Information distribution method and device

[0052] In order to make the purpose, technical solutions and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be described clearly and completely in conjunction with the accompanying drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only It is a part of the embodiments of the present disclosure, but not all the embodiments. The components of the embodiments of the present disclosure generally described and illustrated in the drawings herein may be arranged and designed in various different configurations. Therefore, 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 claimed present disclosure, but merely represents selected embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without creative work shall fall within the protection scope of the present disclosure.

[0053] In the related art, when allocating search requests for search results that do not meet preset conditions to each client, it is generally first to determine the field to which the search information to be produced belongs (for example, food, medicine, electronics, services, etc.). Then, according to the field to which the search information to be produced belongs, a client is selected for the search information to be produced. However, this method may not meet the needs of users.

[0054] Exemplarily, if the search information to be produced is "Detailed explanation of the practice of braised pork", it can be determined by related technology that the field of the search information to be produced is "gourmet", and then the search information to be produced is sent to the "gourmet" "" field of search results, but the user needs corresponding to the search information to be produced may be gourmet videos. If the sending user cannot produce video search results, the search results produced by the end user cannot satisfy the user According to the demand, the user may also need to search again according to the "Video Detailed Explanation of the Practice of Braised Pork", which reduces the search efficiency.

[0055] Based on this, the present disclosure provides an information distribution method, which can determine the production demand information corresponding to the search information to be produced after acquiring the search information to be produced, where the production demand information is the user’s corresponding to the search information to be produced The demand type of the search results; then, the search information to be produced can be sent to the target client that matches the production demand information, so that the target client selected based on the production demand information will produce more accurate search results , It is easier to meet user needs.

[0056] The defects in the above solutions are all the results of the inventor after practice and careful study. Therefore, the discovery process of the above problems and the solutions proposed by the present disclosure below to solve the above problems should be the inventors Contributions made to this disclosure in the course of this disclosure.

[0057] It should be noted that similar reference numerals and letters indicate similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0058] In order to facilitate the understanding of this embodiment, an information distribution method disclosed in the embodiment of the present disclosure is first introduced in detail. The execution subject of the information distribution method provided in the embodiment of the present disclosure is a computer device with a certain computing capability, generally a server. .

[0059] See figure 1 As shown, a flowchart of an information distribution method provided by an embodiment of the present disclosure, the method includes the following steps:

[0060] Step 101: Acquire search information to be produced; search results corresponding to the search information to be produced do not meet preset conditions.

[0061] Step 102: Determine the production demand information corresponding to the search information to be produced, where the production demand information is used to indicate the demand type of the search result to be produced corresponding to the search information.

[0062] Step 103: Send the search information to be produced to a target user terminal that matches the production demand information.

[0063] The following is a detailed introduction to the above steps.

[0064] For step 101,

[0065] When obtaining search information to be produced, you can first obtain multiple pieces of search information generated in the most recent time period, and then input the search information into a pre-trained sensitive information detection model to determine the detection result corresponding to the search information. When the search information corresponds to When the detection result is that no sensitive information is contained, the search information is determined as the search information to be produced.

[0066] In a possible implementation manner, the acquiring multiple pieces of search information generated within the most recent preset time period may be acquiring multiple pieces of search request generated within a preset time period from the current moment, and then from each Extract search information from search requests.

[0067] Among them, the obtained multiple search requests may be obtained from the current search platform, or may be obtained from the current search platform and other search platforms. The search platform includes but is not limited to applications, web pages Wait.

[0068] When determining the detection result corresponding to the search information, you can input the search information into the pre-trained sensitive information detection model, output the probability that the search information contains sensitive information, and then determine the search information corresponding to the probability of containing the sensitive information based on the output. The results of the test can specifically include the following situations:

[0069] Case 1. The probability that the output contains sensitive information is greater than the first preset value.

[0070] When the output probability of containing sensitive information is greater than the first preset value, it can be determined that the detection result corresponding to the search information contains sensitive information.

[0071] Case 2. The probability that the output contains sensitive information is less than or equal to a second preset value, where the second preset value is less than the first preset value.

[0072] In this case, it can be determined that the detection result corresponding to the search information does not contain sensitive information.

[0073] Case 3: The probability that the output contains sensitive information is greater than the second preset value and less than or equal to the first preset value.

[0074] In this case, it means that the search information may or may not contain sensitive information. Therefore, in order to improve the accuracy of the detection result of the search information, the detection result of the search information can be determined as whether the search information contains sensitive information to be verified.

