the sample search information and stability labels corresponding to the sample search information in a preset time period, wherein the sample search information has corresponding target search results, and the stability labels corresponding to the sample search information are used for indicating whether the values of interaction parameters of the sample search information are stable or not;
inputting the characteristic information corresponding to the sample search information and the interaction parameter corresponding to the sample search information into a neural network model to be trained, and outputting the predicted value of the interaction parameter in the preset time length from the current moment to the back of the sample search information, wherein the predicted probability is higher than the value of the interaction parameter in the preset time length from the current moment to the front of the sample search information;
Training the neural network model based on the predictive probability and the stability tag.
In a possible implementation manner, the characteristic information corresponding to the sample search information includes at least one of the following information:
the method comprises the steps of word vectors corresponding to sample search information, word vectors of at least one query request of target search results corresponding to the sample search information, sorting information of the target search results corresponding to the sample search information under different query requests, and uniform resource locators of the target search results corresponding to the sample search information. In a second aspect, an embodiment of the present disclosure further provides an information distribution apparatus, including:
the acquisition module is used for acquiring a plurality of pieces of search information to be produced, wherein the search results corresponding to the search information to be produced do not accord with preset conditions;
the first determining module is used for determining interaction parameters and attribute information respectively corresponding to the plurality of pieces of search information to be produced;
the second determining module is used for determining the importance of each piece of search information to be produced based on the interaction parameters and the attribute information respectively corresponding to the pieces of search information to be produced;
and the sending module is used for determining the priority information of the plurality of pieces of search information to be produced based on the importance of each piece of search information to be produced, and sequentially sending the search information to be produced to a user terminal according to the priority information.
In a possible implementation manner, when the search information to be produced includes first search information, the interaction parameter corresponding to the search information to be produced includes the number of searches corresponding to the first search information, and the attribute information corresponding to the search information to be produced includes the stability information and/or the production requirement information of the first search information; the first search information is search information without target search results, and the target search results are search results meeting preset conditions;
when the search information to be produced comprises second search information, the interaction parameters corresponding to the search information to be produced comprise the browsing times of the target search results corresponding to the second search information, and the attribute information corresponding to the search information to be produced comprises the stability information and/or the production demand information of the first search information; the second search information is search information with target search results, wherein the target search results do not meet target conditions;
the stability information is used for indicating that the value of the interaction parameter in the preset time length from the current moment to the back of the search information to be produced is higher than the probability that the value of the interaction parameter in the preset time length from the current moment to the front of the search information to be produced is higher; the production demand information is used for representing the demand type of the search result to be produced, which corresponds to the search information to be produced.
In a possible implementation manner, the second determining module is configured to, when determining importance of each piece of search information to be produced based on interaction parameters and attribute information corresponding to the pieces of search information to be produced respectively:
taking the interaction parameter of the search information to be produced as an initial importance degree;
and adjusting the initial importance based on the attribute information and a preset adjustment rule to obtain the importance of the search information to be produced.
In a possible implementation manner, the stability information of the search information to be produced is obtained based on a pre-trained neural network model;
the apparatus further includes a training module for training the neural network model according to the following method:
acquiring sample search information, characteristic information corresponding to the sample search information and stability labels corresponding to the sample search information in a preset time period, wherein the sample search information has corresponding target search results, and the stability labels corresponding to the sample search information are used for indicating whether the values of interaction parameters of the sample search information are stable or not;
Inputting the characteristic information corresponding to the sample search information and the interaction parameter corresponding to the sample search information into a neural network model to be trained, and outputting the predicted value of the interaction parameter in the preset time length from the current moment to the back of the sample search information, wherein the predicted probability is higher than the value of the interaction parameter in the preset time length from the current moment to the front of the sample search information;
training the neural network model based on the predictive probability and the stability tag.
In a possible implementation manner, the characteristic information corresponding to the sample search information includes at least one of the following information:
the method comprises the steps of word vectors corresponding to sample search information, word vectors of at least one query request of target search results corresponding to the sample search information, sorting information of the target search results corresponding to the sample search information under different query requests, and uniform resource locators of the target search results corresponding to the sample search information.
In a third aspect, embodiments of the present disclosure further provide a computer device, comprising: a processor, a memory and a bus, the memory storing machine-readable instructions executable by the processor, the processor and the memory in communication via the bus when the computer device is running, the machine-readable instructions when executed by the processor performing the steps of the first aspect, or any of the possible implementations of the first aspect.
In a fourth aspect, the presently disclosed embodiments also provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the first aspect, or any of the possible implementations of the first aspect.
According to the information distribution method and device, the importance degree of each piece of search information to be produced can be determined according to the interaction parameters and attribute information respectively corresponding to the pieces of search information to be produced, then the priority information of the search information to be produced is determined based on the importance degree of each piece of search information to be produced, the search information to be produced is sequentially sent according to the priority information, and the search information to be produced with higher importance degree corresponds to the search information with higher priority degree, so that the search information to be produced can be preferentially distributed, the distribution and production timeliness of the search information with higher importance degree can be improved, and the search efficiency of a user in searching can be improved.
