Demand evaluation information generation method, demand evaluation information display method, and apparatus

Abstract

The present disclosure provides a demand evaluation information generation method, a demand evaluation information display method and device, relates to the field of data processing, and particularly to the field of search sentence processing. The specific implementation scheme is as follows: determining a target search sentence to be analyzed; obtaining search volume information of the target search sentence in a first time period; wherein the first time period is a time period before the current time, and the search volume information of any search sentence in a time period includes the search volume of the search sentence in each statistical period in the time period; determining an estimated volume corresponding to the target search sentence based on the obtained search volume information; wherein the estimated volume is used to represent the search demand of the target search sentence in a second time period, and the second time period is a time period after the current time; and generating demand evaluation information of the target search sentence based on the estimated volume corresponding to the target search sentence. Through the present scheme, demand evaluation information that can accurately reflect the actual demand can be generated.

Description

Technical Field

[0001] This disclosure relates to the field of data processing technology, and in particular to the field of retrieval statement processing technology, specifically to a method for generating demand assessment information, a method for displaying demand assessment information, and an apparatus. Background Technology

[0002] Knowledge content production refers to the creation of knowledge content that meets user needs in various fields and categories, using multimedia formats such as text, images, videos, and audio. Since the search volume of a query is a good indicator of user demand, a common strategy for knowledge content production is to prioritize the production of knowledge content corresponding to search queries with higher search volumes.

[0003] In related technologies, the average search volume of a search query over the past week or the total search volume over the past three days is used as the demand assessment information for that search query. The demand assessment information is information that indicates the degree of demand for the production of knowledge content. Summary of the Invention

[0004] This disclosure provides a method and apparatus for generating demand assessment information that accurately reflects actual needs. In addition, this disclosure also provides a method and apparatus for displaying demand assessment information that accurately reflects actual needs.

[0005] According to one aspect of this disclosure, a method for generating demand assessment information is provided, comprising:

[0006] Determine the target search query to be analyzed;

[0007] Obtain the search volume information of the target search statement within a first time period; wherein, the first time period is the time period before the current time, and the search volume information of any search statement within a time period includes: the search volume of the search statement in each statistical period within the time period.

[0008] Based on the obtained search volume information, the estimated volume corresponding to the target search statement is determined; wherein, the estimated volume is used to characterize the search demand for the target search statement in a second time period, the second time period being the time period after the current time;

[0009] Based on the estimated quantity corresponding to the target search statement, demand assessment information for the target search statement is generated.

[0010] According to another aspect of this disclosure, a method for displaying demand assessment information is provided, the method comprising:

[0011] Obtain filtering information for the search query;

[0012] From the various search statements stored in the demand assessment database, target search statements that match the filtering information are selected; wherein, the demand assessment database stores multiple search statements and demand assessment information for each search statement, and the demand assessment information for each search statement is determined according to any of the demand assessment information generation methods described above.

[0013] From the demand assessment database, determine the demand assessment information for the target search statement; output the target search statement and its demand assessment information.

[0014] According to another aspect of this disclosure, a demand assessment information generation apparatus is provided, comprising:

[0015] The first statement determination module is used to determine the target retrieval statement to be analyzed.

[0016] The first information acquisition module is used to acquire the search volume information of the target search statement within a first time period; wherein, the first time period is the time period before the current time, and the search volume information of any search statement within a time period includes: the search volume of the search statement in each statistical period within the time period.

[0017] The estimated quantity determination module is used to determine the estimated quantity corresponding to the target search statement based on the acquired search volume information; wherein, the estimated quantity is used to characterize the search demand of the target search statement in a second time period, the second time period being the time period after the current time;

[0018] The information generation module is used to generate demand assessment information for the target search statement based on the estimated quantity corresponding to the target search statement.

[0019] According to another aspect of this disclosure, a demand assessment information display device is provided, the device comprising:

[0020] The filter information acquisition module is used to acquire filter information for the search query.

[0021] The statement filtering module is used to filter target search statements that match the filtering information from the search statements stored in the demand assessment database; wherein, the demand assessment database stores multiple search statements and demand assessment information for each search statement, and the demand assessment information for each search statement is determined by the demand assessment information generation device according to any one of the above.

[0022] The information determination module is used to determine the demand assessment information of the target retrieval statement from the demand assessment database;

[0023] The information output module is used to output the target search statement and the demand evaluation information of the target search statement.