[0075] For situation 3, when the detection result of the search information is whether it contains sensitive information to be verified, a sensitive information confirmation instruction carrying the search information and the detection result can be sent to the server, and then based on the feedback result of the server, whether it contains sensitive information to be verified The detection result of is updated, the updated detection result is that the search information contains sensitive information, or the search information does not contain sensitive information.

[0076] Among them, the server end may be the user end of the maintainer of the current search platform.

[0077] Specifically, when updating according to the feedback result of the server, if the feedback result of the server contains sensitive information, the detection result corresponding to the search information is updated to contain sensitive information; if the feedback result of the server does not contain sensitive information, then The detection result corresponding to the search information is updated to not contain sensitive information.

[0078] During the training process of the sensitive information detection model, the sample search information and the sensitive label information of the sample search information can be obtained first. The sensitive label information is used to indicate whether the sample search information contains sensitive information, and then the sample search information is input to the sensitive In the information detection model, output the probability that the sample search information contains sensitive information, and determine the detection result corresponding to the sample search information based on the probability that the sample search information contains sensitive information; then based on the detection result corresponding to the sample search information, and the sample search information Corresponding to the sensitive label information, determine the loss value in this training process, and if the loss value does not meet the preset conditions, perform the above training process again.

[0079] For step 102,

[0080] Wherein, the production demand information corresponding to the search information to be produced may include at least one of the following information:

[0081] Field information, required format information, whether a professional answer is required, and whether an encyclopedia page needs to be generated.

[0082] Exemplarily, the field information may include gourmet, medical, electronics, breeding, planting, etc., and the required format information may include video format, audio format, text format, picture format, and the like.

[0083] In a possible implementation, when determining the production demand information corresponding to the search information to be produced, the search information to be produced can be input into a pre-trained neural network model, and the neural network model can output the search information to be produced Correspond to the probability value corresponding to each type of production demand information, and then determine the production demand information corresponding to the search information to be produced according to the probability value.

[0084] Exemplarily, if the production demand information includes field information, after the search information to be produced is input into the pre-trained neural network model, the neural network model can output the probability that the search information to be produced belongs to the gourmet field and belongs to the medical field If the probability of belonging to the electronic field, the probability of belonging to the breeding field, and the probability of belonging to the field of cultivation, if the probability of belonging to the field of food is the highest, the field information corresponding to the search information to be produced is determined to be the field of food.

[0085] Due to the limited accuracy of the neural network model, in order to improve the accuracy of determining the production demand information corresponding to the search information to be produced, in a possible implementation manner, after determining the production demand information corresponding to the search information to be produced based on the neural network model , The search information to be produced and the production demand information corresponding to the determined search information to be produced can also be sent to the server, and the production demand information of the search information to be produced can be reviewed by the staff. If the review is passed, the staff can The server feedbacks the approval instruction. After receiving the approval instruction, the server directly determines the production demand information determined by the neural network model as the production demand information corresponding to the search information to be produced; if the review fails, the staff can directly The demand information is modified, and then the modified production demand information is fed back to the server, and the server uses the modified production demand information as the production demand information of the search information to be produced; or, if the audit fails, it will feed back to the server that the audit failed After receiving the unapproved instruction, the server re-inputs the search information to be produced into the neural network model to re-determine the production demand information of the search information to be produced.

[0086] In another possible implementation, in order to reduce the workload of the staff, the neural network model can also be output. The probability value corresponding to each type of production demand information corresponding to the search information to be produced does not meet the preset conditions. The search information to be produced and the production demand information of the search information to be produced are sent to the server.

[0087] 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 tagged, such as figure 2 As shown, different production demand information can correspond to tags with attributes. For example, the domain information can correspond to the domain tag, the required format information can correspond to the resource form tag, whether the professional answer can correspond to the resource authority judgment label, whether Encyclopedia pages need to be generated to correspond to resource-satisfying trend labels. After the search information to be produced is input into the neural network model, the neural network model can determine the value of each type of label according to the above four types of labels, and then set the value for the label to be produced Search for information and tag, figure 2 The tags corresponding to the search information to be produced in the input are film and television demand tags (information in the field is film and television), video demand tags (the required format information is video format), expert demand tags (requires professional answers), and encyclopedia Demand tags (encyclopedia pages need to be generated), and then according to the tags of the search information to be produced, the search information to be produced is sent to the user terminal.