The foregoing objects, features and advantages of the disclosure will be more readily apparent from the following detailed description of the preferred embodiments taken in conjunction with the accompanying drawings.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings required for the embodiments are briefly described below, which are incorporated in and constitute a part of the specification, these drawings showing embodiments consistent with the present disclosure and together with the description serve to illustrate the technical solutions of the present disclosure. It is to be understood that the following drawings illustrate only certain embodiments of the present disclosure and are therefore not to be considered limiting of its scope, for the person of ordinary skill in the art may admit to other equally relevant drawings without inventive effort.
FIG. 1 is a flow chart illustrating a method for information distribution provided by an embodiment of the present disclosure;
FIG. 2 illustrates a flow chart of a method of training a neural network model provided by an embodiment of the present disclosure;
FIG. 3 is a schematic diagram of a method for determining importance according to an embodiment of the present disclosure;
FIG. 4 is a schematic diagram of an information distribution device according to an embodiment of the present disclosure;
fig. 5 shows a schematic structural diagram of a computer device 500 according to an embodiment of the disclosure.
Detailed Description
For the purposes of making the objects, technical solutions and advantages of the embodiments of the present disclosure more apparent, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in the embodiments of the present disclosure, and it is apparent that the described embodiments are only some embodiments of the present disclosure, but not all embodiments. The components of the embodiments of the present disclosure, which are generally described and illustrated in the figures herein, may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present disclosure provided in the accompanying drawings is not intended to limit the scope of the disclosure, as claimed, but is merely representative of selected embodiments of the disclosure. All other embodiments, which can be made by those skilled in the art based on the embodiments of this disclosure without making any inventive effort, are intended to be within the scope of this disclosure.
In the related art, when a search request is sent to a user terminal corresponding to the domain of the search request, the search request is generally sent sequentially according to the time sequence of receiving the search request, but because the productivity of the user terminal is limited, the emergency degree and importance of different search requests are different, and only the distribution of the search request is performed according to the time sequence, so that part of urgent search requests may not be processed timely.
Based on the above, in the information distribution method and device, the importance of each piece of search information to be produced can be determined according to the interaction parameters and attribute information respectively corresponding to the pieces of search information to be produced, then the priority information of the search information to be produced is determined based on the importance of each piece of search information to be produced, and the search information to be produced is sequentially sent according to the priority information, and the search information to be produced with higher importance corresponds to the search information with higher priority, so that the search information to be produced can be preferentially distributed, thereby improving the distribution and production timeliness of the search information with higher importance and improving the search efficiency of a user during searching.
The present invention is directed to a method for manufacturing a semiconductor device, and a semiconductor device manufactured by the method.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures.
For the sake of understanding the present embodiment, first, a detailed description will be given of an information distribution method disclosed in the present embodiment, and an execution body of the information distribution method provided in the present embodiment is generally an electronic device with a certain computing capability, for example, may be a server.
The information distribution method provided by the embodiment of the present disclosure will be described below with a server as an execution body. Referring to fig. 1, a flowchart of an information distribution method according to an embodiment of the disclosure is shown, where the method includes the following steps:
step 101, acquiring a plurality of pieces of search information to be produced, wherein a search result corresponding to the search information to be produced does not accord with a preset condition.
Step 102, determining interaction parameters and attribute information respectively corresponding to the plurality of pieces of search information to be produced.
Step 103, determining the importance of each piece of search information to be produced based on the interaction parameters and the attribute information respectively corresponding to the pieces of search information to be produced.
Step 104, determining priority information of the plurality of pieces of search information to be produced based on the importance of each piece of search information to be produced, and sequentially sending the search information to be produced to a user terminal according to the priority information.
The following is a detailed description of the above steps.
Aiming at step 101,
The obtained search information to be generated may include two types, one type is first search information without target search results, and the other type is second search information with target search results, but the target search results do not meet target conditions; the target search result is a search result meeting a preset condition. The second search information includes related information of the corresponding target search result, for example, title information of the target search result.
For example, if a user initiates a certain search request, but does not find a target search result corresponding to the search request, at this time, the search request may be used as the first search information; if a user initiates a certain search request and finds a target search result corresponding to the search request, but the target search result does not meet a target condition, at this time, header information of the target search result corresponding to the search request may be used as the second search information.
In one possible implementation manner, a certain search request may correspond to a plurality of search results, when determining whether the search request has a target search result, the importance corresponding to each search result may be determined based on first interaction information corresponding to each search result, and if the search result with the highest importance meets a preset difference condition compared with other search results in the plurality of search results, the search request is determined to have the corresponding target search result.
The first interaction information corresponding to each search result may include a click time and/or a browsing time, and the determining the importance corresponding to each search result based on the first interaction information corresponding to each search result may be performed by performing weighted summation on information included in the first interaction information, and taking the weighted summation result as the importance corresponding to the search result; when the first interaction information only includes the clicking times (or only includes the browsing duration), the value of the first interaction information can be directly used as the importance corresponding to the search result.
The search result with the highest importance accords with the preset difference condition compared with other search results in the plurality of search results, and can comprise any one of the following cases:
in case 1, the difference between the search result with the highest importance and the search result with the next highest importance is larger than the preset difference.
Specifically, T can be satisfied 1 -T 2 >S, wherein T 1 Representing the importance of the search result with the highest importance, T 2 The importance of the search result having the next highest importance is represented, and S represents a preset difference.
