CN111581515A

CN111581515A - Information processing method and device

Info

Publication number: CN111581515A
Application number: CN202010392595.5A
Authority: CN
Inventors: 林馨怡; 傅馨仪; 汪忠超
Original assignee: Beijing ByteDance Network Technology Co Ltd
Current assignee: Douyin Vision Co Ltd; Douyin Vision Beijing Co Ltd
Priority date: 2020-05-11
Filing date: 2020-05-11
Publication date: 2020-08-25
Anticipated expiration: 2040-05-11
Also published as: CN111581515B

Abstract

The present disclosure provides an information processing method and apparatus, including: acquiring a plurality of pieces of search information generated in a preset time period; determining search information to be produced based on the plurality of pieces of search information; the search result corresponding to the search information to be produced does not accord with the preset condition; determining production demand information corresponding to the search information to be produced, wherein the production demand information is used for representing the demand type of the search result to be produced corresponding to the search information; and sending the search information to be produced to a target user side matched with the production demand information.

Description

Information processing method and device

Technical Field

The present disclosure relates to the field of computer technologies, and in particular, to an information processing method and apparatus.

Background

When a user searches information, a search request is sent to the server through the user side, and the server sends a search result to the user side. In order to improve the browsing efficiency of the user, the search results meeting the preset conditions can be screened from the plurality of search results, and the screened search results are displayed in a special format, so that the user can conveniently check the screened search results.

For the search requests of the search results, the search requests are generally sent to the user terminal corresponding to the field to which the search request belongs directly according to the field to which the search request belongs, and the user terminal produces the search requests.

Disclosure of Invention

The embodiment of the disclosure at least provides an information processing method and device.

In a first aspect, an embodiment of the present disclosure provides an information processing method, including:

acquiring a plurality of pieces of search information generated in a preset time period;

determining search information to be produced based on the plurality of pieces of search information; the search result corresponding to the search information to be produced does not accord with the preset condition;

determining production demand information corresponding to the search information to be produced, wherein the production demand information is used for representing the demand type of the search result to be produced corresponding to the search information;

and sending the search information to be produced to a target user side matched with the production demand information.

In one possible implementation manner, the search information having the target search result meeting the preset condition carries target tag information, and the target tag information is generated in advance;

the method further comprises the following steps: generating the target tag information according to the following steps:

aiming at any piece of search information, determining a plurality of search results corresponding to the piece of search information;

determining a first importance of each search result based on first interactive information corresponding to each search result;

and if the search result with the highest first importance degree is compared with other search results in the plurality of search results and meets a preset difference condition, generating target label information for the search information.

In a possible embodiment, the determining search information to be produced based on the plurality of pieces of search information includes:

determining first search information and second search information from the plurality of pieces of search information;

determining the search information to be produced based on the first search information and the second search information;

the first search information is search information without a target search result, and the target search result is a search result meeting the preset condition; the second search information is search information which has a target search result but does not meet a target condition;

the target search result not satisfying the target condition comprises:

the target search result has a risk, and/or the second interaction information corresponding to the target search result does not accord with a preset interaction condition.

In a possible implementation, the second interaction information includes at least one of the following information:

the page dwell time, the click rate, and the difference between the click times of the target search result corresponding to the second search information and the click times of the other search results corresponding to the second search information except the target search result.

screening out first search information without a target search result from the plurality of pieces of search information;

performing coverage intention judgment on the first search information, and determining a coverage intention judgment result; the coverage intention judgment result is used for indicating whether the target search result corresponding to the first search information needs to be covered;

and if the covering intention judgment result indicates that the target search result corresponding to the first search information needs to be covered, determining the first search information as the search information to be produced.

In a possible embodiment, the determining production demand information corresponding to the search information to be produced includes:

inputting the search information to be produced into a sensitive information detection model trained in advance, and determining a detection result corresponding to the search information to be produced;

and when the detection result corresponding to the search information to be produced does not contain sensitive information, determining the production demand information corresponding to the search information to be produced.

In a possible implementation manner, the inputting the search information to be produced into a sensitive information detection model trained in advance, and determining a detection result corresponding to the search information to be produced includes:

inputting the search information to be produced into a sensitive information detection model trained in advance, and outputting to obtain the probability that the search information to be produced contains sensitive information;

when the probability is larger than a first preset value, determining that a detection result corresponding to the search information to be produced contains sensitive information; when the probability is greater than a second preset value and is less than or equal to the first preset value, determining whether a detection result corresponding to the search information to be produced is to be verified to contain sensitive information; and when the probability is smaller than or equal to the second preset value, determining that the detection result corresponding to the search information to be produced does not contain sensitive information.

In a possible embodiment, the sending the search information to be produced to the target user side matched with the production demand information includes:

determining interaction parameters and attribute information respectively corresponding to the search information to be produced;

determining a second importance of each piece of search information to be produced based on the interactive parameters and the attribute information respectively corresponding to the search information to be produced;

and determining priority information of the search information to be produced based on the second importance of each piece of the search information to be produced, and sending the search information to be produced to a corresponding target user side matched with the production demand information of the search information to be produced according to the priority information.

In one 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 search times corresponding to the first search information, and the attribute information corresponding to the search information to be produced includes stability information and/or production demand information of the first search information;

when the search information to be produced comprises second search information, the interaction parameter corresponding to the search information to be produced comprises the browsing times of a target search result corresponding to the second search information, and the attribute information corresponding to the search information to be produced comprises stability information and/or production demand information of the first search information;

the stability information is used for representing that the probability that the value of the interactive parameter in the preset time length of the search information to be produced from the current time to the later time is higher than the probability that the value of the interactive parameter in the preset time length of the search information to be produced from the current time to the earlier time is higher than the probability that the value of the interactive parameter in the preset time length of the search information to be produced from the later time to the earlier time; the production demand information is used for representing the demand type of the search result to be produced corresponding to the search information to be produced.

In a possible embodiment, the determining the second importance of each piece of search information to be produced based on the interaction parameter and the attribute information respectively corresponding to the search information to be produced includes:

taking the interactive parameters of the search information to be produced as initial importance;

and adjusting the initial importance degree based on the attribute information and a preset adjusting rule to obtain a second importance degree of the search information to be produced.

