Information query method, apparatus, device, storage medium, and program product

Abstract

The present disclosure provides an information query method, device, equipment, storage medium and program product, relates to the technical field of data processing and computer, and particularly relates to the technical field of big data and intelligent search. The specific implementation scheme of the information query method is as follows: determining at least one candidate key information matched with the query information according to the query information; determining a first evaluation value for evaluating the candidate key information according to a key information evaluation parameter; determining at least one target key information from the at least one candidate key information according to the first evaluation value; and determining target content information according to the at least one target key information.

Description

Technical Field

[0001] This disclosure relates to the fields of data processing and computer technology, and in particular to the fields of big data and intelligent search technology, specifically to an information query method, apparatus, device, storage medium, and program product. Background Technology

[0002] With the development of computer and internet technologies, information and data are growing exponentially, which places higher demands on tasks such as information retrieval. Summary of the Invention

[0003] This disclosure provides an information retrieval method, apparatus, device, storage medium, and program product.

[0004] According to one aspect of this disclosure, an information query method is provided, comprising: determining at least one candidate key information matching the query information based on the query information; determining a first evaluation value for evaluating the candidate key information based on key information evaluation parameters; determining at least one target key information from the at least one candidate key information based on the first evaluation value; and determining target content information based on the at least one target key information.

[0005] According to another aspect of this disclosure, an information query apparatus is provided, comprising: a candidate key information determination module, a first evaluation value determination module, a target key information determination module, and a target content information determination module. The candidate key information determination module is used to determine at least one candidate key information matching the query information. The first evaluation value determination module is used to determine a first evaluation value for evaluating the candidate key information based on key information evaluation parameters. The target key information determination module is used to determine at least one target key information from the at least one candidate key information based on the first evaluation value. The target content information determination module is used to determine target content information based on the at least one target key information.

[0006] According to another aspect of this disclosure, an electronic device is provided, comprising: at least one processor and a memory communicatively connected to the at least one processor. The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the methods of embodiments of this disclosure.

[0007] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions for causing a computer to perform the methods of embodiments of this disclosure.

[0008] According to another aspect of this disclosure, a computer program product is provided, including a computer program stored on at least one of a readable storage medium and an electronic device, wherein the computer program, when executed by a processor, implements the methods of embodiments of this disclosure.

[0009] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0010] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0011] Figure 1 This schematically illustrates a system architecture diagram of an information query method and apparatus according to embodiments of the present disclosure;

[0012] Figure 2 A flowchart illustrating an information query method according to an embodiment of the present disclosure is shown schematically;

[0013] Figure 3 A schematic diagram illustrating an information query method according to another embodiment of the present disclosure is shown.

[0014] Figure 4 The diagram illustrates the adjustment of the weights of key information evaluation parameters in an information query method according to yet another embodiment of the present disclosure;

[0015] Figure 5 The diagram illustrates the adjustment of the weights of the content information evaluation parameters in an information query method according to yet another embodiment of the present disclosure;

[0016] Figure 6 A block diagram of an information query device according to an embodiment of the present disclosure is schematically shown; and

[0017] Figure 7 A block diagram of an electronic device that can implement the information query method of the embodiments of this disclosure is shown schematically. Detailed Implementation

[0018] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0019] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this disclosure. The terms “comprising,” “including,” etc., as used herein indicate the presence of features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0020] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0021] When using expressions such as "at least one of A, B, and C", they should generally be interpreted in accordance with the meaning that is commonly understood by a person skilled in the art (e.g., "a system having at least one of A, B, and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B, and C, etc.).

[0022] With the development of computer and internet technologies, information and data are growing exponentially, which places higher demands on tasks such as information retrieval.

[0023] Information retrieval can be understood as the process of querying a set of information based on the query information, and obtaining information that matches the query information as the query result. The information set may include offline existing information as well as online information.

[0024] Information retrieval can be applied to various scenarios such as search engines and online forums.

[0025] In some implementations, based on the query information, keyword matching is used to determine content information related to the query information as the query result.

[0026] Figure 1 The diagram schematically illustrates the system architecture of an information query method and apparatus according to an embodiment of the present disclosure. It should be noted that... Figure 1 The examples shown are merely examples of system architectures that can be applied to the embodiments of this disclosure, in order to help those skilled in the art understand the technical content of this disclosure, but do not mean that the embodiments of this disclosure cannot be used in other devices, systems, environments or scenarios.

[0027] like Figure 1As shown, the system architecture 100 according to this embodiment may include clients 101, 102, and 103, a network 104, and a server 105. The network 104 serves as a medium for providing a communication link between clients 101, 102, and 103 and the server 105. The network 104 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0028] Users can use clients 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Various communication client applications can be installed on clients 101, 102, and 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social media platform software, etc. (for example only).

[0029] Clients 101, 102, and 103 can be various electronic devices with displays and web browsing capabilities, including but not limited to smartphones, tablets, laptops, and desktop computers. Clients 101, 102, and 103 in this embodiment of the disclosure can, for example, run applications.

[0030] Server 105 can be a server providing various services, such as a backend management server supporting websites browsed by users using clients 101, 102, and 103 (this is just an example). The backend management server can analyze and process data such as received user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the clients. Alternatively, server 105 can also be a cloud server, meaning server 105 has cloud computing capabilities.

[0031] It should be noted that the information query method provided in this embodiment can be executed by server 105. Correspondingly, the information query device provided in this embodiment can be located in server 105. The information query method provided in this embodiment can also be executed by a server or server cluster that is different from server 105 and capable of communicating with clients 101, 102, 103 and / or server 105. Correspondingly, the information query device provided in this embodiment can also be located in a server or server cluster that is different from server 105 and capable of communicating with clients 101, 102, 103 and / or server 105.

[0032] In one example, server 105 can obtain query information from clients 101, 102, and 103 via network 104 and perform information queries based on that query information.

[0033] It should be understood that Figure 1The number of clients, networks, and servers shown is merely illustrative. Depending on implementation needs, there can be any number of clients, networks, and servers.

[0034] It should be noted that the collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in the technical solution disclosed herein all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0035] In the technical solution disclosed herein, the user's authorization or consent is obtained before acquiring or collecting the user's personal information.

[0036] This disclosure provides an information query method, which is described below in conjunction with... Figure 1 The system architecture, referencing Figures 2-5 This describes an information query method according to exemplary embodiments of the present disclosure. The information query method of this disclosure, for example, can be derived from... Figure 1 The server 105 shown is used to execute this.