And 2, the ratio of the search result with the highest importance in the search results with the top N digits of the importance row is larger than a preset ratio.
Concrete embodimentsOf which can be satisfied by T 1 /(T 1 +T 2 +…+T N )>Z, wherein T 1 Representing the importance of the search result with the highest importance, T 2 Representing the importance of the next highest search result, and so on, Z represents a preset ratio.
It should be noted that, whether each piece of search information corresponds to the target search result may be determined in advance based on the history search request, and after the search information is acquired, whether the search information has the corresponding target search result may be directly determined.
The target search result does not meet the target condition, and the second interaction information corresponding to the target search result may not meet the preset interaction condition. When the second interaction information corresponding to the target search result does not meet the preset interaction condition, the user experience corresponding to the target search result is poor, and the target search result can be produced again according to the related information of the target search result.
Wherein the second interaction information may include at least one of the following information:
the page stay time, the click rate and the difference between the click times of the target search results corresponding to the second search information and the click times of other search results except the target search results corresponding to the second search information.
The second interaction information does not conform to a preset interaction condition, and the value of any item of information in the interaction information is not in the value range corresponding to the item of information.
In another possible implementation manner, the target search result does not meet the target condition, and may be that the target search result has a risk.
In determining whether the target search result is at risk, a uniform resource locator (Uniform Resource Locator, URL) of the target search result and related information of the target search result (e.g., title information of the target search result) may be acquired first, and risk identification may be performed on the target search result based on the URL of the target search result.
In the URL based on the target search result, performing risk identification on the target search result, namely detecting whether the URL is located in a pre-stored high-risk resource database, if so, determining that the risk identification result indicates that the target search result has risk; or whether the data can be obtained based on the URL (since part of the data can only be detected but cannot be obtained), and if not, determining that the risk recognition result indicates that the target search result is at risk.
Aiming at step 102,
When determining interaction parameters and attribute information corresponding to a plurality of pieces of search information to be produced respectively, different interaction parameters and attribute information can be determined according to the types of the search information to be produced, and the method can be specifically divided into the following two cases:
Case 1, the search information to be produced includes first search information.
When the search information to be produced includes the first search information, the interaction parameter of the first search information may include the number of searches corresponding to the first search information; the attribute information of the first search information may include stability information and/or production demand information of the first search information.
Case 2, the search information to be produced includes second search information.
When the search information to be produced includes the second search information, the interaction parameter of the second search information may include the browsing times of the target search result corresponding to the second search information; the attribute information of the second search information includes stability information and/or production demand information of the second search information.
The stability information is used for indicating that the value of the interaction parameter in the preset time length from the current moment to the back of the search information to be produced is higher than the probability that the value of the interaction parameter in the preset time length from the current moment to the front of the search information to be produced is higher; the production demand information is used for representing the demand type of the search result to be produced, which corresponds to the search information to be produced.
For example, the stability information may represent a probability that the sum of the number of times the first search information is searched in the last 7 days is higher than the sum of the number of times the first search information is searched in the first 7 days.
In one possible embodiment, the stability information of the search information to be produced is obtained based on a pre-trained neural network model; in training the neural network model, reference may be made to a method as shown in fig. 2, comprising the steps of:
step 201, obtaining sample search information in a preset duration, feature information corresponding to the sample search information, and a stability tag corresponding to the sample search information, where the sample search information has a corresponding target search result, and the stability tag corresponding to the sample search information is used to indicate whether the value of the interaction parameter of the sample search information is stable.
The characteristic information corresponding to the sample search information may include at least one of the following information:
the method comprises the steps of word vectors corresponding to sample search information, word vectors of at least one query request of target search results corresponding to the sample search information, sorting information of the target search results corresponding to the sample search information under different query requests, and uniform resource locators of the target search results corresponding to the sample search information.
At least one query request of the target search result corresponding to the sample search information is a request that the target search result can be queried through the query request, and by way of example, the target search result corresponding to the sample search information is an article named as "how to braise meat", the query request corresponding to the target search result can be "how to braise meat", "how to braise meat is good", "how to braise meat in home edition", and the like, and the article named as "how to braise meat in red" can be searched through the query requests.
The sorting information of the target search results corresponding to the sample search information under different query requests is the sorting of the search results of the 'how to cook the braised pork' in the search results of the query requests such as 'how to cook the braised pork', 'how to cook the braised pork in the family', and the like, and if the search results are the target search results corresponding to the search requests of the 'how to cook the braised pork', the sorting information of the search results under the query request of the 'how to cook the braised pork' is 1.
Step 202, inputting feature information corresponding to the sample search information and interaction parameters corresponding to the sample search information into a neural network model to be trained, and outputting a predicted value of the interaction parameters in the preset time period from the current moment to the next of the sample search information, wherein the predicted probability is higher than the predicted probability of the interaction parameters in the preset time period from the current moment to the next of the sample search information.
Step 203, training the neural network model based on the prediction probability and the stability label.
Specifically, when training the neural network model based on the prediction probability and the stability label, a loss value in the training process can be determined based on the prediction probability and the stability label, and then the model parameter value in the neural network model can be adjusted based on the loss value.