In a possible implementation manner, the stability information of the search information to be generated is obtained based on a pre-trained neural network model;

the method further comprises training the neural network model according to the following method:

obtaining sample search information within a preset time length, feature information corresponding to the sample search information and a stability label corresponding to the sample search information, wherein the sample search information has a corresponding target search result, and the stability label corresponding to the sample search information is used for indicating whether the value of an interaction parameter of the sample search information is stable or not;

inputting characteristic information corresponding to the sample search information and interactive parameters corresponding to the sample search information into a neural network model to be trained, and outputting to obtain a predicted value of the interactive parameters in the preset time length of the sample search information from the current time, wherein the predicted probability is higher than the prediction probability of the value of the interactive parameters in the preset time length of the sample search information from the current time to the front;

training the neural network model based on the prediction probabilities and the stability labels.

In one possible embodiment, the characteristic information corresponding to the sample search information includes at least one of the following information:

the word vector corresponding to the sample search information, the word vector of at least one query request of the target search results corresponding to the sample search information, the ordering information of the target search results corresponding to the sample search information under different query requests, and the uniform resource locator of the target search results corresponding to the sample search information.

In one possible embodiment, the target user end matched with the production demand information is determined according to the following steps:

determining attribute information of each candidate user side based on production demand information corresponding to a historical search result generated by each candidate user side;

and determining the target user side from each candidate user side based on the production demand information corresponding to the target search information and the attribute information of each candidate user side.

In a possible embodiment, after sending the search information to be produced to the target user terminal, the method further includes:

acquiring production state information of search information to be produced distributed to the target user side;

determining a second importance degree of the search information to be produced under the condition that the production state information is in an unclaimed state or a claimed unproductive state and time information corresponding to the production state information meets a preset condition;

when the second importance is smaller than a preset value, determining a difficulty coefficient of the search information to be produced based on historical production state information of the search information to be produced;

and redistributing the search information to be produced based on the difficulty coefficient of the search information to be produced.

In a possible embodiment, the determining the difficulty coefficient of the search information to be produced based on the historical production state information of the search information to be produced includes:

and determining the difficulty coefficient of the search information to be produced based on the corresponding times of unclassified and unproductive times after being claimed when the search information is distributed to different user terminals.

In a possible embodiment, the redistributing the search information to be produced based on the difficulty coefficient of the search information to be produced includes:

adjusting the quantity of virtual resources corresponding to the search information to be produced according to a preset resource adjustment rule based on the difficulty coefficient of the search information to be produced;

and sending the search information to be produced and indication information indicating the number of the adjusted virtual resources to other user sides matched with the search information to be produced so that the other user sides can obtain the corresponding number of virtual resources after generating target search results which correspond to the search information to be produced and meet preset conditions.

and determining the priority information of the search information to be produced based on the second importance of each piece of the search information to be produced again, and sequentially sending the search information to be produced to a preset user side according to the priority information.

In a second aspect, an embodiment of the present disclosure further provides an information processing apparatus, including:

the acquisition module is used for acquiring a plurality of pieces of search information generated in a preset time period;

the first determining module is used for determining the search information to be produced based on the plurality of pieces of search information; the search result corresponding to the search information to be produced does not accord with the preset condition;

the second determining module is used for determining production demand information corresponding to the search information to be produced, wherein the production demand information is used for representing the demand type of the search result to be produced corresponding to the search information;

and the sending module is used for sending the search information to be produced to a target user side matched with the production demand information.

the apparatus further comprises a generation module configured to generate the target tag information according to the following steps:

In one possible embodiment, the first determining module, when determining the search information to be produced based on the plurality of pieces of search information, is configured to:

the target search result not satisfying the target condition comprises:

In a possible implementation manner, when determining the production demand information corresponding to the search information to be produced, the second determining module is configured to:

In a possible implementation manner, when the search information to be produced is input to a sensitive information detection model trained in advance, and a detection result corresponding to the search information to be produced is determined, the second determining module is configured to:

In a possible implementation manner, when sending the search information to be produced to the target user side matched with the production demand information, the sending module is configured to:

In a possible implementation manner, when determining the second importance of each piece of search information to be produced based on the interaction parameter and the attribute information respectively corresponding to the search information to be produced, the sending module is configured to:

the apparatus further comprises a training module for training the neural network model according to the following method:

In a possible implementation manner, the sending module is configured to determine the target user side matching the production demand information according to the following steps:

In a possible implementation manner, the sending module is further configured to:

after the search information to be produced is sent to a target user side, obtaining production state information of the search information to be produced distributed to the target user side;

In a possible implementation manner, the sending module, when determining the difficulty coefficient of the search information to be produced based on the historical production state information of the search information to be produced, is configured to:

In a possible implementation manner, when the search information to be generated is re-allocated based on the difficulty coefficient of the search information to be generated, the sending module is configured to:

In a third aspect, an embodiment of the present disclosure further provides a computer device, including: a processor, a memory and a bus, the memory storing machine-readable instructions executable by the processor, the processor and the memory communicating 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 described above, or any possible implementation of the first aspect.

In a fourth aspect, this disclosed embodiment also provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to perform the steps in the first aspect or any one of the possible implementation manners of the first aspect.

According to the information processing method and device provided by the embodiment of the disclosure, search information to be generated, which needs to be allocated to a user side for corresponding target search result production, can be determined according to a plurality of pieces of acquired search information, and then production demand information corresponding to the search information to be generated is determined, wherein the production demand information comprises a demand type of a target search result to be generated by the user aiming at the target search information; then, the target search information can be sent to the target user side matched with the production demand information, so that the target search result produced by the target user side selected based on the production demand information is more accurate and meets the user demand more easily.

In order to make the aforementioned objects, features and advantages of the present disclosure more comprehensible, preferred embodiments accompanied with figures are described in detail below.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings required for use in the embodiments will be briefly described below, and the drawings herein incorporated in and forming a part of the specification illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the technical solutions of the present disclosure. It is appreciated that the following drawings depict only certain embodiments of the disclosure and are therefore not to be considered limiting of its scope, for those skilled in the art will be able to derive additional related drawings therefrom without the benefit of the inventive faculty.