[0024] According to another aspect of this disclosure, an electronic device is provided, comprising:

[0025] At least one processor; and

[0026] A memory communicatively connected to the at least one processor; wherein,

[0027] The memory stores instructions that can be executed by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform a demand assessment information generation method and a demand assessment information display method.

[0028] According to another aspect of this disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause the computer to execute a demand assessment information generation method and a demand assessment information display method.

[0029] According to another aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements a method for generating demand assessment information and a method for displaying demand assessment information.

[0030] 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

[0031] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0032] Figure 1 This is a schematic diagram based on the first embodiment of the present disclosure;

[0033] Figure 2 This is a schematic diagram according to the second embodiment of the present disclosure;

[0034] Figure 3 This is a schematic diagram according to the third embodiment of the present disclosure;

[0035] Figure 4 This is a schematic diagram according to the fourth embodiment of the present disclosure;

[0036] Figure 5 This is a schematic diagram according to the fifth embodiment of the present disclosure;

[0037] Figure 6 This is a schematic diagram according to the sixth embodiment of the present disclosure;

[0038] Figure 7This is a block diagram of an electronic device used to implement the requirement assessment information generation method of the embodiments of this disclosure; Detailed Implementation

[0039] 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.

[0040] Knowledge content production refers to the creation of knowledge content that meets user needs in various multimedia formats such as text, images, videos, and audio, across different domains and verticals. For example, for clients capable of content search, business personnel can produce videos, images, and text content that meets user needs, providing content that satisfies their requirements when users use the client to search for content. Furthermore, since the search volume of a query is a good indicator of user demand, a common strategy for knowledge content production is to prioritize the production of knowledge content corresponding to search queries with higher search volumes.

[0041] With the development of the Internet, a large number of non-repeating search statements are generated on the Internet every day. Among them, high-frequency search statements account for about 20%, while medium- and long-tail search statements account for more than 40%. The high-frequency search statements mentioned above are those with an average daily search volume of more than 10, while the medium- and long-tail search statements mentioned above are those with an average daily search volume of more than 2 and no more than 10.

[0042] How to rationally quantify the value of search queries under limited productivity, and thus efficiently utilize search queries to guide knowledge business lines in producing knowledge content that meets user needs, is the core challenge currently facing the industry.

[0043] In related technologies, the average search volume of a search term over the past week or the total search volume over the past three days is used as demand assessment information for that search term. However, this approach does not consider the significant changes in search volume over time for most search terms. Therefore, for time-sensitive and frequently searched terms, if the production cycle is long, not only can knowledge content that meets user needs not be generated in a timely manner, but the timeliness of the generated knowledge content is also poor, often resulting in lower-than-expected utilization and a low return on investment.

[0044] Therefore, it is evident that the relevant technologies suffer from at least the following technical problems:

[0045] 1. Since the search volume of a search query changes significantly over time, if the average search volume in the past week or the total search volume in the past three days is used as the search information, the search information often cannot accurately reflect the actual needs.

[0046] 2. The demand retrieval information provided by related technologies often fails to generate knowledge content that matches the actual needs.

[0047] To address the problem that demand assessment information in related technologies cannot accurately reflect actual needs, this disclosure provides a method for generating demand assessment information.

[0048] It should be noted that, in specific applications, the requirement assessment information generation method provided in this disclosure can be applied to various electronic devices, such as personal computers, servers, and other devices with data processing capabilities. Furthermore, it is understood that the requirement assessment information generation can be implemented through software, hardware, or a combination of both. Moreover, this requirement assessment information generation method can be applied to any scenario where requirement assessment exists. For example, for a client capable of content search, a user can perform content retrieval through the client; therefore, the search query entered by the user during content retrieval can be assessed using this requirement assessment information generation method. Similarly, for a client capable of multimedia content playback, a user can perform multimedia content retrieval through the client; therefore, the search query entered by the user during multimedia content retrieval can also be assessed using this requirement assessment information generation method.

[0049] The method for generating demand assessment information provided in this embodiment may include:

[0050] Determine the target search query to be analyzed;

[0051] Obtain the search volume information of the target search statement within a first time period; wherein, the first time period is the time period before the current time, and the search volume information of any search statement within a time period includes: the search volume of the search statement in each statistical period within that time period;

[0052] Based on the obtained search volume information, the estimated volume corresponding to the target search statement is determined; wherein, the estimated volume is used to characterize the search demand of the target search statement in the second time period, which is the time period after the current time.