[0037] Figure 2 A flowchart illustrating an information query method according to an embodiment of the present disclosure is shown.

[0038] like Figure 2 As shown, the information query method 200 of this embodiment may include, for example, operations S210 to S240.

[0039] In operation S210, based on the query information, at least one candidate key information that matches the query information is determined.

[0040] For example, query information can be input by an object, and the query information can include the input query.

[0041] For example, candidate key information can be associated with query information through mapping or other means, so that candidate key information can be determined based on the query information.

[0042] Key information can be understood as information data that can cover multiple pieces of information. For example, key information may include specific entities, topics, etc.

[0043] For example, key information can be obtained in advance by classifying and summarizing information.

[0044] For example, candidate key information can be key information that matches the query information, determined from the existing key information.

[0045] In operation S220, a first evaluation value is determined based on the key information evaluation parameters to evaluate the candidate key information.

[0046] Key information evaluation parameters can be used, for example, to assess whether candidate key information meets expectations. For instance, if the user expects to receive high-quality content when entering a query, key information evaluation parameters can be used to assess the quality of candidate key information.

[0047] For example, the key information evaluation parameters can be predetermined.

[0048] In operation S230, at least one target key information is determined from at least one candidate key information based on the first evaluation value.

[0049] For example, if the magnitude of the first evaluation value is positively correlated with the degree to which the evaluation candidate key information meets expectations, at least one candidate key information can be sorted from largest to smallest based on the first evaluation value, and at least one candidate key information ranked first by the first evaluation value can be used as the target key information.

[0050] In operation S240, target content information is determined based on at least one key target information.

[0051] For example, target key information can be associated with target content information through mapping or other means, so that target content information can be determined based on target key information.

[0052] According to the information query method of this disclosure, candidate key information matching the query information can be determined based on the query information, and target key information can be determined based on the candidate key information. This is similar to screening key information, which can obtain target key information that better matches the query information from a large amount of key information. In some cases, the number of target key information is less than the number of candidate key information. Therefore, the information query method of this disclosure can determine more matching target key information from a large amount of key information, thereby improving the speed and efficiency of information query.

[0053] According to the information query method of this disclosure, key information evaluation parameters can measure whether candidate key information meets the expectations of the target. Based on the key information evaluation parameters, a first evaluation value determined for evaluating candidate key information serves as the basis for determining target key information from the candidate key information, making the target key information more aligned with the target's expectations. Subsequently, the target content information determined based on the target key information also correspondingly better meets the target's expectations. Therefore, the information query method of this disclosure has higher information query efficiency.

[0054] It should be noted that the key information evaluation parameters can be set according to the specific expectations of the target audience. For example, if the target audience expects to obtain high-quality target content information, the key information evaluation parameters can include at least one parameter that measures the quality of candidate key information.

[0055] Figure 3 A schematic diagram of an information query method according to another embodiment of the present disclosure is shown.

[0056] like Figure 3 As shown, according to another embodiment of the information query method 300 of this disclosure, the specific example of determining target content information based on at least one target key information in operation S340 can be implemented using the following embodiment.

[0057] In operation S341, for any target key information, at least one candidate content information related to the target key information is determined.

[0058] For example, target key information can be associated with candidate content information through mapping or other means, so that candidate content information can be determined based on the target key information.

[0059] For example, candidate content information may be content information that matches the target key information, determined from existing or online content information.

[0060] In operation S342, a second evaluation value is determined based on the content information evaluation parameters to evaluate the candidate content information.

[0061] Content information evaluation parameters can be used, for example, to assess whether candidate content information meets expectations. For instance, if the expectation of the object inputting the query is to obtain high-quality content information, then content information evaluation parameters can be used to assess whether the candidate content information is of high quality.

[0062] For example, the content information evaluation parameters can be predetermined.

[0063] In operation S343, target content information is determined from at least one candidate content information based on the second evaluation value.

[0064] For example, if the magnitude of the second evaluation value is positively correlated with the degree to which the evaluation candidate content information meets expectations, at least one candidate content information can be sorted from largest to smallest based on the second evaluation value, and at least one candidate content information ranked first by the second evaluation value can be used as the target content information.

[0065] According to the information query method of this disclosure, for any given target key information, candidate content information related to the target key information can be determined, and the target content information can be determined based on the candidate content information. This is similar to filtering the content information, allowing for the extraction of target content information that better matches the target key information from a large amount of content information. In some cases, the number of target content information is less than the number of candidate content information. Therefore, the information query method of this disclosure can determine more matching target content information from a large amount of content information, improving the speed and efficiency of information query.

[0066] According to the information query method of this disclosure, content information evaluation parameters can measure whether candidate content information meets the expectations of the object. Based on the content information evaluation parameters, a second evaluation value determined for evaluating candidate content information serves as the basis for determining target content information from the candidate content information, making the target content information more in line with the object's expectations. Subsequently, the target content information determined based on the target key information also better meets the object's expectations. The information query method of this disclosure has higher information query efficiency.

[0067] It should be noted that content information evaluation parameters can be set according to the specific expectations of the target audience. For example, if the target audience expects high-quality target content information, the content information evaluation parameters can include at least one parameter that measures the quality of candidate content information.

[0068] exist Figure 3 In the example, taking target key information tk-1 as an example, it illustrates a specific example of determining r candidate content information, including candidate content information ti-1 to candidate content information ti-r, related to target key information tk-1. Figure 3 The illustration also shows a specific example of determining a second evaluation value for evaluating candidate content information based on the content information evaluation parameter 302. The second evaluation value for each candidate content information can be determined using the content information evaluation parameter 302. For example, candidate content information ti-1 corresponds to the second evaluation value tv-1, and candidate content information ti-r corresponds to the second evaluation value tv-r.

[0069] exist Figure 3The example also illustratively illustrates a specific example of operation S310, which determines n candidate key information pieces, including candidate key information ki-1 to ki-n, that match the query information based on the query information. It also illustratively illustrates operation S320, which determines a first evaluation value for each candidate key information piece based on the key information evaluation parameter 301; for example, candidate key information ki-1 corresponds to the first evaluation value kv-1, and candidate key information ki-n corresponds to the first evaluation value kv-n. It also illustratively illustrates a specific example of operation S330, which determines at least one target key information piece from at least one candidate key information piece based on the first evaluation value. For example, in... Figure 3 The example illustrates a specific instance of determining a total of s target key information from n candidate key information to target key information tk-1 to tk-s based on the first evaluation value corresponding to each candidate key information.