Fig. 1 shows a flowchart of an information processing method provided by an embodiment of the present disclosure;

fig. 2 shows a flowchart of a target tag information generation method provided by an embodiment of the present disclosure;

FIG. 3 illustrates a flowchart of a training method for an overlay intent determination model provided by an embodiment of the present disclosure;

FIG. 4 is a schematic diagram illustrating a process for determining production requirement information provided by an embodiment of the present disclosure;

fig. 5 is a flowchart illustrating a method for sending search information to be generated according to an embodiment of the present disclosure;

FIG. 6 is a flow chart of a neural network model training method provided by an embodiment of the present disclosure;

fig. 7 is a schematic diagram illustrating a second importance determination method provided by an embodiment of the present disclosure;

fig. 8 is a schematic diagram illustrating an architecture of an information processing apparatus according to an embodiment of the present disclosure;

fig. 9 shows a schematic structural diagram of a computer device 900 provided by an embodiment of the present disclosure.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present disclosure more clear, the technical solutions of the embodiments of the present disclosure will be described clearly and completely with reference to the drawings in the embodiments of the present disclosure, and it is obvious that the described embodiments are only a part of the embodiments of the present disclosure, not all of the embodiments. The components of the embodiments of the present disclosure, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present disclosure, presented in the figures, is not intended to limit the scope of the claimed disclosure, but is merely representative of selected embodiments of the disclosure. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the disclosure without making creative efforts, shall fall within the protection scope of the disclosure.

In the related art, when a search request without a search result meeting a preset condition is distributed to each user terminal, generally, a field (for example, may include food, medicine, electronics, service, and the like) to which target search information belongs is determined, and then the user terminal is selected for the target search information according to the field to which the target search information belongs, however, this method may not meet the user's requirement.

For example, if the target search information is "video details of cooking with braised pork", the domain to which the target search information belongs may be determined to be "food" by the related technology, and then the target search information is sent to the user side capable of producing the target search result in the "food" domain, however, the user requirement corresponding to the target search information is a video of food, and if the sent user side cannot produce the video type target search result, the target search result produced by the user side finally cannot meet the user requirement.

Based on this, the embodiment of the present disclosure provides an information processing method and apparatus, which may determine, according to a plurality of pieces of acquired search information, to-be-generated search information that needs to be allocated to a user side for corresponding target search result production, and then determine production demand information corresponding to the to-be-generated search information, where the production demand information includes a demand type of a target search result to be generated by a user for the target search information; then, the target search information can be sent to the target user side matched with the production demand information, so that the target search result produced by the target user side selected based on the production demand information is more accurate and meets the user demand more easily.

The above-mentioned drawbacks are the results of the inventor after practical and careful study, and therefore, the discovery process of the above-mentioned problems and the solutions proposed by the present disclosure to the above-mentioned problems should be the contribution of the inventor in the process of the present disclosure.

It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.

For the convenience of understanding of the present embodiment, first, an information processing method disclosed in the embodiments of the present disclosure is described in detail, and an execution subject of the information processing method provided in the embodiments of the present disclosure is generally an electronic device with certain computing capability, for example, a server. The following describes an information processing method provided by the embodiment of the present disclosure, taking an execution subject as a server as an example.

Referring to fig. 1, a flowchart of an information processing method provided in an embodiment of the present disclosure is shown, where the method includes the following steps:

step 101, obtaining a plurality of pieces of search information generated in a latest preset time period.

Step 102, determining search information to be produced based on the plurality of pieces of search information; and the search result corresponding to the search information to be produced does not accord with the preset condition.

103, determining production demand information corresponding to the search information to be produced, wherein the production demand information is used for representing a demand type of a search result to be produced corresponding to the search information.

And 104, sending the search information to be produced to a target user side matched with the production demand information.

The following is a detailed description of the above steps 101 to 104.

For step 101,

In a possible implementation manner, the obtaining of the plurality of pieces of search information generated within the latest preset time period may be obtaining a plurality of search requests generated within a time range in which a specific current time is a preset time duration, and then extracting the search information from each search request.

The obtained search requests may be search requests received by the current search platform, or search requests received by the current search platform and other search platforms, where the search platforms include but are not limited to application programs, web pages, and the like.

In practical applications, after a plurality of pieces of search information are acquired, there may be a case where target search results required for part of the search information are the same, for example, target search results corresponding to the search information "how to cook pork in red" and the search information "how to cook pork in red" are the same, so in order to avoid repeated production of the search information by the user side, in one possible implementation, the acquired plurality of pieces of search information may be subjected to deduplication processing first.

When multiple pieces of search information are subjected to deduplication processing, the similarity between any two pieces of search information can be determined through a Vector Space Model (VSM), or word vectors corresponding to any two pieces of search information are determined through word2vec, then the cosine distance between the word vectors is used as the similarity between the two pieces of search information, and if the similarity between the two pieces of search information is larger than a preset value, one piece of search information is selected from the two pieces of search information as the acquired search information.

With respect to step 102,

In practical application, in the search range of the current search platform, the search information with the target search result meeting the preset condition is the search information with the target tag information, the target tag information is generated in advance, and after the search information is obtained, whether the target tag information exists in the search information can be directly determined.

The search result meeting the preset condition may be that the first importance of the search result is the highest, and the search result with the highest first importance meets a preset difference condition compared with other search results in the plurality of search results.

The search result with the highest first importance meets a preset difference condition compared with other search results in the plurality of search results, and may include any one of the following cases:

and in case 1, the difference value between the search result with the highest first importance and the search result with the second highest first importance is greater than a preset difference value.

Specifically, T1-T2> S may be satisfied, where T1 denotes the first importance of the search result with the highest first importance, T2 denotes the first importance of the search result with the second highest first importance, and S denotes a preset difference.

And 2, the ratio of the search result with the highest first importance in the search results with the first importance ranked in the top N is larger than the preset ratio.

Specifically, T1/(T1+ T2+ … + TN) > Z may be satisfied, where T1 represents the first importance of the search result with the highest first importance, T2 represents the first importance of the search result with the second highest first importance, and so on, and Z represents the preset ratio.

In one possible implementation, the target tag information may be generated according to the method shown in fig. 2, including the following steps:

step 201, aiming at any piece of search information, determining a plurality of search results corresponding to the piece of search information.

The search results determined to correspond to the piece of search information may be a plurality of search results corresponding to the piece of search information within a search range of the current search platform. The search result corresponding to the search information may be content including the search information or content including part of the search information; the search range of the current search platform is a range in which the current search platform can acquire data, and for example, data of some websites cannot be queried through the current search platform, and the networks do not belong to the search range of the current search platform.

Step 202, determining a first importance degree corresponding to each piece of search result based on the first interaction information corresponding to each piece of search result.