[0053] Based on the estimated volume corresponding to the target search statement, demand assessment information for the target search statement is generated.

[0054] The solution provided in this disclosure utilizes the search volume information of the target search statement in a first time period before the current time to determine the estimated volume of the target search statement in a second time period after the current time. Based on the determined estimated volume, demand assessment information for the target search statement is generated. Since the estimated volume represents the search demand of the target search statement in the second time period, the demand assessment information can accurately reflect the actual demand of the target search statement in the future second time period. Therefore, the solution provided in this disclosure can solve the problem in related technologies where demand assessment information cannot accurately reflect actual demand.

[0055] Furthermore, since demand assessment information can accurately reflect actual needs, when using demand assessment information to guide knowledge content production, knowledge content that matches actual needs can be produced. The solution provided in this disclosure provides a foundation for producing knowledge content that matches actual needs.

[0056] The following describes a method for generating demand assessment information according to an embodiment of this disclosure, with reference to the accompanying drawings.

[0057] like Figure 1 As shown in the embodiments of this disclosure, a method for generating demand assessment information may include the following steps:

[0058] S101, Determine the target search statement to be analyzed;

[0059] The target search statement is the search statement used to determine the requirements assessment information. Different methods can be used to determine the target search statement depending on the actual application scenario. For example, the methods for determining the target search statement include at least one of the following two methods:

[0060] In the first determination method, when there is a need to analyze a specified search statement, the search statement referred to by the received specified operation can be used as the target search statement. The specified operation can include selection operations, input operations, etc.

[0061] The second method involves using search queries that meet specific filtering criteria as target queries when there is a need to analyze those queries. These filtering criteria can be determined based on needs and experience; for example, they could be set within a certain time period, or the search frequency within that time period exceeds a predetermined threshold. This specific time period can be the period preceding the moment the query analysis requirement arises.

[0062] Alternatively, in one implementation, the above filtering condition can be: search statements with a search frequency greater than a preset frequency threshold within a first time period. Therefore, determining the target search statement to be analyzed in this step can include:

[0063] From the search queries within the first time period, those queries with a search frequency greater than a preset frequency threshold are selected as target search queries for analysis. By selecting target search queries with a search frequency greater than the preset frequency threshold, it can be ensured that the target search queries are those with a certain demand.

[0064] The preset frequency threshold can be determined based on needs and experience, such as once per day, twice per week, etc.

[0065] The first time period mentioned above can be a period of time prior to the current time, where the current time is the time when this method was executed. Optionally, in one implementation, the first time period can be a period of time ending at the current time and lasting for a first specified duration. The first specified duration can be determined based on requirements and experience, such as 3 days, 1 week, 10 days, etc. If the first specified duration is 1 week and the current time is September 8, 2021, then the first time period is [September 2, 2021, September 8, 2021]. Optionally, in another implementation, the first time period can be N1 consecutive statistical periods preceding the current period. For example, if the statistical period is one week, then the first time period is N1 consecutive weeks preceding the current week, i.e., N1 consecutive weeks preceding the current week.

[0066] The process described above, which filters search statements with a search frequency greater than a preset frequency threshold from all search statements within the first time period, involves first obtaining all search statements within the first time period, then counting the number of times each search statement appears within the first time period. Subsequently, the ratio of the number of times each search statement appears to the number of times it appears within the first time period can be calculated to obtain the search frequency of each search statement. Based on the search frequency of each search statement, search statements with a search frequency greater than the preset frequency threshold are then filtered out.

[0067] In addition, it is understandable that when selecting the target search statement, the selected time period is the first time period, which is the time period used to obtain the search volume information of the target search statement in the subsequent S102. This can ensure that the target search statement appears in the first time period and avoid the problem of invalid data caused by the target search statement not appearing in the first time period after filtering the target search statement using other time periods.

[0068] S102, Obtain the search volume information of the target search statement within the first time period;

[0069] The search volume information for any search query within a time period includes: the search volume for that search query in each statistical period within that time period. Each statistical period can be determined based on experience and needs, for example, it can be 1 day or 1 week.

[0070] After determining the target search query, the search volume of the target search query in each statistical period within the first time period can be read from the search data generated within the first time period.