[0088] For step 103,

[0089] When determining the target client terminal that matches the production demand information of the search information to be produced, the attribute information of each candidate client terminal can be determined based on the production demand information corresponding to the historical search results generated by each candidate client terminal, and then based on the The production demand information corresponding to the production search information and the attribute information of each candidate client terminal are used to determine the target client terminal from each candidate client terminal.

[0090] Among them, when determining the attribute information of each candidate client based on the production demand information corresponding to the historical search results generated by each candidate client, you can count each item of the production demand information corresponding to the historical search results generated by each candidate client The value of the production demand information, and then the corresponding production demand information with a value higher than the preset value is used as the attribute information of each candidate client.

[0091] Exemplarily, if the production demand information (including field information and format information required by the historical search results) corresponding to the historical search results generated by the candidate client is shown in Table 1 and Table 2 below:

[0092] Table 1

[0093]

[0094]

[0095] Table 2

[0096] Format information required for historical search results Number of historical search results Video format 0 Image Format 10 audio format 2 Text format 30

[0097] If the preset value corresponding to the domain information is 100 and the preset value corresponding to the format information of the historical search results is 20, then the attribute information of the candidate client includes "food", "farming", and "text format". The production demand information corresponding to the produced search information includes "food" and "text format", then the candidate client can be used as a target client, and the search information to be produced can be sent to the target client.

[0098] In a possible implementation, based on the production demand information corresponding to the search information to be produced and the attribute information of each candidate client, when determining the target client from each candidate client, you can select the corresponding attribute information and the The candidate client terminal that matches the production demand information corresponding to the produced search information is used as the target client terminal. If the number of determined target client terminals is more than one, a target client terminal can be randomly selected, and then the search information to be produced is sent To the selected target client.

[0099] In another possible implementation manner, in order to balance the workload of each client terminal, based on the production demand information corresponding to the search information to be produced and the attribute information of each candidate client terminal, when determining the target client terminal from each candidate client terminal , You can also first determine the client to be screened from the candidate client based on the production demand information corresponding to the search information to be produced and the attribute information of each candidate client, and then based on the amount of uncompleted tasks of each client to be screened The number of target clients is selected from the clients to be screened, where the number of uncompleted tasks is the number of search information currently received by the client to be screened for the search results to be produced.

[0100] In another possible implementation manner, considering that the efficiency of generating search information to be produced may be different for different client terminals, when selecting a target client terminal from candidate client terminals, historical search results can also be generated based on the candidate client terminal. The processing efficiency of the target client, the number of tasks currently unfinished by the target client and the number of tasks currently completed by the target client, are selected from the client to be filtered.

[0101] Specifically, according to the processing efficiency of the candidate client's generation of historical search results, the number of tasks currently unfinished by the target client, and the number of tasks currently completed by the target client, the search information to be produced that can be received by the candidate client can be determined Then sort according to the number of search information to be produced that can be received, and then select the target client according to the sorting result.

[0102] Exemplarily, if the average daily processing volume of the candidate client is 20, and the number of tasks currently completed by the candidate client is 3, the number of unfinished tasks is currently one. For this situation , It means that the number of search information to be produced that the candidate client can currently receive is 16. If the candidate client is ranked first in each candidate client, when there is search information to be produced to be distributed, the The search information to be produced is allocated to the candidate client.

[0103] The information distribution method provided by the embodiments of the present disclosure can determine the production demand information corresponding to the search information to be produced after obtaining the search information to be produced, where the production demand information is the search result of the user for the search information to be produced corresponding to the search information. The type of demand; then, the search information to be produced can be sent to the target client that matches the production demand information. In this way, the target client selected based on the production demand information will produce more accurate search results and easier Meet user needs.

[0104] Those skilled in the art can understand that in the above-mentioned methods of the specific implementation, the writing order of the steps does not mean a strict execution order but constitutes any limitation on the implementation process. The specific execution order of each step should be based on its function and possibility. The inner logic is determined.

[0105] Based on the same inventive concept, the embodiment of the present disclosure also provides an information distribution device corresponding to the information distribution method. Since the principle of the device in the embodiment of the disclosure to solve the problem is similar to the above-mentioned information distribution method of the embodiment of the disclosure, the implementation of the device You can refer to the implementation of the method, and the repetition will not be repeated.