The first interaction information corresponding to each search result may include click times and/or browsing duration, the first importance degree corresponding to each search result is determined based on the first interaction information corresponding to each search result, and the first importance degree corresponding to each search result may be obtained by performing weighted summation on information included in the first interaction information and taking a result of the weighted summation as the first importance degree corresponding to each search result; when the first interactive information only includes the number of clicks (or only includes the browsing duration), the value of the first interactive information may be directly used as the first importance corresponding to the search result.

Step 203, if the search result with the highest first importance degree is compared with other search results in the plurality of search results and meets a preset difference condition, generating target label information for the search information.

If the search result with the highest first importance degree is compared with other search results in the plurality of search results and meets the preset difference condition, generating target label information for the search information; and if the search result with the highest first importance degree is not in accordance with the preset difference condition compared with other search results in the plurality of search results, not generating target label information for the search information.

Here, the case where the target tag information is not generated for the piece of search information may include two cases, one case is that the piece of search information does not have any tag information, and one case is that the target tag information is not generated for the piece of search information, but other tag information is generated for the piece of search information, for example, the tag "0" may be used to indicate that the search range of the current search platform does not have the target search result, the tag "1" may be used to indicate that the search range of the current search platform has the target search result, and the tag "1" is the target tag information.

When the search information to be produced is determined, first search information and second search information can be screened from a plurality of pieces of acquired search information, and then the search information to be produced is determined based on the first search information and the second search information, wherein the first search information is search information without a target search result, and the target search result is a search result meeting the preset condition; the second search information is search information which has a target search result but does not meet a target condition;

in practical applications, a reason why some search information does not have corresponding target search results meeting preset conditions may be that the quality of the search information itself is low, for example, for the search information "rice is not good and eaten well", because the search information itself is a problem with subjective colors of users, a client producing the search results may not be able to produce corresponding search results after receiving the problem, and the part of the search information may increase unnecessary workload for the client producing the search results. In order to avoid the influence of the part of search information on the user side, the coverage intention judgment can be firstly carried out on the first search information, and then the search information with lower quality is removed.

In one possible implementation, when determining search information to be produced based on a plurality of pieces of search information, first screening out first search information without a target search result from the plurality of pieces of search information, then performing coverage intention judgment on the first search information, and determining a coverage intention judgment result, wherein the coverage intention judgment result is used for indicating whether the target search result corresponding to the first search information needs to be covered; and if the covering intention judgment result indicates that the target search result corresponding to the first search information needs to be covered, determining the first search information as the search information to be produced.

In one possible embodiment, when the coverage intention determination is performed on the first search information, the determination may be performed by a coverage intention determination model trained in advance. Specifically, the first search information may be input into a trained coverage intention determination model, and the coverage intention determination model may process the first search information and output the result of coverage intention determination.

When training the coverage intention determination model for determining the coverage intention, reference may be made to the method for training the coverage intention determination model shown in fig. 3, which includes the following steps:

step 301, obtaining sample search information and a coverage label corresponding to the sample search information, where the coverage label is used to indicate whether the target search result corresponding to the first search information needs to be covered in the search range of the current search platform.

Step 302, inputting the sample search information into a coverage intention judgment model to be trained, and outputting to obtain a coverage intention judgment result.

And step 303, calculating a loss value in the training process based on the coverage intention judgment result and the coverage label of the sample search information.

And step 304, judging whether the loss value in the training process is smaller than a preset loss value.

If yes, go to step 305; if not, adjusting the model parameters of the coverage intention judgment model in the training process, and returning to execute the step 302.

And 305, determining that the training of the coverage intention judgment model is finished, and determining the coverage intention judgment model adopted in the training process as the trained coverage intention judgment model.

The target search result of the search information not satisfying the target condition includes:

When determining whether the target search result has a risk, a Uniform Resource Locator (URL) of the target search result and related information of the target search result (for example, title information of the target search result) may be obtained first, and risk identification may be performed on the target search result based on the URL of the target search result.

Performing risk identification on the target search result based on the URL of the target search result, wherein the risk identification can be used for detecting whether the URL is located in a pre-stored high-risk resource database, and if so, determining that the risk identification result indicates that the target search result has risk; or whether the data can be acquired based on the URL is detected (since part of the data can only be detected but cannot be acquired), and if not, the risk identification result is determined to indicate that the target search result has risk.

For example, if the second search information is "how to do the red-cooked pork", the target search result corresponding to the second search information is an article named "doing the red-cooked pork", but there is a risk in detecting the target search result based on the URL of the target search result, in this case, the second search information is determined as the search information to be produced.

If the risk identification result indicates that the target search result does not have a risk, but a part of the target search result may have poor user experience, in a possible implementation manner, second interaction information corresponding to the target search result may also be determined, and if the second interaction information does not meet a preset interaction condition, tag information to be allocated is allocated to the second search information.

Wherein the second interactive information may include at least one of the following information:

The target search result corresponding to the second interactive information does not meet the preset interactive condition, and the value of any item of information in the second interactive information may not be in the value range corresponding to the item of information.

If the second interaction information meets the preset interaction condition, the user experience of the target search result corresponding to the second search information is better, and in this case, the target search result may not be changed.

In a specific implementation, when determining search information to be produced based on the first search information and the second search information, the first search information and the second search information indicating that the coverage intention determination result needs to cover the target search result corresponding to the first search information may be determined as the search information to be produced.

For step 103,

In a possible implementation manner, before determining the production demand information corresponding to the search information to be produced, sensitive information detection may be performed on the search information to be produced first.

Specifically, the search information to be produced may be input into a sensitive information detection model trained in advance, a detection result corresponding to the search information to be produced is determined, and when the detection result corresponding to the search information to be produced does not include sensitive information, production demand information corresponding to the search information to be produced is determined.

After the search information to be produced is input into the sensitive information detection model trained in advance, the probability that the search information to be produced contains the sensitive information is output, and then the detection result corresponding to the search information to be produced is determined according to the probability that the search information to be produced contains the sensitive information, which specifically includes the following conditions:

and in case 1, the probability of the sensitive information is greater than a first preset value.

When the probability of the sensitive information is greater than a first preset value, the detection result corresponding to the search information to be produced can be determined to be sensitive information.

And 2, outputting the obtained probability containing the sensitive information to be less than or equal to a second preset value, wherein the second preset value is less than the first preset value.