[0071] For example, as shown in Table 1, the search volume distribution of the target search statement in each statistical period within the first time period is shown.

[0072] Table 1

[0073] Statistical period 1 Statistical period 2 Statistical period 3 Statistical period 4 3 4 2 1

[0074] The search volume information for the target search statement may include (3,4,2,1), or include {(statistical period 1,3),(statistical period 2,4),(statistical period 3,2),(statistical period 4,1)}. S103, Based on the obtained search volume information, determine the estimated volume corresponding to the target search statement;

[0075] The estimated quantity is used to characterize the retrieval demand of the target retrieval statement in the second time period. For example, the estimated quantity can be the total retrieval volume of the target retrieval statement in the second time period, or it can also be the retrieval volume of the target retrieval statement in each statistical period of the second time period, or it can also be the average retrieval volume of the target retrieval statement in each statistical period of the second time period, etc., all of which are reasonable.

[0076] Since the search volume information includes the search volume of the target search statement in each statistical period within the first time period, the search volume information of the target search statement can reflect the changing trend of the search volume of the target search statement. Therefore, based on the changing trend of the search volume of the target search statement, the estimated volume of the target search statement in the second time period can be predicted.

[0077] For example, the search volume of the target search statement in each statistical period within the first time period can be fitted to obtain a target change function of time and search volume, and then the estimated volume of the target search statement in the second time period can be determined using the target change function. Alternatively, the estimated volume of the target search statement in the second time period can also be determined using a neural network model, which will be described in detail in subsequent embodiments and will not be repeated here.

[0078] Furthermore, the aforementioned second time period refers to the time period following the current time. Optionally, in one implementation, the second time period can be a time period starting from the current time and lasting for a second specified duration. This second specified duration can be determined based on requirements and experience, such as 3 days, 1 week, 10 days, etc. If the second specified duration is 1 week, and the date is September 8, 2021, then the second time period would be [September 8, 2021, September 15, 2021]. Optionally, in another implementation, the second time period can be N² consecutive periods following the current period. For example, if the period is one week, then the second time period would be N² consecutive weeks following the current week.

[0079] It should be emphasized that, in order to improve the accuracy of the determined estimates, the duration of the first time period can be no less than the duration of the second time period. For example, the duration of the first time period can be equal to or greater than the duration of the second time period.

[0080] S104, Based on the estimated quantity corresponding to the target search statement, generate demand assessment information for the target search statement.

[0081] In this step, after obtaining the estimated volume of the target search query within the second time period, the demand assessment information for the target search query can be further determined. There are many ways to generate demand assessment information; for example, at least one of the following methods is included:

[0082] The first approach is to use the obtained estimates as demand assessment information for the target retrieval statement.

[0083] The second approach involves determining the demand level corresponding to the obtained estimate based on a pre-built correspondence between the estimated quantity and the demand level, using this as the demand assessment information for the target retrieval statement.

[0084] The aforementioned demand levels can be determined based on demand and experience, such as high demand, medium demand, low demand, or first-level demand, second-level demand, third-level demand, etc. The correspondence between estimated quantities and demand levels can be defined based on demand and experience. Each demand level can correspond to a range of estimated quantities, and all estimated quantities within that range correspond to that demand level.

[0085] The solution provided in this disclosure utilizes the search volume information of the target search statement in a first time period before the current time to determine the estimated volume of the target search statement in a second time period after the current time. Based on the determined estimated volume, demand assessment information for the target search statement is generated. Since the estimated volume represents the search demand of the target search statement in the second time period, the demand assessment information can accurately reflect the actual demand of the target search statement in the future second time period. Therefore, the solution provided in this disclosure can solve the problem in related technologies where demand assessment information cannot accurately reflect actual demand.

[0086] Furthermore, since demand assessment information can accurately reflect actual needs, when using demand assessment information to guide knowledge content production, knowledge content that matches actual needs can be produced. The solution provided in this disclosure provides a foundation for producing knowledge content that matches actual needs.

[0087] Optionally, in another embodiment of this disclosure, after generating demand assessment information for the target search statement based on the estimated quantity corresponding to the target search statement, the method for generating the demand assessment information may further include:

[0088] Write the target search statement and its requirement assessment information into the requirement assessment database.