After the neural network model is trained, when predicting is performed based on the neural network model, the search information to be produced can be directly input into the neural network model, and the probability that the value of the interaction parameter in the preset time length from the current moment to the back of the search information to be produced can be obtained is output, so that the probability of the value of the interaction parameter in the preset time length from the current moment to the front of the search information to be produced is high.
The production demand information includes at least one of the following information:
information on the domain, information on the format required, whether a professional answer is required, whether an encyclopedia needs to be generated.
By way of example, the domain information may include food, medicine, electronics, farming, planting, etc., and the required format information may include video format, audio format, text format, picture format, etc.
In one possible implementation manner, when determining production requirement information corresponding to the search information to be produced, the search information to be produced may be input into a neural network model trained in advance, the neural network model may output a probability value corresponding to each production requirement information corresponding to the search information to be produced, and then determine the production requirement information corresponding to the search information to be produced according to the probability values.
For example, if the production requirement information includes the domain information, after the search information to be produced is input into the neural network model trained in advance, the neural network model may output a probability that the search information to be produced belongs to the food domain, a probability that the search information belongs to the medical domain, a probability that the search information belongs to the electronic domain, a probability that the search information belongs to the cultivation domain, and a probability that the search information belongs to the planting domain, and if the probability that the search information belongs to the food domain is highest, it is determined that the production requirement information corresponding to the search information to be produced is the food domain.
In one possible implementation manner, when determining the production requirement information corresponding to the search information to be produced, the method may tag the search information to be produced, different production requirement information may correspond to a tag with an attribute, for example, the domain information may correspond to a domain tag, the required format information may correspond to a resource form tag, whether a required professional answer may correspond to a resource authority judging tag, whether an encyclopedia may correspond to a resource meeting trend tag needs to be generated, after inputting the search information to be produced into the neural network model, the neural network model may determine the value of each type of tag according to the four types of tags, and then tag the search information to be produced, for example, the tag corresponding to the input search information to be produced may be a video requirement tag (the domain information is a video type), a video requirement tag (the required format information is a video format), an expert requirement tag (the required professional answer), and an encyclopedia requirement tag (the encyclopedia needs to be generated).
Because the neural network model has limited precision, in order to improve the precision of determining the production requirement information corresponding to the search information to be produced, in one possible implementation manner, after determining the production requirement information corresponding to the search information to be produced based on the neural network model, the search information to be produced and the determined production requirement information corresponding to the search information to be produced can be sent to the server, the production requirement information of the search information to be produced is audited by the staff, if the audit is passed, the staff can feed back an audit passing instruction through the server, and after receiving the audit passing instruction, the server directly determines the production requirement information determined by the neural network model as the production requirement information corresponding to the search information to be produced; if the verification is not passed, the staff can modify the production demand information, then the modified production demand information is fed back to the server, and the server takes the modified production demand information as the production demand information of the search information to be produced; or if the audit is not passed, feeding back an audit-failing instruction to the server, and after receiving the audit-failing instruction, re-inputting the search information to be produced into the neural network model by the server again, and re-determining the production demand information of the search information to be produced.
Aiming at step 103,
When determining the importance of each piece of search information to be produced based on the interaction parameters and the attribute information respectively corresponding to the pieces of search information to be produced, the interaction parameters of the search information to be produced can be used as the initial importance, and then the initial importance is adjusted based on the attribute information and the preset adjustment rule to obtain the importance of the search information to be produced.
The adjustment rule may be a preset rule, for example, as shown in fig. 3, when the initial importance is adjusted based on the attribute information and the preset adjustment rule, the initial importance may be increased by a if the value of the stability information is greater than a first preset value a; the initial importance may also be adjusted according to the category of the search information to be produced, for example, if the search information to be produced belongs to the first search information, the initial importance is increased by b times, and if the search information to be produced belongs to the second search information, the initial importance is increased by c times; in addition, the initial importance degree can be adjusted according to the label of the search information to be produced, for example, when the search information to be produced carries the target label, the basic importance degree can be increased by d times.
If the value of the stability information of a certain search information to be produced is greater than a, and the search information to be produced is the first search information, the search information to be produced carries target tag information, and the value of the interaction parameter is set to be p, when the importance of the search information to be produced is calculated, importance=p (1+a) (1+b) (1+c).
For step 104,
Determining priority information of the plurality of pieces of search information to be produced based on the importance of each piece of search information to be produced, wherein the priority information is the sequencing result of the search information to be produced; when the search information to be produced is sent to the user terminal once according to the priority information, the search information to be produced, which is arranged in the first N bits, can be selected each time, then the search information to be produced in the first N bits is sent to the user terminal, then the rest search information to be produced is rearranged, the search information to be produced, which is arranged in the first N bits, is selected and sent to the user terminal, and the like, wherein N is a positive integer.
Here, it should be noted that the client may include a plurality of clients, and when sending the search information to be produced to the client, each search information to be produced may be sent to the client that matches the search information to be produced.
When determining the user end matched with the search information to be produced, the attribute information of each user end can be determined based on the production requirement information corresponding to the historical search result generated by each user end, and then the user end matched with the search information to be produced is determined from each user end based on the production requirement information corresponding to the search information to be produced and the attribute information of each user end.