In this case, it may be determined that the detection result corresponding to the search information to be produced does not contain sensitive information.

And in case 3, the probability of the sensitive information is greater than the second preset value and less than or equal to the first preset value.

In this case, it is described that the search information to be produced may or may not contain sensitive information, and therefore, in order to improve the accuracy of the detection result of the search information to be produced, the detection result of the search information to be produced may be determined as whether or not sensitive information is contained to be verified.

For the case 3, when the detection result of the search information to be produced is to check whether the search information to be produced includes sensitive information, a sensitive information confirmation instruction carrying the search information to be produced and the detection result may be sent to the server, and then the detection result of whether the search information to be checked includes sensitive information is updated according to the feedback result of the server, where the updated detection result is that the search information includes sensitive information, or the search information does not include sensitive information.

The server can be a user side of a maintainer of the current search platform.

Specifically, when updating is performed according to the feedback result of the server, if the feedback result of the server is that sensitive information is included, the detection result corresponding to the search information to be generated is updated to include the sensitive information; and if the feedback result of the server side does not contain the sensitive information, updating the detection result corresponding to the search information to be generated to be not containing the sensitive information.

When the sensitive information detection model is in a training process, sample search information and sensitive marking information of the sample search information can be obtained firstly, the sensitive marking information is used for indicating whether the sample search information contains sensitive information or not, then the sample search information is input into the sensitive information detection model, the probability that the sample search information contains the sensitive information is output, and a detection result corresponding to the sample search information is determined according to the probability that the sample search information contains the sensitive information; and then determining a loss value in the training process based on a detection result corresponding to the sample searching information and sensitive marking information corresponding to the sample searching information, and re-executing the training process under the condition that the loss value does not meet a preset condition.

The production demand information corresponding to the search information to be produced may include at least one of the following information:

domain information, required format information, whether a professional is required to answer, and whether an encyclopedia page needs to be generated.

Illustratively, the domain information may include food, medicine, electronics, farming, planting, etc., and the desired format information may include video format, audio format, text format, picture format, etc.

In a possible implementation manner, when the production demand information corresponding to the search information to be produced is determined, the search information to be produced may be input into a pre-trained user demand detection model, the user demand detection model may output a probability value corresponding to each type of production demand information corresponding to the search information to be produced, and then the production demand information corresponding to the search information to be produced is determined according to the probability value.

Illustratively, if the production demand information includes the domain information, after the search information to be produced is input into the pre-trained user demand detection model, the user demand detection model may output a probability that the search information to be produced belongs to the food domain, a probability that the search information to be produced belongs to the medical domain, a probability that the search information belongs to the electronic domain, a probability that the search information to be produced belongs to the breeding domain, and a probability that the search information to be produced belongs to the planting domain.

Because the precision of the user demand detection model is limited, in order to improve the precision of determining the production demand information corresponding to the search information to be produced, in a possible implementation manner, after the production demand information corresponding to the search information to be produced is determined based on the user demand detection model, the search information to be produced and the production demand information corresponding to the determined search information to be produced can be sent to a server, a worker audits the production demand information of the search information to be produced, if the audit is passed, the worker can feed back an audit passing instruction through the server, and after the server receives the audit passing instruction, the server directly determines the production demand information determined by the user demand detection model as the production demand 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 instruction of the audit not passed to the server, after the server receives the instruction of the audit not passed, re-inputting the search information to be produced into the user demand detection model, and re-determining the production demand information of the search information to be produced.

In another possible implementation manner, in order to reduce the task load of the staff, the search information to be produced and the production demand information of the search information to be produced, which are output by the user demand detection model and have probability values corresponding to each type of production demand information corresponding to the search information to be produced that do not meet the preset conditions, may also be sent to the server.

In a possible implementation manner, when determining the production demand information corresponding to the search information to be produced, the search information to be produced may be labeled, as shown in fig. 4, different production demand information may correspond to a label having an attribute, for example, the domain information may correspond to a domain label, the format information required may correspond to a resource form label, whether a professional is required to answer the label that can be judged by corresponding resource authority, whether it is necessary to generate an encyclopedia page that can correspond to a resource satisfaction tendency label, 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 label according to the four types of labels, and then label the search information to be produced, which is input in fig. 4, the label corresponding to the search information to be produced is a movie and television demand label (the domain information is a movie and television), and the method for determining the format information to be produced may include the resource form label, and the method for determining the search, The method comprises the steps of generating a video demand label (required format information is in a video format), an expert demand label (required by a professional to answer), and an encyclopedia demand label (required to generate an encyclopedia page), and then sending search information to be produced to a user side according to the label of the search information to be produced.

With respect to step 104,

In practical applications, when there is a lot of search information to be processed and to be produced, some important search information to be produced may not be processed in time due to limited production capability of the user side. Therefore, before sending the search information to be produced to the target user side matched with the production demand information, the priority of each search information to be produced can be determined.

Specifically, the search information to be generated may be sent according to the method shown in fig. 5, which includes the following steps:

step 501, determining interaction parameters and attribute information respectively corresponding to the search information to be produced.

Step 502, determining a second importance of each piece of search information to be produced based on the interaction parameters and the attribute information respectively corresponding to the search information to be produced.

Step 503, determining priority information of each piece of search information to be produced based on the second importance of the search information to be produced, and sending the search information to be produced to a corresponding target user side matched with the production demand information of the search information to be produced according to the priority information.

When determining the interactive parameters and the attribute information corresponding to the search information to be produced respectively, different second interactive information and attribute information can be determined according to the type of the search information to be produced, and the following two situations can be specifically distinguished:

case 1, the search information to be generated 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 search times 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 the 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.

For example, the stability information may indicate a probability that the sum of the number of times the first search information is searched for in the last 7 days is higher than the sum of the number of times the first search information is searched for in the previous 7 days.

The stability information of the search information to be generated is obtained based on a pre-trained neural network model; in training the neural network model, reference may be made to the method shown in fig. 6, which includes the following steps:

step 601, obtaining sample search information within a preset time length, feature information corresponding to the sample search information, and a stability label corresponding to the sample search information, where the sample search information has a corresponding target search result, and the stability label corresponding to the sample search information is used to indicate whether a value of an 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:

At least one query request of the target search results corresponding to the sample search information is a request that the target search results can be queried through the query request, illustratively, the target search results corresponding to the sample search information are articles named as "red-cooked meat practice", the query request corresponding to the target search results can be articles named as "red-cooked meat practice", "red-cooked meat is good, and" family version red-cooked meat practice ", and the like, and the articles named as" red-cooked meat practice "can be found through the query requests.