[0089] Understandably, when there are multiple target search statements, when writing these statements and their respective requirement assessment information into the requirement assessment database, the target search statements can be clustered to obtain a cluster title and its corresponding requirement assessment information. Furthermore, the cluster title and requirement assessment information are recorded, along with the hierarchical relationship between the cluster title and the corresponding target search statement. This way, when querying the requirement assessment database subsequently, the cluster title and its corresponding requirement assessment information can be displayed first. Upon receiving instructions for further refined display, the individual target search statements corresponding to the cluster title and their corresponding requirement platform information are then displayed. This approach makes information recording and output more hierarchical.

[0090] In addition, target search statements and their demand assessment information can be periodically written to the demand assessment database. Specifically, this can be done weekly, selecting the current date and identifying the target search statements to be predicted. Then, the demand assessment information generation method provided in this embodiment is used to determine the demand assessment information for the target search statements, and finally, the target search statements and their demand assessment information are written to the demand assessment database. This ensures that the demand assessment database can store the latest target search statements and their demand assessment information in real time.

[0091] The solution provided in this disclosure can generate demand assessment information that accurately reflects actual needs, and provides a foundation for producing knowledge content that matches actual needs. Furthermore, writing the target search statement and its demand assessment information into a demand assessment database provides a foundation for subsequent utilization of the target search statement and its demand assessment information.

[0092] based on Figure 1 The illustrated embodiment, as Figure 2 As shown, another embodiment of the present disclosure provides a method for generating demand assessment information, which may include the following steps:

[0093] S201, Determine the target search statement to be analyzed;

[0094] S202, Obtain the search volume information of the target search statement within the first time period;

[0095] The first time period is the time period before the current time. The search volume information of any search statement within a time period includes: the search volume of the search statement in each statistical period within that time period.

[0096] In this embodiment, S201-S202 are the same as S101-S102 in the above embodiment, and will not be described again here.

[0097] S203, Based on the obtained search volume information, construct feature data of the target search statement within the first time period;

[0098] In this step, the feature data can be a feature vector. At this time, the search volume of the target search statement in each statistical period within the first time period can be obtained from the search volume information, and then the search volume of the target search statement in each statistical period can be used as a dimension value of the feature vector.

[0099] For example, if the retrieval volume information is: {(statistical period 1,3),(statistical period 2,4),(statistical period 3,2),(statistical period 4,1)}, then the constructed feature vector is (3,4,2,1).

[0100] Optionally, the feature data may also include other feature values ​​that process the search volume information. In this case, the feature data for the target search statement within the first time period, constructed based on the acquired search volume information, may include:

[0101] Calculate the mean and / or variance of each search volume in the acquired search volume information, and construct a feature vector using the search volume included in the acquired search volume information and the calculated mean and / or variance, which serves as the feature data of the target search statement in the first time period.

[0102] In this step, if it is necessary to calculate the average value of each search volume in the obtained search information, you can first calculate the sum of each search volume, and then divide the calculated sum of search volumes by the number of statistical periods in the first time period to obtain the average value of the target search statement in each statistical period in the first time period.

[0103] To calculate the variance of each search quantity in the retrieved information, you can substitute each search quantity into the variance calculation formula to obtain the variance of each search quantity.

[0104] After calculating the mean / variance of each search quantity, a feature vector can be constructed based on the obtained search quantity information, including the search quantity itself, and the calculated mean / or variance. In one implementation, each search quantity and the calculated mean / or variance can be directly used as one dimension of the feature vector. In another implementation, a logarithmic transformation can be performed on each search quantity and the calculated mean / or variance, and the transformed values ​​can then be used as one dimension of the feature vector.

[0105] S204. Using a pre-trained prediction model, the feature data of the target retrieval statement is processed to obtain the prediction value corresponding to the target retrieval statement.

[0106] The prediction model is trained based on sample data and corresponding labeled data. The sample data consists of the feature data of a specified search query within a sample time period, and the labeled data is used to characterize the search demand of the specified search query within a labeled time period. The sample time period is the time period before the baseline time, and the labeled time period is the time period after the baseline time.

[0107] The aforementioned reference time can be any specified historical time. For example, if the reference time is January 15, 2021, then the sample time period can be [January 8, 2021, January 15, 2021], and the labeled time period can be [January 15, 2021, January 22, 2021].