According to the information distribution method provided by the embodiment of the disclosure, the importance of each piece of search information to be produced can be determined according to the interaction parameters and attribute information respectively corresponding to the plurality of pieces of search information to be produced, then the priority information of the search information to be produced is determined based on the importance of each piece of search information to be produced, the search information to be produced is sequentially sent according to the priority information, and the search information to be produced with higher importance corresponds to the search information with higher priority, so that the search information to be produced can be preferentially distributed, the distribution of the search information with higher importance and the timeliness of production can be improved, and the search efficiency of a user in searching can be improved.
It will be appreciated by those skilled in the art that in the above-described method of the specific embodiments, the written order of steps is not meant to imply a strict order of execution but rather should be construed according to the function and possibly inherent logic of the steps.
Based on the same inventive concept, the embodiments of the present disclosure further provide an information distribution device corresponding to the information distribution method, and since the principle of solving the problem by the device in the embodiments of the present disclosure is similar to that of the information distribution method in the embodiments of the present disclosure, the implementation of the device may refer to the implementation of the method, and the repetition is omitted.
Referring to fig. 4, an architecture diagram of an information distribution device according to an embodiment of the disclosure is shown, where the device includes: an acquisition module 401, a first determination module 402, a second determination module 403, a transmission module 404, and a training module 405; wherein,,
an obtaining module 401, configured to obtain a plurality of pieces of search information to be produced, where a search result corresponding to the search information to be produced does not conform to a preset condition;
a first determining module 402, configured to determine interaction parameters and attribute information corresponding to the plurality of pieces of search information to be produced respectively;
A second determining module 403, configured to determine importance of each piece of search information to be produced based on interaction parameters and attribute information corresponding to the pieces of search information to be produced respectively;
and the sending module 404 is configured to determine priority information of the plurality of pieces of search information to be produced based on importance of each piece of search information to be produced, and send the search information to be produced to a user side sequentially according to the priority information.
In a possible implementation manner, when the search information to be produced includes first search information, the interaction parameter corresponding to the search information to be produced includes the number of searches corresponding to the first search information, and the attribute information corresponding to the search information to be produced includes the stability information and/or the production requirement information of the first search information; the first search information is search information without target search results, and the target search results are search results meeting preset conditions;
when the search information to be produced comprises second search information, the interaction parameters corresponding to the search information to be produced comprise the browsing times of the target search results corresponding to the second search information, and the attribute information corresponding to the search information to be produced comprises the stability information and/or the production demand information of the first search information; the second search information is search information with target search results, wherein the target search results do not meet target conditions;
The stability information is used for indicating that the value of the interaction parameter in the preset time length from the current moment to the back of the search information to be produced is higher than the probability that the value of the interaction parameter in the preset time length from the current moment to the front of the search information to be produced is higher; the production demand information is used for representing the demand type of the search result to be produced, which corresponds to the search information to be produced.
In a possible implementation manner, the second determining module 403 is configured to, when determining the importance of each piece of the to-be-produced search information based on the interaction parameters and attribute information corresponding to the pieces of the to-be-produced search information, respectively:
taking the interaction parameter of the search information to be produced as an initial importance degree;
and adjusting the initial importance based on the attribute information and a preset adjustment rule to obtain the importance of the search information to be produced.
In a possible implementation manner, the stability information of the search information to be produced is obtained based on a pre-trained neural network model;
the apparatus further comprises a training module 405, the training module 405 being configured to train the neural network model according to the following method:
Acquiring sample search information, characteristic information corresponding to the sample search information and stability labels corresponding to the sample search information in a preset time period, wherein the sample search information has corresponding target search results, and the stability labels corresponding to the sample search information are used for indicating whether the values of interaction parameters of the sample search information are stable or not;
inputting the characteristic information corresponding to the sample search information and the interaction parameter corresponding to the sample search information into a neural network model to be trained, and outputting the predicted value of the interaction parameter in the preset time length from the current moment to the back of the sample search information, wherein the predicted probability is higher than the value of the interaction parameter in the preset time length from the current moment to the front of the sample search information;
training the neural network model based on the predictive probability and the stability tag.
In a possible implementation manner, the characteristic information corresponding to the sample search information includes at least one of the following information:
the method comprises the steps of word vectors corresponding to sample search information, word vectors of at least one query request of target search results corresponding to the sample search information, sorting information of the target search results corresponding to the sample search information under different query requests, and uniform resource locators of the target search results corresponding to the sample search information.
The process flow of each module in the apparatus and the interaction flow between the modules may be described with reference to the related descriptions in the above method embodiments, which are not described in detail herein.
Based on the same technical conception, the embodiment of the application also provides computer equipment. Referring to fig. 5, a schematic structural diagram of a computer device 500 according to an embodiment of the present application includes a processor 501, a memory 502, and a bus 503. The memory 502 is configured to store execution instructions, including a memory 5021 and an external memory 5022; the memory 5021 is also referred to as an internal memory, and is used for temporarily storing operation data in the processor 501 and data exchanged with an external memory 5022 such as a hard disk, the processor 501 exchanges data with the external memory 5022 through the memory 5021, and when the computer device 500 is running, the processor 501 and the memory 502 communicate through the bus 503, so that the processor 501 executes the following instructions:
acquiring a plurality of pieces of search information to be produced; wherein, the search result corresponding to the search information to be produced does not accord with the preset condition;
determining interaction parameters and attribute information respectively corresponding to the plurality of pieces of search information to be produced;
Determining the importance of each piece of search information to be produced based on the interaction parameters and attribute information respectively corresponding to the pieces of search information to be produced;
and determining priority information of the plurality of pieces of search information to be produced based on the importance of each piece of search information to be produced, and sequentially sending the search information to be produced to a user terminal according to the priority information.
In a possible implementation manner, in the instructions executed by the processor 501, when the search information to be produced includes first search information, the interaction parameter corresponding to the search information to be produced includes the number of searches corresponding to the first search information, and the attribute information corresponding to the search information to be produced includes the stability information and/or the production requirement information of the first search information; the first search information is search information without target search results, and the target search results are search results meeting preset conditions;
when the search information to be produced comprises second search information, the interaction parameters corresponding to the search information to be produced comprise the browsing times of the target search results corresponding to the second search information, and the attribute information corresponding to the search information to be produced comprises the stability information and/or the production demand information of the first search information; the second search information is search information with target search results, wherein the target search results do not meet target conditions;
The stability information is used for indicating that the value of the interaction parameter in the preset time length from the current moment to the back of the search information to be produced is higher than the probability that the value of the interaction parameter in the preset time length from the current moment to the front of the search information to be produced is higher; the production demand information is used for representing the demand type of the search result to be produced, which corresponds to the search information to be produced.
In a possible implementation manner, in the instructions executed by the processor 501, the determining the importance of each piece of search information to be produced based on the interaction parameters and attribute information corresponding to the pieces of search information to be produced respectively includes:
taking the interaction parameter of the search information to be produced as an initial importance degree;
and adjusting the initial importance based on the attribute information and a preset adjustment rule to obtain the importance of the search information to be produced.
In a possible implementation manner, in the instructions executed by the processor 501, the stability information of the search information to be produced is obtained based on a pre-trained neural network model;
the method further includes training the neural network model according to the following method:
Acquiring sample search information, characteristic information corresponding to the sample search information and stability labels corresponding to the sample search information in a preset time period, wherein the sample search information has corresponding target search results, and the stability labels corresponding to the sample search information are used for indicating whether the values of interaction parameters of the sample search information are stable or not;
inputting the characteristic information corresponding to the sample search information and the interaction parameter corresponding to the sample search information into a neural network model to be trained, and outputting the predicted value of the interaction parameter in the preset time length from the current moment to the back of the sample search information, wherein the predicted probability is higher than the value of the interaction parameter in the preset time length from the current moment to the front of the sample search information;
training the neural network model based on the predictive probability and the stability tag.
In a possible implementation manner, in the instructions executed by the processor 501, the feature information corresponding to the sample search information includes at least one of the following information:
the method comprises the steps of word vectors corresponding to sample search information, word vectors of at least one query request of target search results corresponding to the sample search information, sorting information of the target search results corresponding to the sample search information under different query requests, and uniform resource locators of the target search results corresponding to the sample search information.
The disclosed embodiments also provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the information distribution method described in the method embodiments above. Wherein the storage medium may be a volatile or nonvolatile computer readable storage medium.
The computer program product of the information distribution method provided by the embodiment of the disclosure includes a computer readable storage medium storing a program code, where the program code includes instructions for executing the steps of the information distribution method described in the above method embodiment, and specifically, reference may be made to the above method embodiment, which is not described herein.
The disclosed embodiments also provide a computer program which, when executed by a processor, implements any of the methods of the previous embodiments. The computer program product may be realized in particular by means of hardware, software or a combination thereof. In an alternative embodiment, the computer program product is embodied as a computer storage medium, and in another alternative embodiment, the computer program product is embodied as a software product, such as a software development kit (Software Development Kit, SDK), or the like.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described system and apparatus may refer to corresponding procedures in the foregoing method embodiments, which are not described herein again. In the several embodiments provided in the present disclosure, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. The above-described apparatus embodiments are merely illustrative, for example, the division of the units is merely a logical function division, and there may be other manners of division in actual implementation, and for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some communication interface, device or unit indirect coupling or communication connection, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present disclosure may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer readable storage medium executable by a processor. Based on such understanding, the technical solution of the present disclosure may be embodied in essence or a part contributing to the prior art or a part of the technical solution, or in the form of a software product stored in a storage medium, including several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in the embodiments of the present disclosure. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Finally, it should be noted that: the foregoing examples are merely specific embodiments of the present disclosure, and are not intended to limit the scope of the disclosure, but the present disclosure is not limited thereto, and those skilled in the art will appreciate that while the foregoing examples are described in detail, it is not limited to the disclosure: any person skilled in the art, within the technical scope of the disclosure of the present disclosure, may modify or easily conceive changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features thereof; such modifications, changes or substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the disclosure, and are intended to be included within the scope of the present disclosure. Therefore, the protection scope of the present disclosure shall be subject to the protection scope of the claims.