[0070] It is understood that operations S310, S320, S330 and S340 are similar to operations S210, S220, S230 and S240 in the above embodiments, respectively, and will not be described again here.

[0071] According to another embodiment of the information query method of this disclosure, the key information evaluation parameters include multiple parameters, and each key information evaluation parameter has a corresponding weight.

[0072] Determining the first evaluation value for evaluating candidate key information based on key information evaluation parameters may include: determining the first evaluation value of candidate key information based on the weights of the key information evaluation parameters, the key information evaluation parameters, and the candidate key information.

[0073] For example, the weighted sum of multiple key information evaluation parameters corresponding to candidate key information can be used as the first evaluation value.

[0074] like Figure 3 As shown, in Figure 3 The example illustrates specific examples of m key information evaluation parameters, from key information evaluation parameter kp-1 to key information evaluation parameter kp-m.

[0075] According to the information query method of this disclosure, each key information evaluation parameter represents a dimension for evaluating candidate key information. Based on multiple key information evaluation parameters, candidate key information can be comprehensively evaluated from multiple dimensions, making the candidate key information more in line with the expectations of the target audience. Furthermore, each key information evaluation parameter has a corresponding weight, which allows for more accurate evaluation of candidate key information.

[0076] For example, the key information evaluation parameters include at least one of the following: the amount of content information related to the candidate key information, the number of people who follow the candidate key information, the number of views, the number of reposts, and the number of check-ins.

[0077] According to the information query method of this disclosure, given the increasing prevalence of online information dissemination, users can perform operations such as following, browsing, forwarding, and checking in on online information. By using specific key information evaluation parameters such as the number of content information related to the candidate key information, the number of users following the candidate key information, the number of views, the number of forwards, and the number of check-ins, the candidate key information can be comprehensively evaluated. The resulting target key information is more accurate, of higher quality, and better meets the user's expectations.

[0078] For example, if relevant data shows that a candidate key information K is mapped to x1 pieces of content information, then x1 can be taken as the number of pieces of content information related to the candidate key information K. If relevant data shows that x2 objects follow the candidate key information K, then x2 can be taken as the number of objects following the candidate key information K. If relevant data shows that the candidate key information K or its related content information has been viewed x3 times, then x3 can be taken as the number of views of the candidate key information. If relevant data shows that the candidate key information K or its related content information has been forwarded x4 times, then x4 can be taken as the number of forwards of the candidate key information. If relevant data shows that the candidate key information K or its related content information has been checked in x5 times, then x5 can be taken as the number of check-ins of the candidate key information.

[0079] For example, by using w1 to w5 to represent the weights of the five key information evaluation parameters related to the candidate key information, the number of objects of interest in the candidate key information, the number of views, the number of forwards, and the number of check-ins, respectively, the first evaluation value V1 can be obtained using the following formula (1).

[0080] V1=w1*x1+w2*x2+w3*x3+w4*x4+w5*x5 (1)

[0081] For example, candidate key information can also be filtered based on the number of content information related to the candidate key information as a key information evaluation parameter. For instance, if the number of content information corresponding to a certain candidate key information is less than or equal to a certain threshold, the candidate key information can be filtered.

[0082] According to another embodiment of the information query method of this disclosure, the content information evaluation parameters include multiple parameters, and each content information evaluation parameter has a corresponding weight.

[0083] Determining a second evaluation value for evaluating candidate content information based on content information evaluation parameters may include: determining a first evaluation value for candidate key information based on the weights of key information evaluation parameters, key information evaluation parameters, and candidate key information.

[0084] For example, the weighted sum of multiple content information evaluation parameters corresponding to the candidate content information can be used as the second evaluation value.

[0085] like Figure 3 As shown, in Figure 3 The example illustrates specific examples of t content information evaluation parameters, from cp-1 to cp-t.

[0086] According to the information query method of this disclosure, each content information evaluation parameter represents a dimension of the candidate content information. Based on multiple content information evaluation parameters, the candidate content information can be comprehensively evaluated from multiple dimensions, making the candidate content information more in line with the expectations of the target audience. Furthermore, each content information evaluation parameter has a corresponding weight, which allows for a more accurate evaluation of the candidate content information.

[0087] For example, the content information evaluation parameters include at least one of the following: the number of responses to candidate content information, the number of shares, and the publication time.

[0088] According to the information query method of this disclosure, given the increasing prevalence of online information publishing, the target can reply to and share online content information. By using specific content information evaluation parameters such as the number of replies, the number of shares, and the publication time of candidate content information, the candidate content information can be comprehensively evaluated. The resulting target key information is more accurate, of higher quality, and better meets the target's expectations.

[0089] For example, the corresponding calculated value can be determined based on the publication time of the candidate content information, and a second evaluation value can be determined based on the number of replies, the number of shares, and the calculated value corresponding to the publication time of the candidate content information. The calculated value corresponding to the publication time can be determined, for example, based on the time interval from the current time: the smaller the time interval from the current time, the larger the corresponding calculated value.

[0090] For example, if relevant data shows that a candidate content information C was replied to x6 times, then x6 can be taken as the number of replies to the candidate content information. If relevant data shows that a candidate content information C was shared x7 times, then x7 can be taken as the number of shares to the candidate content information. For example, the corresponding calculated value can be determined as x8 based on the publication time of the candidate content information.

[0091] For example, by using w6 to w8 to represent the weights of the three content information evaluation parameters of the corresponding candidate content information—the number of replies, the number of shares, and the publication time—the first evaluation value V2 can be obtained using the following formula (2).

[0092] V2=w6*x6+w7*x7+w8*x8 (2)

[0093] For example, the information query method according to another embodiment of the present disclosure may further include at least one of the following: adjusting the weight of the key information evaluation parameter according to a first weight adjustment period; and adjusting the weight of the content information evaluation parameter according to a second weight adjustment period.

[0094] For example, the first weight adjustment period may be 24 hours / time; the second weight adjustment period may also be 24 hours / time.

[0095] For example, according to another embodiment of the information query method of this disclosure, the specific example of adjusting the weight of the key information evaluation parameter according to the first weight adjustment period can be implemented by the following embodiment: at each adjustment node of the first weight adjustment period, the weight of the key information evaluation parameter is adjusted according to the difference value of the key information evaluation parameter.

[0096] The candidate key information includes multiple items.