[0108] Optionally, the duration of the sample time period can be the same as the duration of the first time period, and the duration of the labeled time period can be the same as the duration of the second time period. Furthermore, the time interval between the sample time period and the labeled time period is the same as the interval between the first time period and the second time period, such as 0.

[0109] Specifically, the feature data of the target retrieval statement can be input into the prediction model, and the data output by the prediction model can be used as the prediction value corresponding to the target retrieval statement.

[0110] The labeled data corresponding to the above sample data can be the total number of searches for the specified search statement within the labeled time period, or the estimated number of searches for the specified search statement within each statistical period of the labeled time period, or the estimated number of searches for the specified search statement within each statistical period of the labeled time period. All of these are reasonable.

[0111] The specific training method for the prediction model will be described in subsequent embodiments and will not be repeated here.

[0112] S205, Based on the estimated quantity corresponding to the target search statement, generate demand assessment information for the target search statement.

[0113] In this embodiment, S205 is the same as S104 in the above embodiment, and will not be described again here.

[0114] The above-described solution provided in this disclosure can generate demand assessment information that accurately reflects actual needs and provides a foundation for producing knowledge content that matches actual needs. Furthermore, a predictive estimation model can be used to predict the estimated volume of target search statements in the second time period, thus providing a foundation for generating demand assessment information that accurately reflects actual needs. Moreover, through a predictive estimation detection model, the estimated volume of target search statements in the second time period can be predicted accurately and quickly.

[0115] based on Figure 2 The illustrated embodiment, as Figure 3 As shown, in another embodiment of the demand assessment information generation method provided by this disclosure, the training method for training the prediction model is as follows:

[0116] S301, Obtain the first search volume information of the specified search statement within the sample time period and the second search volume information of the specified search statement within the labeled time period from the training dataset;

[0117] The training dataset may contain first search volume information for each search statement within the sample time period, and second search volume information for each search statement within the labeled time period. The specified search statement can be any search statement within the sample time period, or a search statement with a search frequency greater than a preset frequency threshold within the sample time period. After determining the search statement, the first search volume information for the specified search statement within the sample time period, and the second search volume information for the specified search statement within the labeled time period, can be obtained from the training dataset.

[0118] The training dataset mentioned above can be pre-built. Optionally, a baseline time can be pre-specified to determine the sample time periods after the baseline time and the labeled time periods before the baseline time, thereby constructing the training dataset.

[0119] In one implementation, after determining the sample time period and the labeled time period, the various search statements existing within the sample time period can be identified. Then, the first search volume information of each search statement within the sample time period and the second search volume information within the labeled time period can be obtained. Finally, the training dataset is constructed using each search statement and the first and second search volume information of each search statement.

[0120] It is important to emphasize that the training dataset can contain multiple pairs of sample time periods and labeled time periods, with each pair corresponding to a baseline time. As shown in Table 2:

[0121] Table 2

[0122] Training dataset Sample time period Mark time period Baseline time Training set 1 20200422 20200930 20200708 Training set 2 20200429 20201007 20200715 Training set 3 20200506 20201014 20200722 … … … … training set n 20201111 20210421 20210127

[0123] Each training set consists of a pair of sample time periods and labeled time periods. Taking training set 1 as an example, the base time is July 8, 2020, its sample time periods are [April 22, 2020, July 8, 2020], and its labeled time periods are [July 8, 2020, September 30, 2020].

[0124] S302, Based on the first search volume information, generate feature data of the specified search statement within the sample time period as sample data, and based on the second search volume information, generate labeled data of the specified search statement within the labeled time period.

[0125] The process of determining the feature data of the specified search statement within the sample time period is the same as or similar to the process of determining the feature data of the target search statement within the first time period, and will not be repeated here.

[0126] The labeled data for the specified search statement within the labeled time period may include at least one of the following: the total number of searches within the labeled time period, the search volume in each statistical period within the labeled time period, and the average search volume in each statistical period within the labeled time period.

[0127] If the labeled data includes the total number of searches, the search volumes for each statistical period in the second search volume information can be summed to obtain the total search volume. If the labeled data includes the search volume for each statistical period within the labeled time period, the second search volume information can be directly used as part of the labeled data. If the labeled data includes the average search volume for each statistical period within the labeled time period, the total search volume can be calculated using the second search volume information, and then averaged to obtain the search volume for each statistical period within the labeled time period.