Claims (10)

1. An information distribution method, comprising:
acquiring a plurality of pieces of search information to be produced; wherein, the search result corresponding to the search information to be produced does not accord with the preset condition;
determining interaction parameters and attribute information respectively corresponding to the plurality of pieces of search information to be produced; the attribute information comprises stability information, wherein the stability information is used for indicating the probability that the value of the interaction parameter in the preset time length from the current moment to the back of the search information to be produced is higher than the probability that the value of the interaction parameter in the preset time length from the current moment to the front of the search information to be produced;
determining the importance of each piece of search information to be produced based on the interaction parameters and attribute information respectively corresponding to the pieces of search information to be produced;
and determining priority information of the plurality of pieces of search information to be produced based on the importance of each piece of search information to be produced, and sequentially sending the search information to be produced to a user terminal according to the priority information.
2. The method according to claim 1, wherein when the search information to be produced includes first search information, the interaction parameter corresponding to the search information to be produced includes a number of searches corresponding to the first search information, and the attribute information corresponding to the search information to be produced further includes production requirement information of the first search information; the first search information is search information without target search results, and the target search results are search results meeting preset conditions;
When the search information to be produced comprises second search information, the interaction parameters corresponding to the search information to be produced comprise the browsing times of the target search results corresponding to the second search information, and the attribute information corresponding to the search information to be produced also comprises the production requirement information of the second search information; the second search information is search information with target search results, wherein the target search results do not meet target conditions;
the production requirement information is used for indicating a requirement type of a search result to be produced, which corresponds to the search information to be produced.
3. The method according to claim 1, wherein determining the importance of each piece of the search information to be produced based on the interaction parameters and the attribute information respectively corresponding to the pieces of the search information to be produced includes:
taking the interaction parameter of the search information to be produced as an initial importance degree;
and adjusting the initial importance based on the attribute information and a preset adjustment rule to obtain the importance of the search information to be produced.
4. The method according to claim 2, wherein the stability information of the search information to be produced is obtained based on a pre-trained neural network model;
The method further includes training the neural network model according to the following method:
acquiring sample search information, characteristic information corresponding to the sample search information and stability labels corresponding to the sample search information in a preset time period, wherein the sample search information has corresponding target search results, and the stability labels corresponding to the sample search information are used for indicating whether the values of interaction parameters of the sample search information are stable or not;
inputting the characteristic information corresponding to the sample search information and the interaction parameter corresponding to the sample search information into a neural network model to be trained, and outputting the predicted value of the interaction parameter in the preset time length from the current moment to the back of the sample search information, wherein the predicted probability is higher than the value of the interaction parameter in the preset time length from the current moment to the front of the sample search information;
training the neural network model based on the predictive probability and the stability tag.
5. The method of claim 4, wherein the characteristic information corresponding to the sample search information includes at least one of:
The method comprises the steps of word vectors corresponding to sample search information, word vectors of at least one query request of target search results corresponding to the sample search information, sorting information of the target search results corresponding to the sample search information under different query requests, and uniform resource locators of the target search results corresponding to the sample search information.
6. An information distribution device, characterized by comprising:
the acquisition module is used for acquiring a plurality of pieces of search information to be produced, wherein the search results corresponding to the search information to be produced do not accord with preset conditions;
the first determining module is used for determining interaction parameters and attribute information respectively corresponding to the plurality of pieces of search information to be produced; the attribute information comprises stability information, wherein the stability information is used for indicating the probability that the value of the interaction parameter in the preset time length from the current moment to the back of the search information to be produced is higher than the probability that the value of the interaction parameter in the preset time length from the current moment to the front of the search information to be produced;
the second determining module is used for determining the importance of each piece of search information to be produced based on the interaction parameters and the attribute information respectively corresponding to the pieces of search information to be produced;
And the sending module is used for determining the priority information of the plurality of pieces of search information to be produced based on the importance of each piece of search information to be produced, and sequentially sending the search information to be produced to a user terminal according to the priority information.
7. The apparatus of claim 6, wherein when the search information to be produced includes first search information, the interaction parameter corresponding to the search information to be produced includes a number of searches corresponding to the first search information, and the attribute information corresponding to the search information to be produced further includes production requirement information of the first search information; the first search information is search information without target search results, and the target search results are search results meeting preset conditions;
when the search information to be produced comprises second search information, the interaction parameters corresponding to the search information to be produced comprise the browsing times of the target search results corresponding to the second search information, and the attribute information corresponding to the search information to be produced also comprises the production requirement information of the second search information; the second search information is search information with target search results, wherein the target search results do not meet target conditions;
The production requirement information is used for indicating a requirement type of a search result to be produced, which corresponds to the search information to be produced.
8. The apparatus of claim 6, wherein the second determining module is configured to, when determining importance of each piece of search information to be produced based on interaction parameters and attribute information corresponding to the pieces of search information to be produced, respectively:
taking the interaction parameter of the search information to be produced as an initial importance degree;
and adjusting the initial importance based on the attribute information and a preset adjustment rule to obtain the importance of the search information to be produced.
9. A computer device, comprising: a processor, a memory and a bus, said memory storing machine readable instructions executable by said processor, said processor and said memory communicating via the bus when the computer device is running, said machine readable instructions when executed by said processor performing the steps of the information distribution method according to any of claims 1 to 5.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a computer program which, when executed by a processor, performs the steps of the information distribution method according to any of claims 1 to 5.
CN202010392113.6A 2020-05-11 2020-05-11 Information distribution method and device Active CN111581514B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010392113.6A CN111581514B (en) 2020-05-11 2020-05-11 Information distribution method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010392113.6A CN111581514B (en) 2020-05-11 2020-05-11 Information distribution method and device