[0106] Reference image 3 What is shown is a schematic structural diagram of an information distribution device provided by an embodiment of the present disclosure. The device includes: an acquisition module 301, a determination module 302, and a sending module 303; wherein,

[0107] The obtaining module 301 is configured to obtain search information to be produced; the search result corresponding to the search information to be produced does not meet preset conditions;

[0108] The determining module 302 is configured to determine production demand information corresponding to the search information to be produced, where the production demand information is used to indicate the demand type of the search result to be produced corresponding to the search information;

[0109] The sending module 303 is configured to send the search information to be produced to a target user terminal that matches the production demand information.

[0110] In a possible implementation manner, the acquiring module 301 is used to: when acquiring search information to be produced:

[0111] Acquire multiple pieces of search information generated in the latest preset time period;

[0112] Input the search information into a pre-trained sensitive information detection model, and determine the detection result corresponding to the search information;

[0113] When the detection result corresponding to the search information does not contain sensitive information, the search information is determined as the search information to be produced.

[0114] In a possible implementation manner, the acquisition module 301 is used to input the search information into a pre-trained sensitive information detection model to determine the detection result corresponding to the search information:

[0115] Inputting the search information into a pre-trained sensitive information detection model, and outputting the probability that the search information contains sensitive information;

[0116] When the probability is greater than the first preset value, it is determined that the detection result corresponding to the search information contains sensitive information; when the probability is greater than the second preset value and less than or equal to the first preset value, It is determined whether the detection result corresponding to the search information contains sensitive information to be verified; when the probability is less than or equal to the second preset value, it is determined that the detection result corresponding to the search information does not contain sensitive information.

[0117] In a possible implementation manner, the production demand information includes at least one of the following information:

[0118] Field information, required format information, whether a professional answer is required, and whether an encyclopedia page needs to be generated.

[0119] In a possible implementation manner, the determining module 302 is further configured to determine a target client that matches the production demand information according to the following steps:

[0120] Determine the attribute information of each candidate client based on the production demand information corresponding to the historical search results generated by each candidate client;

[0121] Based on the production demand information corresponding to the search information to be produced and the attribute information of each candidate client terminal, the target client terminal is determined from each candidate client terminal.

[0122] In a possible implementation manner, the determining module 302 determines the target user from each candidate client based on the production demand information corresponding to the search information to be produced and the attribute information of each candidate client. At the end, used for:

[0123] Based on the production demand information corresponding to the search information to be produced and the attribute information of each candidate client terminal, determine the client terminal to be screened from the candidate client terminals;

[0124] Based on the current number of uncompleted tasks of each client to be screened, the target client is selected from the client to be screened, and the number of unfinished tasks is the client to be screened The number of search information currently received for the search results to be produced.

[0125] The information distribution device provided by the embodiment of the present disclosure can determine the production demand information corresponding to the search information to be produced after obtaining the search information to be produced. The production demand information here includes the search information for the user to be produced and the search information to be produced. The demand type of the search result; then, the search information to be produced can be sent to the target client that matches the production demand information, so that the target client selected based on the production demand information will produce more accurate search results. Easier to meet user needs.

[0126] Based on the same technical concept, the embodiment of the present application also provides a computer device. Reference Figure 4 As shown, a schematic structural diagram of a computer device 400 provided in an embodiment of this application includes a processor 401, a memory 402, and a bus 403. Among them, the memory 402 is used to store execution instructions, including a memory 4021 and an external memory 4022; here, the memory 4021 is also called internal memory, which is used to temporarily store the calculation data in the processor 401 and the data exchanged with the external memory 4022 such as a hard disk. The processor 401 exchanges data with the external memory 4022 through the memory 4021. When the computer device 400 is running, the processor 401 and the memory 402 communicate through the bus 403, so that the processor 401 executes the following instructions:

[0127] Acquiring search information to be produced; search results corresponding to the search information to be produced do not meet preset conditions;

[0128] Determining the production demand information corresponding to the search information to be produced, where the production demand information is used to indicate the demand type of the search result to be produced corresponding to the search information;

[0129] The search information to be produced is sent to the target user terminal that matches the production demand information.

[0130] In a possible implementation manner, in the instruction executed by the processor 401, the acquiring search information to be produced includes:

[0131] Acquire multiple pieces of search information generated in the latest preset time period;

[0132] Input the search information into a pre-trained sensitive information detection model, and determine the detection result corresponding to the search information;

[0133] When the detection result corresponding to the search information does not contain sensitive information, the search information is determined as the search information to be produced.