[0128] Optionally, the labeled data can be determined according to requirements, and it can take various forms, such as:

[0129] In one approach, the total number of searches within the labeled time period or the average number of searches within each statistical period within the labeled time period can be used as the labeled data.

[0130] In another approach, the labeled data may contain multiple values, such as the search volume in each statistical period within the labeled time period, or at least two of the following: the search volume in each statistical period within the labeled time period, the total search volume within the labeled time period, and the average search volume in each statistical period within the labeled time period. In this case, the labeled data can be a labeled vector.

[0131] For example, in the first scenario, the labeled data is the search volume in each statistical period within the labeled time period. The labeled data can be (A1, A2, ..., An), where A1, A2, ..., An are the search volumes of the specified search statement in each statistical period within the labeled time period.

[0132] In the second scenario, the labeled data includes the search volume in each statistical period within the labeled time period and the total search volume within the labeled time period. In this case, the labeled data can be (A1, A2, ..., An, B), where B is the total search volume within the labeled time period.

[0133] In the third scenario, the labeled data includes the search volume in each statistical period within the labeled time period and the average search volume in each statistical period within the labeled time period. The labeled data can be (A1, A2, ..., An, C), where B is the average search volume in each statistical period within the labeled time period.

[0134] In the fourth scenario, the labeled data includes the total number of searches within the labeled time period and the average number of searches within each statistical period within the labeled time period. In this case, the labeled data can be (B, C).

[0135] S303, Input the sample data into the neural network model to be trained, so that the neural network model can predict the estimated quantity of the specified search statement within the labeled time period based on the sample data, and use it as prediction data;

[0136] In order to train the neural network model to be trained, in this step, sample data can be input into the neural network model to obtain the prediction of the specified sample model within the labeled time period.

[0137] S304, Calculate the loss function value of the neural network model based on the predicted data and labeled data;

[0138] After obtaining the 3D data output by the neural network model, the loss function value of the neural network model can be calculated based on the predicted data and labeled data. The loss function value can be used to characterize the difference between the predicted data output by the neural network model and the ideal labeled data.

[0139] Optionally, in one implementation, the difference between the predicted data and the labeled data in the same dimension can be calculated, and the sum of the differences in each dimension can be used as the loss function value of the neural network model.

[0140] For example, if the labeled data is (a1, a2, ..., an) and the predicted data is (b1, b2, ..., bn), then...

[0141] S305, Adjust the neural network model parameters based on the loss function value;

[0142] For neural network models, the greater the loss, the larger the range of parameter adjustments required. Therefore, the parameters of the neural network model can be adjusted based on the actual situation and needs, taking into account the resulting loss. Optionally, parameter tuning algorithms such as gradient descent can be used to adjust the neural network model parameters based on the loss function value.

[0143] S306, determine whether all retrieval information in the training sample set has been utilized. If yes, end the training; otherwise, return to execute S301.

[0144] After adjusting the neural network model parameters based on the loss function value, the next training iteration can be performed until all the retrieval information in the training sample set has been utilized.

[0145] The above-mentioned solution provided in this disclosure can generate demand assessment information that accurately reflects actual needs and provides a foundation for producing knowledge content that matches actual needs. Furthermore, by training the prediction model, it provides a foundation for generating demand assessment information that accurately reflects actual needs.

[0146] It should be noted that the estimated quantity prediction model in this embodiment is not a model for a specific user and cannot reflect the personal information of a specific user.

[0147] 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 relevant laws and regulations and do not violate public order and good morals. The search statements in this embodiment may be derived from publicly available datasets.

[0148] To better understand the solution provided in this disclosure, in one embodiment of this disclosure, taking 12 weeks as a specified duration as an example, the solution provided in this disclosure is described below:

[0149] First, the target search query can be determined based on the log data of mobile users' searches within the current week (i.e., within the current week), or the target search query can be specified to obtain the search volume of the target search query within the historical 12 weeks between the current week.

[0150] Then, logarithmic transformation is performed on the search volume of the target search statement over the past 12 weeks, as well as the mean and variance of the search volume of the target search statement over the past 12 weeks, to obtain the transformed values, which are used as the feature data of the target search statement.

[0151] Finally, the obtained feature data is input into a pre-built prediction model to obtain the sum of the retrieval volume of the target search statement for the next 12 weeks.

[0152] The aforementioned prediction model can be trained based on the search volume of historical search queries.