[0097] The numerical difference in key information assessment parameters characterizes the degree of influence of the key information assessment parameters on determining the first assessment value.

[0098] The first weight adjustment cycle can be understood as the time points at which the weights of key information evaluation parameters are periodically adjusted, and the adjustment node is the specific moment when the weights of the key information evaluation parameters are adjusted. For example, if the first weight adjustment cycle is 24 hours / time, the current adjustment node is the moment obtained by adding 24 hours to the previous adjustment node.

[0099] For example, according to another embodiment of the information query method of this disclosure, the following specific example can be used to implement the adjustment of the weight of the content information evaluation parameter according to the second weight adjustment period: at each adjustment node of the second weight adjustment period, the weight of the content information evaluation parameter is adjusted according to the difference value of the content information evaluation parameter.

[0100] The candidate content information includes multiple items.

[0101] The numerical difference in the content information evaluation parameters characterizes the degree of influence of the content information evaluation parameters on the determination of the second evaluation value.

[0102] The second weight adjustment cycle can be understood as the time points at which the weights of the content information evaluation parameters are periodically adjusted. The adjustment node is the specific moment when the weights of the content information evaluation parameters are adjusted. For example, if the second weight adjustment cycle is 24 hours / time, the current adjustment node is the moment obtained by adding 24 hours to the previous adjustment node.

[0103] According to the information query method of this disclosure, by adjusting the weight of the key information evaluation parameters based on the difference value of the key information evaluation parameters at each adjustment node of the first weight adjustment period, and wherein the difference value of the key information evaluation parameters characterizes the degree of influence of the key information evaluation parameters on determining the first evaluation value, the weight of the key information evaluation parameters can be adaptively adjusted. Similarly, the weight of the content information evaluation parameters can also be adaptively adjusted.

[0104] Figure 4 The diagram illustrates the adjustment of the weights of key information evaluation parameters in an information query method according to yet another embodiment of the present disclosure.

[0105] like Figure 4 As shown, the information query method according to the embodiments of this disclosure can, for example, utilize the following embodiments to implement specific examples of adjusting the weight of key information evaluation parameters based on the difference values ​​of key information evaluation parameters.

[0106] In operation S411, N preceding candidate key information items ranked first N and N subsequent candidate key information items ranked last N are determined from multiple candidate key information items.

[0107] exist Figure 4 The example illustrates a specific instance of adjusting the weight of a key information evaluation parameter kp-i at an adjustment node j during the first weight adjustment period Ac1.

[0108] exist Figure 4 The example illustrates an adjustment node j in the first weight adjustment period Ac1. From n candidate key information pieces from candidate key information ki-1 to candidate key information ki-n, the N preceding candidate key information pieces ranked in the first evaluation value are determined. Specifically, this includes the candidate key information top1 ranked first by the value of the first evaluation value in descending order, up to the candidate key information topN ranked N by the value of the first evaluation value in descending order. N and n are both positive integers greater than 1, and N is less than or equal to n.

[0109] In operation S412, for any key information evaluation parameter, the mean of the key information evaluation values ​​of the corresponding N preceding candidate key information and the mean of the key information evaluation values ​​of the N subsequent candidate key information are determined respectively, so as to obtain the mean of the preceding key information evaluation and the mean of the subsequent key information evaluation.

[0110] The evaluation value of a key information evaluation parameter can be understood as the numerical value corresponding to that key information evaluation parameter. For example, in the example above where the number of objects of interest is used as a key information evaluation parameter to evaluate candidate key information K, x2 is the evaluation value of the key information evaluation parameter of the number of objects of interest.

[0111] exist Figure 4 The example illustrates a specific instance of determining the mean of the preceding key information evaluation, ikta, and the mean of the subsequent key information evaluation, ikba, for the key information evaluation parameter kp-i.

[0112] exist Figure 4 In the example, the key information evaluation value ikt-1 corresponding to candidate key information top1 is illustrated, up to the key information evaluation value ikt-N corresponding to candidate key information topN. By averaging the N values ​​of key information evaluation values ​​ikt-1 to key information evaluation value ikt-N, the mean evaluation value ikta of the preceding key information can be obtained. Similarly, the mean evaluation value ikba of the following key information can also be obtained, which will not be elaborated here.

[0113] In operation S413, the difference value of the key information evaluation parameters is determined based on the mean of the preceding key information evaluation and the mean of the subsequent key information evaluation.

[0114] The difference in key information evaluation parameters can characterize the degree of difference between the mean of preceding and subsequent key information evaluations for the current key information evaluation parameter. A smaller difference indicates a smaller impact and contribution of the key information evaluation parameter in determining the first evaluation value, allowing for adjustment of the parameter's weight. Adjusting the parameter's weight can increase its impact and contribution in determining the first evaluation value, thus enabling adaptive adjustment of the key information evaluation parameter's weight.

[0115] For example, (1-ikta / ikba) can be used as the difference value diffik for the key information evaluation parameter kp-i. It is understood that for other key information evaluation parameters among multiple key information evaluation parameters, the corresponding difference values ​​for the key information evaluation parameters can also be determined.

[0116] In operation S414, the weights of the key information evaluation parameters are adjusted based on the differences in the key information evaluation parameters.

[0117] It should be noted that at the first adjustment node of the first weight adjustment cycle, for example, the initial weight of each key information evaluation parameter can be predetermined, and the initial weight of the key information evaluation parameter can be adjusted according to the above embodiment to obtain the adjusted weight of the key information evaluation parameter. For any other adjustment node, the weight of each key information evaluation parameter after the previous weight adjustment can be used as the initial weight, and the initial weight of the key information evaluation parameter can be adjusted according to the above embodiment to obtain the adjusted weight of the key information evaluation parameter.

[0118] For example, the average difference value of each key information evaluation parameter can be calculated to obtain the average difference value, diffak. For any key information evaluation parameter kp-i, the weight wk′ of the adjusted key information evaluation parameter can be obtained using the following formula (3).

[0119] wk′=wk*(1+(diffik-diffak) / diffak) (3)

[0120] Where wk represents the initial weight of the key information evaluation parameter kp-i at any adjustment node in the first weight adjustment period; diffik represents the difference value of the key information evaluation parameter kp-i; and diffak represents the mean difference obtained from multiple key information evaluation parameters.