The ranking information of the target search results corresponding to the sample search information under different query requests is ranking of the search results of the ' red-cooked meat practice ' in the search results of the query requests such as ' how to do red-cooked meat ', ' how well to do red-cooked meat and ' family version red-cooked meat practice ', and if the search results are the target search results corresponding to the search request of ' how to do red-cooked meat ', the ranking information of the search results under the query request of ' how to do red-cooked meat ' is 1.

Step 602, inputting the feature 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 a predicted value of the interaction parameter within the preset time period after the current time of the sample search information, wherein the predicted probability is higher than the predicted probability of the value of the interaction parameter within the preset time period before the current time of the sample search information.

Step 603, training the neural network model based on the prediction probability and the stability label.

Specifically, when the neural network model is trained based on the prediction probability and the stability label, a loss value in the current training process may be determined based on the prediction probability and the stability label, and then a model parameter value in the neural network model may be adjusted based on the loss value.

After the training of the neural network model is completed, when prediction is performed based on the neural network model, search information to be produced can be directly input into the neural network model, and the value of the interaction parameter within the preset time length from the current time to the back of the search information to be produced can be output, so that the probability that the value of the interaction parameter within the preset time length from the current time to the front of the information to be screened is higher than that of the interaction parameter within the preset time length from the current time.

When the second importance of each piece of search information to be produced is determined based on the interaction parameters and the attribute information respectively corresponding to the 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 a preset adjustment rule to obtain the second importance of the search information to be produced.

The adjustment rule may be a preset rule, for example, as shown in fig. 7, 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 can be adjusted according to the tag of the search information to be produced, for example, when the search information to be produced carries the target tag, the initial importance can be increased by d times.

If the value of the stability information of a certain search information to be generated is greater than a, the search information to be generated is first search information, the search information to be generated carries target tag information, and the value of the interaction parameter is p, when the second importance of the search information to be generated is calculated, the second importance is p (1+ a) × (1+ b) × (1+ c).

The priority information of the search information to be produced is determined based on the second importance of each piece of search information to be produced, and the search information to be produced can be ranked based on the second importance of each piece of search information to be produced, and the priority information is a ranking result of the search information to be produced; when the search information to be produced is sent to the target user side according to the priority information, the search information to be produced, which is arranged at the top N positions, can be selected each time, then the search information to be produced, which is arranged at the top N positions, is sent to the corresponding target user side respectively, then the remaining search information to be produced is sorted again, the search information to be produced, which is arranged at the top N positions, is selected and sent to the corresponding target user side, and so on, wherein N is a positive integer.

When the target user side matched with the production demand information of the search information to be produced is determined, the attribute information of each preset user side can be determined based on the demand information corresponding to the historical search result generated by each preset user side, and then the target user side matched with the production demand information of the search information to be produced is determined based on the production demand information corresponding to the search information to be produced and the attribute information of each preset user side.

When determining the attribute information of each candidate user side based on the production demand information corresponding to the historical search result generated by each candidate user side, the value of each item of production demand information in the production demand information corresponding to the historical search result generated by each candidate user side can be counted, and then the production demand information of which the corresponding value is higher than the preset value is used as the attribute information of each candidate user side.

For example, if the production requirement information (including the domain information and the format information required by the historical search result) corresponding to the historical target search result generated by the candidate user side is shown in the following tables 1 and 2:

TABLE 1

Information of the field	Number of historical target search results
		Food	200
Medical science	0
		Electronic device	0
Cultivation of fish	2
		Planting	150

TABLE 2

If the preset value corresponding to the information of the belonging field is 100 and the preset value corresponding to the format information of the historical search result is 20, the attribute information of the candidate user side comprises 'food', 'cultivation', and 'text format', and if the production demand information corresponding to the search information to be produced comprises 'food' and 'text format', the candidate user side can be used as a target user side, and the search information to be produced is sent to the target user side.

In a possible implementation manner, when a target user side is determined from each candidate user side based on production demand information corresponding to search information to be produced and attribute information of each candidate user side, the candidate user side whose corresponding attribute information matches the production demand information corresponding to the search information to be produced may be selected as the target user side, if a plurality of the determined target user sides are provided, one target user side may be randomly selected, and then the search information to be produced is sent to the selected target user side.

When determining the attribute information of the candidate user side, the attribute information may be determined based on the attribute information of the content published by the candidate user side on the search platform.

In another embodiment of the present application, each user terminal may further modify (including adding, deleting, and changing) attribute information manually, for example, if the attribute information of a certain user terminal includes "food", and if the user deletes the attribute information of "food" manually, the user terminal will not be assigned with corresponding requirement information including search information of "food".

In another possible implementation manner, in order to balance the workload of each user side, when a target user side is determined from each candidate user side based on the production demand information corresponding to the search information to be produced and the attribute information of each candidate user side, the user side to be screened may be determined from each candidate user side based on the production demand information corresponding to the search information to be produced and the attribute information of each candidate user side, and then the target user side is screened from the user sides to be screened based on the number of currently unfinished tasks of each user side to be screened, where the number of unfinished tasks is the number of search information of the target search result to be generated.

In another embodiment of the present disclosure, after the search information to be produced is sent to the target user side, the production condition of each target user side can be monitored.

Specifically, after the search information to be produced is sent to the target user side, the production state information of the search information allocated to the target user side can be acquired, when the production state information is in an unclaimed state or a claimed unproductive state and time information corresponding to the production state information meets a preset condition, a second importance degree of the search information to be produced is determined, then when the second importance degree is smaller than the preset value, a difficulty coefficient of the search information to be produced is determined based on historical production state information of the search information to be produced, and the search information to be produced is allocated again based on the difficulty coefficient of the search information to be produced.

The time information corresponding to the production state information meeting the preset condition may include the following two cases:

in case 1, after the search information to be generated is distributed to the target user side, the state information corresponding to the search information to be generated is in an unclaimed state, and if a claim instruction sent by the target user side is not received within a first preset time period, it is determined that the time information corresponding to the production state information of the search information to be generated meets a preset condition.