Publications (2)

Publication Number Publication Date
CN111581514A CN111581514A (en) 2020-08-25
CN111581514B true CN111581514B (en) 2023-05-09

Family

ID=72126478

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010392113.6A Active CN111581514B (en) 2020-05-11 2020-05-11 Information distribution method and device

Country Status (1)

Country Link
CN (1) CN111581514B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104866522A (en) * 2015-03-25 2015-08-26 百度在线网络技术（北京）有限公司 Method and device for providing answer information for questioner
CN107992604A (en) * 2017-12-14 2018-05-04 北京搜狗科技发展有限公司 The distribution method and relevant apparatus of a kind of task entry
US10366349B1 (en) * 2010-07-22 2019-07-30 Intuit Inc. Question prioritization in community-driven question-and-answer systems
CN111581486A (en) * 2020-05-11 2020-08-25 北京字节跳动网络技术有限公司 Information distribution method and device

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10366349B1 (en) * 2010-07-22 2019-07-30 Intuit Inc. Question prioritization in community-driven question-and-answer systems
CN104866522A (en) * 2015-03-25 2015-08-26 百度在线网络技术（北京）有限公司 Method and device for providing answer information for questioner
CN107992604A (en) * 2017-12-14 2018-05-04 北京搜狗科技发展有限公司 The distribution method and relevant apparatus of a kind of task entry
CN111581486A (en) * 2020-05-11 2020-08-25 北京字节跳动网络技术有限公司 Information distribution method and device

Also Published As

Publication number Publication date
CN111581514A (en) 2020-08-25

Similar Documents

Publication Publication Date Title
CN109492764B (en) Training method, related equipment and medium for generating countermeasure network
CN109168047B (en) Video recommendation method and device, server and storage medium
CN112035599B (en) Query method and device based on vertical search, computer equipment and storage medium
TW201322021A (en) Image search method and image search apparatus
US10628403B2 (en) Annotation system for extracting attributes from electronic data structures
CN109918498B (en) Problem warehousing method and device
CN106339507A (en) Method and device for pushing streaming media message
CN111125328B (en) Text processing method and related equipment
CN111581486B (en) Information distribution method and device
CN113391867B (en) Big data service processing method and service server based on digitization and visualization
CN111581514B (en) Information distribution method and device
CN117611272A (en) Commodity recommendation method and device and electronic equipment
CN113032524A (en) Trademark infringement identification method, terminal device and storage medium
US20070043711A1 (en) System and method for optimizing event predicate processing
CN111581487B (en) Information processing method and device
CN111489207A (en) Evaluation information writing method and device based on block chain system and hardware equipment
EP4002157A1 (en) Method and system for identifying user search scenario
CN114528908B (en) Network request data classification model training method, classification method and storage medium
CN111581515B (en) Information processing method and device
CN112328779B (en) Training sample construction method, device, terminal equipment and storage medium
CN114282119A (en) Scientific and technological information resource retrieval method and system based on heterogeneous information network
CN114093447A (en) Data asset recommendation method and device, computer equipment and storage medium
CN114338058A (en) Information processing method, device and storage medium
CN111581485B (en) Information distribution method and device
CN106919626B (en) Data processing method and device and data query method and device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
CP01 Change in the name or title of a patent holder
CP01 Change in the name or title of a patent holder

Address after: 100041 B-0035, 2 floor, 3 building, 30 Shixing street, Shijingshan District, Beijing.

Patentee after: Douyin Vision Co.,Ltd.

Address before: 100041 B-0035, 2 floor, 3 building, 30 Shixing street, Shijingshan District, Beijing.

Patentee before: Tiktok vision (Beijing) Co.,Ltd.

Address after: 100041 B-0035, 2 floor, 3 building, 30 Shixing street, Shijingshan District, Beijing.

Patentee after: Tiktok vision (Beijing) Co.,Ltd.

Address before: 100041 B-0035, 2 floor, 3 building, 30 Shixing street, Shijingshan District, Beijing.

Patentee before: BEIJING BYTEDANCE NETWORK TECHNOLOGY Co.,Ltd.