[0121] According to the information query method of this disclosure, when there are multiple key information evaluation parameters, the weight of each key information evaluation parameter can be adaptively and automatically adjusted according to the corresponding candidate key information, so that the N preceding candidate key information and the N subsequent candidate key information with smaller differences can be determined according to the adjusted weight of the key information evaluation parameters, and the overall candidate key information is more in line with the specific expectations of information query.

[0122] Figure 5 The diagram illustrates the weighting of content information evaluation parameters in an information query method according to yet another embodiment of the present disclosure.

[0123] like Figure 5 As shown, the information query method according to the embodiments of this disclosure can, for example, utilize the following embodiments to implement specific examples of adjusting the weight of the content information evaluation parameters based on the difference values ​​of the content information evaluation parameters.

[0124] In operation S511, M preceding candidate content information ranked first M and M subsequent candidate content information ranked last M of the second evaluation value are determined from multiple candidate content information.

[0125] exist Figure 5 The example illustrates a specific instance of adjusting the weight of a content information evaluation parameter cp-i at an adjustment node j during the second weight adjustment period Ac1.

[0126] exist Figure 5 In the example, a schematic illustration shows an adjustment node j in the second weight adjustment period Ac2. From r candidate content information from ti-1 to ti-r, the M preceding candidate key information with the second evaluation value ranked in the top M are determined. Specifically, this includes the candidate content information top1 ranked first in descending order of the second evaluation value, up to the candidate content information topM ranked M in descending order of the second evaluation value. M and r are both positive integers greater than 1, and M is less than or equal to r.

[0127] In operation S512, for any content information evaluation parameter, the mean of the content information evaluation values ​​of the corresponding M preceding candidate content information and the mean of the content information evaluation values ​​of the M subsequent candidate content information are determined respectively, so as to obtain the mean of the preceding content information evaluation and the mean of the subsequent content information evaluation.

[0128] The content information evaluation value of a certain content information evaluation parameter can be understood as the numerical value corresponding to that content information evaluation parameter. For example, in the example above where the number of shares is used as a content information evaluation parameter to evaluate candidate content information C, x7 is the content information evaluation value of the number of shares.

[0129] exist Figure 5 The example illustrates a specific instance of determining the mean of the preceding content information evaluation, icta, and the mean of the subsequent content information evaluation, icba, for the content information evaluation parameter cp-i.

[0130] exist Figure 5 In the example, the content information evaluation value ict-1 corresponding to candidate content information top1 is illustrated, up to the content information evaluation value ict-M corresponding to candidate content information topM. By averaging the M values ​​from key content evaluation value ict-1 to content information evaluation value ict-M, the mean evaluation value icta of the preceding content information can be obtained. Similarly, the mean evaluation value icba of the subsequent content information can also be obtained, which will not be elaborated here.

[0131] In operation S513, the difference value of the content information evaluation parameters is determined based on the mean evaluation value of the preceding content information and the mean evaluation value of the subsequent content information.

[0132] The numerical difference in content information evaluation parameters can characterize the degree of difference between the mean of preceding and subsequent content information evaluations for the current evaluation parameter. A smaller difference indicates a smaller influence and contribution of the content information evaluation parameter in determining the second evaluation value, allowing for adjustment of its weight. Adjusting the weight of this content information evaluation parameter can then increase its influence and contribution in determining the first evaluation value, thus enabling adaptive adjustment of its weight.

[0133] For example, (1-icta / icba) can be used as the difference value (diffic) for the content information evaluation parameter cp-i. It is understood that for other content information evaluation parameters among multiple content information evaluation parameters, the corresponding difference values ​​can also be determined.

[0134] In operation S514, the weights of the content information evaluation parameters are adjusted based on the differences in the content information evaluation parameters.

[0135] It should be noted that at the first adjustment node of the second weight adjustment cycle, for example, the initial weight of each content information evaluation parameter can be predetermined, and the initial weight of the content information evaluation parameter can be adjusted according to the above embodiment to obtain the adjusted weight of the content information evaluation parameter. For any other adjustment node, the weight of each content information evaluation parameter after the previous weight adjustment can be used as the initial weight, and the initial weight of the content information evaluation parameter can be adjusted according to the above embodiment to obtain the adjusted weight of the content information evaluation parameter.

[0136] For example, the average difference value of each content information evaluation parameter can be calculated to obtain the average difference value diffac. For any key information evaluation parameter cp-i, the adjusted weight wc′ of the key information evaluation parameter can be obtained using the following formula (4).

[0137] wc′=wc*(1+(diffic-diffac) / diffac) (4)

[0138] Wherein, wc represents the initial weight of the key information evaluation parameter cp-i at any adjustment node in the first weight adjustment period; diffic represents the difference value of the content information evaluation parameter cp-i; and diffac represents the mean difference obtained from multiple content information evaluation parameters.

[0139] According to the information query method of this disclosure, when there are multiple content information evaluation parameters, the weight of each content information evaluation parameter can be adaptively and automatically adjusted according to the corresponding candidate content information, so that the M preceding candidate key information and the M subsequent candidate content information with smaller differences can be determined according to the adjusted weight of the content information evaluation parameters, and the overall candidate content information is more in line with the specific expectations of information query.

[0140] For example, according to another embodiment of the information query method of this disclosure, the following specific example can be used to determine at least one candidate key information that matches the query information: based on the query information, existing key information that is more relevant to the query information than a preset value is selected as candidate key information.

[0141] For example, a set of key information can be predetermined, where each element in the set of key information is existing key information.

[0142] It should be noted that, in one scenario, existing key information can be traversed based on the query information to obtain existing key information that is identical to the query information; this identical key information can be used as candidate key information. In another scenario, existing key information can be traversed based on the correlation between the query information and existing key information; existing key information that is different from the query information but has a correlation greater than a preset value can be used as candidate key information.

[0143] According to the information query method of this disclosure, at least one candidate key information can be accurately determined based on the query information, which facilitates the subsequent accurate determination of target content information that better meets the expectations of the target.

[0144] For example, the information query method according to another embodiment of the present disclosure may further include: filtering query information related to the filtering information based on the filtering information.

[0145] For example, the filtering information can be predetermined. The filtering information may include, for example, information that does not comply with relevant laws or regulations.

[0146] According to the information query method of this disclosure, the quality of information query can be improved by filtering related query information.

[0147] For example, the information query method according to another embodiment of this disclosure may also include: pushing target content information.

[0148] For example, "pushing target content information" can be understood as forwarding target content information to the target's terminal in the form of a webpage.