And 2, after the search information to be produced is distributed to the target user side, if the status information of the search information to be produced is updated to claim unproduction after a claim instruction of the target user side is received, and if a target search result which is sent by the target user side and is produced based on the search information to be produced is not received within a second preset time length after the claim instruction of the target user side is received, determining that the time information corresponding to the production status information of the search information to be produced meets a preset condition.

In another possible implementation manner, the target user side may further send a delay request for indicating delay processing to the server, and after receiving the delay request, the server may determine, within a third preset time period after receiving a claim instruction of the target user side, that the time information corresponding to the production state information of the search information to be produced satisfies a preset condition if a target search result, which is sent by the target user side and is produced based on the search information to be produced, is not received. And the third preset time length is greater than the second preset time length.

Because the second importance of different search information to be produced is different, the search information to be produced with higher second importance may need to be allocated to other clients as soon as possible, and because certain time needs to be consumed for determining the difficulty coefficient, in order to improve the processing efficiency of the search information to be produced with higher second importance, the search information to be produced can be directly sent to other clients matched with the search information to be produced; some search information to be generated with a second importance that is not very high may not be able to generate corresponding target search results after being distributed to other clients due to the difficulty of the search information itself.

For the two possible situations, in one possible implementation, when determining the difficulty coefficient of the search information to be produced based on the historical production state information of the search information to be produced, the second importance degree corresponding to the search information to be produced may be determined first, and when the second importance degree is smaller than a preset value, the difficulty coefficient of the search information to be produced may be determined based on the historical production state information of the search information to be produced.

The method for determining the second importance of the search information to be generated is the same as the method for determining the second importance, and will not be described herein again.

It should be noted that, when the search information to be generated is distributed to any ue, since the second importance of the search information to be generated is determined according to the interaction parameter and the attribute information corresponding to the search information to be generated, and the interaction parameter corresponding to the search information may change during the period from the time the search information is distributed to the previous ue to the time the search information is distributed to the current ue, the second importance of the search information to be generated needs to be determined again when the search information to be generated is redistributed to any ue.

When the difficulty coefficient of the search information to be produced is determined based on the historical production state information of the search information to be produced, the difficulty coefficient of the search information to be produced may be determined based on the corresponding unclaimed times when the search information to be produced is distributed to different clients and the unclaimed times after the search.

For the same piece of search information to be produced, the search information to be produced may be allocated to one user side at a time, the unclaimed times may be times that the search information to be produced is not claimed after being sequentially allocated to different user sides, and the unclaimed times may be times that the search information to be produced is claimed but not produced after being sequentially allocated to different user sides.

Illustratively, if a search information to be generated is assigned to a, but a does not claim the search information to be generated, then is assigned to b again, but b does not claim, then is assigned to c again, c claims but is not generated, the number of times that the search information to be generated is not claimed is two, and the number of times that the search information is not generated after being claimed is one.

When determining the difficulty factor of the search information to be produced based on the corresponding unclaimed times and unclaimed times when the search information to be produced is distributed to different user terminals, the calculation may be performed by referring to the following formula:

P＝2x+y

wherein p represents the difficulty coefficient corresponding to the search information to be produced, x represents the times that the search information to be produced is not claimed, and y represents the times that the search information to be produced is not produced after being claimed.

In another example, when the difficulty coefficient of the search information to be produced is determined based on the corresponding unclaimed times and the corresponding unclaimed times after being claimed when the search information to be produced is distributed to different user terminals, the unclaimed times and the unclaimed times after being claimed may be weighted and summed according to preset weights, and the summed result is used as the difficulty coefficient corresponding to the search information to be produced.

When the search information to be produced is distributed again based on the difficulty coefficient of the search information to be produced, the number of virtual resources corresponding to the search information to be produced can be adjusted according to a preset resource adjustment rule based on the difficulty coefficient of the search information to be produced, and then the search information to be produced and indication information indicating the adjusted number of virtual resources are sent to other user sides except for the target user side matched with the search information to be produced, so that the virtual resources in corresponding number are obtained after the other user sides generate target search results corresponding to the search information to be produced and meeting preset conditions.

The virtual resource may be a privilege, virtual currency, red envelope, etc.

In specific implementation, the difficulty level corresponding to the search information to be produced may be determined according to the difficulty coefficient of the search information to be produced, and then the number of virtual resources corresponding to the search information to be produced may be adjusted to the number matching the difficulty level.

In another embodiment of the application, when the determined second importance of the search information to be produced is greater than or less than a preset value, other clients, except the target client, matched with the search information to be produced can be directly determined, and then the search information to be produced is sent to the other clients.

In a possible application scenario, the reason that the production state information is an unclaimed state or a claimed unproductive state may be that the user forgets to claim or claim to forget to produce, so in another example of the present application, when the production state information is an unclaimed state or a claimed unproductive state and the time information corresponding to the production state information does not satisfy the preset condition, sending a reminding message to the first user end to remind the first user end to process the search information to be produced.

According to the information processing method provided by the embodiment of the disclosure, search information to be generated, which needs to be allocated to a user side for corresponding target search result production, can be determined according to a plurality of pieces of acquired search information, and then production demand information corresponding to the search information to be generated is determined, wherein the production demand information comprises a demand type of a target search result to be generated by the user aiming at the target search information; then, the target search information can be sent to the target user side matched with the production demand information, so that the target search result produced by the target user side selected based on the production demand information is more accurate and meets the user demand more easily.

It will be understood by those skilled in the art that in the method of the present invention, the order of writing the steps does not imply a strict order of execution and any limitations on the implementation, and the specific order of execution of the steps should be determined by their function and possible inherent logic.

Based on the same inventive concept, an information processing apparatus corresponding to the information processing method is also provided in the embodiments of the present disclosure, and because the principle of the apparatus in the embodiments of the present disclosure for solving the problem is similar to the information processing method described above in the embodiments of the present disclosure, the implementation of the apparatus may refer to the implementation of the method, and repeated details are not described again.