[0134] In a possible implementation manner, in the instruction executed by the processor 401, the inputting the search information into a pre-trained sensitive information detection model to determine the detection result corresponding to the search information includes:

[0135] Inputting the search information into a pre-trained sensitive information detection model, and outputting the probability that the search information contains sensitive information;

[0136] When the probability is greater than the first preset value, it is determined that the detection result corresponding to the search information contains sensitive information; when the probability is greater than the second preset value and less than or equal to the first preset value, It is determined whether the detection result corresponding to the search information contains sensitive information to be verified; when the probability is less than or equal to the second preset value, it is determined that the detection result corresponding to the search information does not contain sensitive information.

[0137] In a possible implementation manner, in the instructions executed by the processor 401, the production demand information includes at least one of the following information:

[0138] Field information, required format information, whether a professional answer is required, and whether an encyclopedia page needs to be generated.

[0139] In a possible implementation manner, among the instructions executed by the processor 401, the target client that matches the production demand information is determined according to the following steps:

[0140] Determine the attribute information of each candidate client based on the production demand information corresponding to the historical search results generated by each candidate client;

[0141] Based on the production demand information corresponding to the search information to be produced and the attribute information of each candidate client terminal, the target client terminal is determined from each candidate client terminal.

[0142] In a possible implementation manner, in the instructions executed by the processor 401, the target is determined from each candidate client based on the production demand information corresponding to the search information to be produced and the attribute information of each candidate client. User side, including:

[0143] Based on the production demand information corresponding to the search information to be produced and the attribute information of each candidate client terminal, determine the client terminal to be screened from the candidate client terminals;

[0144] Based on the number of currently uncompleted tasks of each client to be screened, the target client is selected from the client to be screened, and the number of unfinished tasks is the client to be screened The number of search information currently received for the search results to be produced.

[0145] The embodiments of the present disclosure also provide a computer-readable storage medium on which a computer program is stored, and the computer program executes the steps of the information distribution method described in the above method embodiment when the computer program is run by a processor. Wherein, the storage medium may be a volatile or nonvolatile computer readable storage medium.

[0146] The computer program product of the information distribution method provided by the embodiment of the present disclosure includes a computer-readable storage medium storing program code, and the program code includes instructions that can be used to execute the steps of the information distribution method described in the above method embodiment For details, please refer to the above method embodiment, which will not be repeated here.

[0147] The embodiments of the present disclosure also provide a computer program, which, when executed by a processor, implements any method of the foregoing embodiments. The computer program product can be specifically implemented by hardware, software or a combination thereof. In an optional embodiment, the computer program product is specifically embodied as a computer storage medium. In another optional embodiment, the computer program product is specifically embodied as a software product, such as a software development kit (SDK), etc. .

[0148] Those skilled in the art can clearly understand that for the convenience and conciseness of the description, the specific working process of the system and device described above can refer to the corresponding process in the foregoing method embodiment, which will not be repeated here. In the several embodiments provided in the present disclosure, it should be understood that the disclosed system, device, and method may be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there may be other divisions in actual implementation. For example, multiple units or components may be combined or It can be integrated into another system, or some features can be ignored or not implemented. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection may be through some communication interfaces, indirect coupling or communication connection of devices or units, and may be in electrical, mechanical or other forms.

[0149] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments.

[0150] In addition, the functional units in the various embodiments of the present disclosure may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit.

[0151] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a nonvolatile computer readable storage medium executable by a processor. Based on this understanding, the technical solution of the present disclosure essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including Several instructions are used to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in the various embodiments of the present disclosure. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk and other media that can store program codes.

[0152] Finally, it should be noted that the above-mentioned embodiments are only specific implementations of the present disclosure, and are used to illustrate the technical solutions of the present disclosure, rather than limiting them. The protection scope of the present disclosure is not limited to this, although referring to the foregoing The embodiments describe the present disclosure in detail, and those of ordinary skill in the art should understand that any person skilled in the art can still modify the technical solutions described in the foregoing embodiments within the technical scope disclosed in the present disclosure. Or it may be easily conceived of changes, or equivalent replacements of some of the technical features; these modifications, changes or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should be covered by the present disclosure Within the scope of protection. Therefore, the protection scope of the present disclosure should be subject to the protection scope of the claims.