[0149] According to the information query method of this disclosure, by pushing target content information, the target can conveniently and efficiently obtain the target content information on the terminal, thereby satisfying the target's information query needs.

[0150] For example, according to another embodiment of the information query method of this disclosure, the query information also has at least one of the following: relevant evaluation level, push frequency, and associated content.

[0151] The assessment level represents the importance of the queried information, the related content represents the content information related to the queried information, and the push frequency represents the frequency of pushing related content.

[0152] For example, query information can be pushed based on its evaluation level. For instance, the priority of pushing query information can be determined based on its evaluation level. Query information with a higher evaluation level can be pushed first.

[0153] For example, the associated content of the query information can be determined by mapping or other methods, so that the query information can be mapped and associated with the content information.

[0154] For example, the information query method according to the embodiments of this disclosure may further include: configuring the query information according to operation configuration information.

[0155] The operation configuration information includes at least one of the following for the query information: evaluation level, push frequency, and associated content.

[0156] The information query method according to the embodiments of this disclosure can configure at least one of the evaluation level, push frequency and associated content of the query information, which can adapt to the needs of more scenarios.

[0157] For example, for certain current events, you can configure the evaluation level or push priority related to the current event through operation configuration information, so that content information related to the current event can be pushed more frequently.

[0158] Figure 6 A block diagram of an information query device according to an embodiment of the present disclosure is shown schematically.

[0159] like Figure 6 As shown, the information query device 600 of this embodiment includes, for example, a candidate key information determination module 610, a first evaluation value determination module 620, a target key information determination module 630, and a target content information determination module 640.

[0160] The candidate key information determination module 610 is used to determine at least one candidate key information that matches the query information based on the query information.

[0161] The first evaluation value determination module 620 is used to determine the first evaluation value for evaluating candidate key information based on the key information evaluation parameters.

[0162] The target key information determination module 630 is used to determine at least one target key information from at least one candidate key information based on a first evaluation value.

[0163] The target content information determination module 640 is used to determine target content information based on at least one key target information.

[0164] According to the information query device of this disclosure, the target content information determination module includes: a candidate content information determination submodule, a second evaluation value determination submodule, and a target content information determination submodule.

[0165] The candidate content information determination submodule is used to determine at least one candidate content information related to any given target key information.

[0166] The second evaluation value determination submodule is used to determine the second evaluation value for evaluating candidate content information based on the content information evaluation parameters.

[0167] The target content information determination submodule is used to determine the target content information from at least one candidate content information based on a second evaluation value.

[0168] According to the information query device of this disclosure, the key information evaluation parameters include multiple parameters, and each key information evaluation parameter has a corresponding weight; the first evaluation value determination module includes: a first evaluation value determination submodule, used to determine the first evaluation value of the candidate key information based on the weight of the key information evaluation parameters, the key information evaluation parameters, and the candidate key information.

[0169] According to the information query device of this disclosure, the content information evaluation parameters include multiple parameters, and each content information evaluation parameter has a corresponding weight; the second evaluation value determination module includes: a second evaluation value determination submodule, used to determine the second evaluation value of the candidate content information based on the weight of the content information evaluation parameters, the content information evaluation parameters, and the candidate content information.

[0170] The information query device according to the embodiments of this disclosure further includes at least one of the following: a first weight adjustment module and a second weight adjustment module.

[0171] The first weight adjustment module is used to adjust the weights of key information evaluation parameters according to the first weight adjustment cycle.

[0172] The second weight adjustment module is used to adjust the weights of the content information evaluation parameters according to the second weight adjustment cycle.

[0173] According to the information query device of this disclosure, the candidate key information includes multiple items, and the candidate content information includes multiple items.

[0174] The first weight adjustment module includes a first weight adjustment submodule, used to adjust the weight of the key information evaluation parameter at each adjustment node of the first weight adjustment cycle according to the difference value of the key information evaluation parameter, wherein the difference value of the key information evaluation parameter characterizes the degree of influence of the key information evaluation parameter on determining the first evaluation value.

[0175] The second weight adjustment module includes a second weight adjustment submodule, used to adjust the weight of the content information evaluation parameter at each adjustment node of the second weight adjustment cycle according to the difference value of the content information evaluation parameter, wherein the difference value of the content information evaluation parameter characterizes the degree of influence of the content information evaluation parameter on determining the second evaluation value.

[0176] According to the information query device of this disclosure, the first weight adjustment submodule includes: a unit for determining the preceding and following candidate key information, a unit for determining the average value of the preceding and following key information evaluation, a unit for determining the difference value of the key information evaluation parameters, and a first adjustment unit.

[0177] The preceding and following candidate key information determination unit is used to determine, at each adjustment node of the first weight adjustment cycle, N preceding candidate key information items ranked in the top N by the first evaluation value and N following candidate key information items ranked in the bottom N by the first evaluation value from multiple candidate key information items.

[0178] The unit for determining the mean evaluation values ​​of preceding and subsequent key information is used to determine the mean evaluation values ​​of the corresponding N preceding candidate key information and the mean evaluation values ​​of the corresponding N subsequent candidate key information for any key information evaluation parameter, thereby obtaining the mean evaluation values ​​of preceding and subsequent key information.

[0179] The critical information evaluation parameter difference value determination unit is used to determine the difference value of the critical information evaluation parameters based on the mean of the preceding critical information evaluation and the mean of the subsequent critical information evaluation.

[0180] The first adjustment unit is used to adjust the weights of the key information evaluation parameters based on the differences in the key information evaluation parameters.

[0181] According to the information query device of this disclosure, the second weight adjustment submodule includes: a unit for determining preceding and following candidate content information, a unit for determining the average value of preceding and following content information evaluation, a unit for determining the difference value of content information evaluation parameters, and a second adjustment unit.

[0182] The preceding and following candidate content information determination unit is used to determine, at each adjustment node of the second weight adjustment cycle, M preceding candidate content information ranked first M and M following candidate content information ranked last M from multiple candidate content information.

[0183] The unit for determining the mean evaluation values ​​of preceding and subsequent content information uses an evaluation parameter to determine the mean of the evaluation values ​​of the corresponding M preceding candidate content information and the mean of the evaluation values ​​of the M subsequent candidate content information, thus obtaining the mean evaluation values ​​of the preceding and subsequent content information.

[0184] The unit for determining the difference in content information evaluation parameters determines the difference in content information evaluation parameters based on the mean of the preceding content information evaluation and the mean of the subsequent content information evaluation.