Referring to fig. 8, which is a schematic diagram of an architecture of an information processing apparatus according to an embodiment of the present disclosure, the apparatus includes: an acquisition module 801, a first determination module 802, a second determination module 803, a sending module 804, a generation module 805, and a training module 806; wherein the content of the first and second substances,

an obtaining module 801, configured to obtain multiple pieces of search information generated within a preset time period;

a first determining module 802, configured to determine search information to be produced based on the plurality of pieces of search information; the search result corresponding to the search information to be produced does not accord with the preset condition;

a second determining module 803, configured to determine production demand information corresponding to the search information to be produced, where the production demand information is used to indicate a demand type of a search result to be produced corresponding to the search information;

a sending module 804, configured to send the search information to be produced to a target user side matched with the production demand information.

the apparatus further comprises a generating module 805 configured to generate the target tag information according to the following steps:

In one possible implementation, the first determining module 802, when determining the search information to be produced based on the plurality of pieces of search information, is configured to:

the target search result not satisfying the target condition comprises:

In a possible implementation manner, when determining the production demand information corresponding to the search information to be produced, the second determining module 803 is configured to:

In a possible implementation manner, when the search information to be produced is input to a sensitive information detection model trained in advance, and a detection result corresponding to the search information to be produced is determined, the second determining module 803 is configured to:

In a possible implementation manner, the sending module 804, when sending the search information to be produced to the target user side matched with the production demand information, is configured to:

In a possible implementation manner, when determining the second importance of each piece of search information to be produced based on the interaction parameter and the attribute information respectively corresponding to the search information to be produced, the sending module 804 is configured to:

the apparatus further comprises a training module 806, the training module 806 configured to train the neural network model according to the following method:

In a possible implementation manner, the sending module 804 is configured to determine the target user end matching the production demand information according to the following steps:

In a possible implementation manner, the sending module 804 is further configured to:

In a possible implementation manner, the sending module 804, when determining the difficulty coefficient of the search information to be produced based on the historical production state information of the search information to be produced, is configured to:

In a possible implementation manner, the sending module 804, when re-allocating the search information to be produced based on the difficulty coefficient of the search information to be produced, is configured to:

The description of the processing flow of each module in the device and the interaction flow between the modules may refer to the related description in the above method embodiments, and will not be described in detail here.

Based on the same technical concept, the embodiment of the application also provides computer equipment. Referring to fig. 9, a schematic structural diagram of a computer device 900 provided in the embodiment of the present application includes a processor 901, a memory 902, and a bus 903. The memory 902 is used for storing execution instructions, and includes a memory 9021 and an external memory 9022; the memory 9021 is also referred to as an internal memory, and is configured to temporarily store operation data in the processor 901 and data exchanged with an external memory 9022 such as a hard disk, the processor 901 exchanges data with the external memory 9022 through the memory 9021, and when the computer device 900 is operated, the processor 901 communicates with the memory 902 through the bus 903, so that the processor 901 executes the following instructions:

The embodiments of the present disclosure also provide a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to perform the steps of the information processing method described in the above method embodiments. The storage medium may be a volatile or non-volatile computer-readable storage medium.

The computer program product of the information processing method provided in the embodiments of the present disclosure includes a computer-readable storage medium storing a program code, where instructions included in the program code may be used to execute steps of the information processing method described in the above method embodiments, which may be referred to specifically for the above method embodiments, and are not described herein again.

The embodiments of the present disclosure also provide a computer program, which when executed by a processor implements any one of the methods of the foregoing embodiments. The computer program product may be embodied in hardware, software or a combination thereof. In an alternative embodiment, the computer program product is embodied in a computer storage medium, and in another alternative embodiment, the computer program product is embodied in a Software product, such as a Software Development Kit (SDK), or the like.

It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the system and the apparatus described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again. In the several embodiments provided in the present disclosure, it should be understood that the disclosed system, apparatus, and method may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some communication interfaces, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed 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 can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present disclosure may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into 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 the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present disclosure. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.

Finally, it should be noted that: the above-mentioned embodiments are merely specific embodiments of the present disclosure, which are used for illustrating the technical solutions of the present disclosure and not for limiting the same, and the scope of the present disclosure is not limited thereto, and although the present disclosure is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive of the technical solutions described in the foregoing embodiments or equivalent technical features thereof within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present disclosure, and should be construed as being included therein. Therefore, the protection scope of the present disclosure shall be subject to the protection scope of the claims.

Claims

1. An information processing method characterized by comprising:

2. The method according to claim 1, wherein the search information having the target search result meeting the preset condition carries target tag information, the target tag information being generated in advance;

3. The method of claim 1, wherein determining search information to be produced based on the plurality of pieces of search information comprises:

the target search result not satisfying the target condition comprises:

4. The method of claim 3, wherein the second interaction information comprises at least one of the following information:

5. The method of claim 1, wherein determining search information to be produced based on the plurality of pieces of search information comprises:

6. The method according to claim 1, wherein the determining production demand information corresponding to the search information to be produced comprises:

7. The method according to claim 6, wherein the inputting the search information to be produced into a sensitive information detection model trained in advance and determining a detection result corresponding to the search information to be produced comprises:

8. The method according to claim 3, wherein the sending the search information to be produced to the target user side matched with the production demand information comprises:

9. The method according to claim 8, wherein when the search information to be produced comprises first search information, the interaction parameter corresponding to the search information to be produced comprises the number of searches corresponding to the first search information, and the attribute information corresponding to the search information to be produced comprises stability information and/or production demand information of the first search information;

10. The method according to claim 8, wherein the determining the second importance of each piece of search information to be produced based on the interaction parameter and the attribute information respectively corresponding to the search information to be produced comprises:

11. The method according to claim 9, wherein the stability information of the search information to be produced is obtained based on a pre-trained neural network model;

12. The method of claim 11, wherein the characteristic information corresponding to the sample search information comprises at least one of the following information:

13. The method of claim 1, wherein the target customer end matching the production demand information is determined according to the following steps:

14. The method of claim 1, wherein after sending the search information to be produced to a target user terminal, the method further comprises:

15. The method of claim 14, wherein the determining the difficulty factor of the search information to be produced based on historical production status information of the search information to be produced comprises:

16. The method of claim 14, wherein the reassigning the search information to be produced based on the difficulty factor of the search information to be produced comprises:

17. The method of claim 14, wherein the reassigning the search information to be produced based on the difficulty factor of the search information to be produced comprises:

18. An information processing apparatus characterized by comprising:

19. 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 communicating via the bus when a computer device is running, the machine-readable instructions when executed by the processor performing the steps of the information processing method according to any one of claims 1 to 17.

20. A computer-readable storage medium, characterized in that a computer program is stored thereon, which computer program, when being executed by a processor, performs the steps of the information processing method according to any one of claims 1 to 17.