[0185] The second adjustment unit is used to adjust the weights of the content information evaluation parameters based on the differences in the content information evaluation parameters.

[0186] According to the information query device of this disclosure, the key information evaluation parameters include at least one of the following: the number of content information related to the candidate key information, the number of objects of interest of the candidate key information, the number of views, the number of forwards, and the number of check-ins; the content information evaluation parameters include at least one of the following: the number of replies to the candidate content information, the number of shares, and the publication time.

[0187] According to the information query device of this disclosure, the candidate key information determination module includes: a candidate key information determination submodule, which is used to select existing key information that is more relevant to the query information than a preset value as candidate key information based on the query information.

[0188] The information query device according to the embodiments of this disclosure further includes: a filtering module, used to filter query information related to the filtering information based on the filtering information.

[0189] The information query device according to the embodiments of this disclosure further includes: a push module for pushing target content information.

[0190] It should be understood that the embodiments of the apparatus portion of this disclosure correspond to the same or similar embodiments of the method portion of this disclosure, and the technical problems solved and the technical effects achieved are also the same or similar. This disclosure will not repeat them here.

[0191] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0192] Figure 7A schematic block diagram of an example electronic device 700 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0193] like Figure 7 As shown, device 700 includes a computing unit 701, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 702 or a computer program loaded from storage unit 708 into random access memory (RAM) 703. RAM 703 may also store various programs and data required for the operation of device 700. The computing unit 701, ROM 702, and RAM 703 are interconnected via bus 704. Input / output (I / O) interface 705 is also connected to bus 704.

[0194] Multiple components in device 700 are connected to I / O interface 705, including: input unit 706, such as keyboard, mouse, etc.; output unit 707, such as various types of monitors, speakers, etc.; storage unit 708, such as disk, optical disk, etc.; and communication unit 709, such as network card, modem, wireless transceiver, etc. Communication unit 709 allows device 700 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0195] The computing unit 701 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 701 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 701 performs the various methods and processes described above, such as information query methods. For example, in some embodiments, the information query method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 708. In some embodiments, part or all of the computer program may be loaded and / or installed on device 700 via ROM 702 and / or communication unit 709. When the computer program is loaded into RAM 703 and executed by the computing unit 701, one or more steps of the information query method described above may be performed. Alternatively, in other embodiments, the computing unit 701 may be configured to perform information query methods by any other suitable means (e.g., by means of firmware).

[0196] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0197] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0198] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0199] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0200] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0201] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other.

[0202] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0203] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. An information retrieval method, comprising: Based on the query information, identify multiple candidate key information that match the query information; For each candidate key information, a first evaluation value is determined based on key information evaluation parameters. The key information evaluation parameters include multiple parameters, each of which has a corresponding weight. The first evaluation value is determined by the weighted sum of the multiple key information evaluation parameters corresponding to the candidate key information. Based on the first evaluation value, at least one target key piece of information is determined from the plurality of candidate key information; and Based on the at least one key target information, determine the target content information; Also includes: At each adjustment node of the first weight adjustment period, for any key information evaluation parameter, the weight of the key information evaluation parameter is adjusted according to the difference value of the key information evaluation parameter. The difference value represents the degree of difference between the mean of the preceding key information evaluation and the mean of the subsequent key information evaluation for the current key information evaluation parameter. The degree of difference represents the degree of influence of the current key information evaluation parameter on determining the first evaluation value. Wherein, the mean of the preceding key information evaluation is the mean of the key information evaluation values ​​of the N candidate key information items ranked first N times for the current key information evaluation parameter, and the mean of the following key information evaluation is the mean of the key information evaluation values ​​of the N candidate key information items ranked last N times for the current key information evaluation parameter, where N is an integer greater than 1.

2. The method according to claim 1, wherein, The step of determining the target content information based on the at least one target key information includes: For any one of the target key information, determine at least one candidate content information related to the target key information; Based on the content information evaluation parameters, a second evaluation value is determined for evaluating the candidate content information; and The target content information is determined from the at least one candidate content information based on the second evaluation value.

3. The method according to claim 2, wherein, The content information evaluation parameters include multiple parameters, each of which has a corresponding weight; determining the second evaluation value for evaluating the candidate content information based on the content information evaluation parameters includes: The second evaluation value of the candidate content information is determined based on the weights of the content information evaluation parameters, the content information evaluation parameters, and the candidate content information.

4. The method according to claim 3, further comprising: The weights of the content information evaluation parameters are adjusted according to the second weight adjustment period.

5. The method according to claim 4, wherein, The candidate content information includes multiple items; adjusting the weights of the content information evaluation parameters according to the second weight adjustment period includes: at each adjustment node of the second weight adjustment period, The weights of the content information evaluation parameters are adjusted based on the differences in the content information evaluation parameters, wherein the differences in the content information evaluation parameters characterize the degree of influence of the content information evaluation parameters on determining the second evaluation value.

6. The method according to claim 5, wherein, The step of adjusting the weights of the key information evaluation parameters based on the differences in the key information evaluation parameters includes: From the plurality of candidate key information, determine the N preceding candidate key information items ranked first N times by the first evaluation value and the N subsequent candidate key information items ranked last N times by the first evaluation value; For any one of the key information evaluation parameters, the mean of the key information evaluation values ​​of the corresponding N preceding candidate key information and the mean of the key information evaluation values ​​of the N subsequent candidate key information are determined respectively, so as to obtain the mean of the preceding key information evaluation and the mean of the subsequent key information evaluation. Based on the mean values ​​of the preceding key information evaluations and the mean values ​​of the subsequent key information evaluations, the difference in the key information evaluation parameters is determined; and The weights of the key information evaluation parameters are adjusted based on the differences in the key information evaluation parameters.

7. The method according to claim 5, wherein, The step of adjusting the weights of the content information evaluation parameters based on the differences in the content information evaluation parameters includes: From the plurality of candidate content information, determine the M preceding candidate content information ranked first M by the second evaluation value and the M subsequent candidate content information ranked last M by the second evaluation value; For any one of the content information evaluation parameters, the mean of the content information evaluation values ​​of the corresponding M preceding candidate content information and the mean of the content information evaluation values ​​of the M subsequent candidate content information are determined respectively, so as to obtain the mean of the preceding content information evaluation and the mean of the subsequent content information evaluation. Based on the mean evaluation values ​​of the preceding content information and the mean evaluation values ​​of the subsequent content information, the difference in the content information evaluation parameters is determined; and The weights of the content information evaluation parameters are adjusted based on the differences in the evaluation parameters.

8. The method according to claim 2, wherein, The key information evaluation parameters include at least one of the following: the number of content information related to the candidate key information, the number of followers of the candidate key information, the number of views, the number of reposts, and the number of check-ins; the content information evaluation parameters include at least one of the following: the number of replies to the candidate content information, the number of shares, and the publication time.

9. The method according to any one of claims 1-8, wherein, The step of determining multiple candidate key information matching the query information based on the query information includes: Based on the query information, existing key information that is more relevant to the query information than a preset value is selected as candidate key information.

10. The method according to any one of claims 1-8, further comprising: Before determining multiple candidate key information matching the query information based on the query information, the query information related to the filtering information is filtered based on the filtering information.

11. The method according to any one of claims 1-8, further comprising: The target content information is pushed.

12. An information query device, comprising: The candidate key information determination module is used to determine multiple candidate key information that match the query information based on the query information. The first evaluation value determination module is used to determine a first evaluation value for each candidate key information based on key information evaluation parameters. The key information evaluation parameters include multiple parameters, each of which has a corresponding weight. The first evaluation value is determined by the weighted sum of the multiple key information evaluation parameters corresponding to the candidate key information. A target key information determination module is configured to determine at least one target key information from the plurality of candidate key information based on the first evaluation value; and The target content information determination module is used to determine target content information based on the at least one target key information; Also includes: The first weight adjustment module is used to adjust the weight of any key information evaluation parameter at each adjustment node in the first weight adjustment period, based on the difference value of the key information evaluation parameter. The difference value represents the degree of difference between the mean of the preceding key information evaluation and the mean of the subsequent key information evaluation for the current key information evaluation parameter, and the degree of difference represents the degree of influence of the current key information evaluation parameter on determining the first evaluation value. Wherein, the mean of the preceding key information evaluation is the mean of the key information evaluation values ​​of the N candidate key information items ranked first N times for the current key information evaluation parameter, and the mean of the following key information evaluation is the mean of the key information evaluation values ​​of the N candidate key information items ranked last N times for the current key information evaluation parameter, where N is an integer greater than 1.

13. The apparatus according to claim 12, wherein, The target content information determination module includes: The candidate content information determination submodule is used to determine at least one candidate content information related to any one of the target key information. The second evaluation value determination submodule is used to determine a second evaluation value for evaluating the candidate content information based on the content information evaluation parameters; and The target content information determination submodule is used to determine the target content information from the at least one candidate content information based on the second evaluation value.

14. The apparatus according to claim 13, wherein, The content information evaluation parameters include multiple parameters, and each of the content information evaluation parameters has a corresponding weight. The second evaluation value determination module includes: The second evaluation value determination submodule is used to determine the second evaluation value of the candidate content information based on the weights of the content information evaluation parameters, the content information evaluation parameters, and the candidate content information.

15. The apparatus of claim 14, further comprising: The second weight adjustment module is used to adjust the weights of the content information evaluation parameters according to the second weight adjustment period.

16. The apparatus according to claim 15, wherein, The candidate content information includes multiple items; The second weight adjustment module includes a second weight adjustment submodule, used to adjust the weight of the content information evaluation parameter at each adjustment node of the second weight adjustment cycle according to the difference value of the content information evaluation parameter, wherein the difference value of the content information evaluation parameter characterizes the degree of influence of the content information evaluation parameter on determining the second evaluation value.

17. The apparatus according to claim 16, wherein, The first weight adjustment module includes a first weight adjustment submodule, which includes: The preceding and following candidate key information determination unit is used to determine, at each adjustment node of the first weight adjustment period, N preceding candidate key information items ranked in the first N and N following candidate key information items ranked in the last N from the plurality of candidate key information items. The unit for determining the mean evaluation values ​​of preceding and subsequent key information is used to determine the mean evaluation values ​​of the key information of the corresponding N preceding candidate key information and the mean evaluation values ​​of the key information of the N subsequent candidate key information for any one of the key information evaluation parameters, so as to obtain the mean evaluation value of the preceding key information and the mean evaluation value of the subsequent key information. A key information evaluation parameter difference value determination unit is used to determine the difference value of the key information evaluation parameter based on the mean of the preceding key information evaluation and the mean of the subsequent key information evaluation; and The first adjustment unit is used to adjust the weight of the key information evaluation parameters based on the difference values ​​of the key information evaluation parameters.

18. The apparatus according to claim 16, wherein, The second weight adjustment submodule includes: The preceding and following candidate content information determination unit is used to determine, at each adjustment node of the second weight adjustment period, M preceding candidate content information in which the second evaluation value ranks first M and M following candidate content information in which the second evaluation value ranks last M from the plurality of candidate content information. The unit for determining the mean evaluation value of preceding and subsequent content information uses the content information evaluation parameter to determine the mean of the content information evaluation values ​​of the corresponding M preceding candidate content information and the mean of the content information evaluation values ​​of the M subsequent candidate content information, thereby obtaining the mean evaluation value of preceding content information and the mean evaluation value of subsequent content information. The content information evaluation parameter difference value determination unit determines the difference value of the content information evaluation parameter based on the mean of the preceding content information evaluation and the mean of the subsequent content information evaluation; and The second adjustment unit is used to adjust the weight of the content information evaluation parameters based on the difference values ​​of the content information evaluation parameters.

19. The apparatus according to claim 13, wherein, The key information evaluation parameters include at least one of the following: the number of content information related to the candidate key information, the number of followers of the candidate key information, the number of views, the number of reposts, and the number of check-ins; the content information evaluation parameters include at least one of the following: the number of replies to the candidate content information, the number of shares, and the publication time.

20. The apparatus according to any one of claims 12-19, wherein, The candidate key information determination module includes: The candidate key information determination submodule is used to select existing key information that is more relevant to the query information than a preset value as the candidate key information based on the query information.

21. The apparatus according to any one of claims 12-19, further comprising: The filtering module is used to filter the query information related to the filtering information according to the filtering information before determining multiple candidate key information matching the query information based on the query information.

22. The apparatus according to any one of claims 12-19, further comprising: The push module is used to push the target content information.

23. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-11.

24. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-11.

25. A computer program product comprising a computer program stored on at least one of a readable storage medium and an electronic device, the computer program implementing the method according to any one of claims 1-11 when executed by a processor.

Images