[0153] For example, if the week date is May 5, 2021, then as shown in Table 3, the search volume data for search terms from April 22, 2020 to April 21, 2021 can be obtained as training set data, and multiple training sets are divided according to different base times, as shown in Table 3:

[0154] Table 3

[0155] Training dataset Sample time period Mark time period Baseline time Training set 1 20200422 20200930 20200708 Training set 2 20200429 20201007 20200715 Training set 3 20200506 20201014 20200722 … … … … training set n 20201111 20210421 20210127 test set 20201118 20210428 20210203

[0156] Furthermore, additional test data can be added, such as the test set data in Table 3 with February 3, 2021 as the base time.

[0157] It should be noted that each date in Table 3 is the Wednesday of its respective week, meaning that Wednesday represents the data for that week.

[0158] After obtaining the training and testing data, the prediction model can be trained using the training data and tested using the testing data until a prediction model that meets the requirements is obtained.

[0159] After obtaining the sum of search volume for the target search query in the next 12 weeks through the prediction model, the sum of search volume for the target search query in the past 12 weeks, as well as the sum of search volume for the target search query in the next 12 weeks, can be stored in the Elasticsearch database. Elasticsearch is a database with a real-time distributed storage, search, and analysis engine.

[0160] The solution provided in this disclosure utilizes the search volume information of the target search statement in a first time period before the current time to determine the estimated volume of the target search statement in a second time period after the current time. Based on the determined estimated volume, demand assessment information for the target search statement is generated. Since the estimated volume represents the search demand of the target search statement in the second time period, the demand assessment information can accurately reflect the actual demand of the target search statement in the future second time period. Therefore, the solution provided in this disclosure can solve the problem in related technologies where demand assessment information cannot accurately reflect actual demand.

[0161] Furthermore, since demand assessment information can accurately reflect actual needs, when using demand assessment information to guide knowledge content production, knowledge content that matches actual needs can be produced. The solution provided in this disclosure provides a foundation for producing knowledge content that matches actual needs.

[0162] like Figure 4 As shown in the embodiments of this disclosure, a method for displaying demand assessment information is provided, which may include the following steps:

[0163] S401, Obtain filtering information for the search query;

[0164] The filtering information can be determined based on the user's filtering action; this filtering information constitutes the filtering criteria. Optionally, a front-end page can be pre-displayed, showing users different information as needed, such as cluster title options, PV (daily average search volume) range, keywords, the date the demand assessment information was generated, and the type of knowledge content produced. Optionally, the above information can be visualized.

[0165] Of course, other information can also be present on the front-end page to provide richer options for information filtering. For example: demand classification: primary category, secondary category, where the primary and secondary categories are domain classifications, and the secondary category is a refinement of the primary category. When the user is received to perform selection, input, or other operations on the front-end page, filtering information for the search query can be generated based on the user's operation. This disclosure does not limit the filtering information provided.

[0166] S402, Filter the target search statements that match the filtering information from the search statements stored in the demand assessment database;

[0167] The demand assessment database stores multiple search statements and demand assessment information for each search statement. The demand assessment information for each search statement is determined according to the demand assessment information generation method provided in this disclosure.

[0168] The method for determining the demand assessment information for each search query is described in the aforementioned embodiment and will not be repeated here. After obtaining the filtering information, target search queries that match the filtering information can be selected from the search queries stored in the demand assessment database.

[0169] For example, if the filtering information is to select keywords related to the education industry and containing "middle school", then the target search terms such as "how to learn Chinese in middle school" and "learning methods for physics in middle school" can be filtered out.

[0170] Understandably, the demand assessment database can also record descriptive information for each search query, such as: the domain, generation time, type of knowledge content production, etc., so that after providing filtering information, each search query can be filtered according to the filtering information.

[0171] S403, Determine the demand assessment information for the target retrieval statement from the demand assessment database;

[0172] After identifying the target search query, the next step is to retrieve the demand assessment information for the target search query from the demand assessment database.

[0173] S404, outputs the target search statement and the demand assessment information for the target search statement.

[0174] After determining the target search statement and its requirements assessment information, the target search statement and its requirements assessment information can be output. Optionally, the target search statement and its requirements assessment information can be visualized.

[0175] Understandably, in addition to outputting the target search statement and the demand assessment information for the target search statement, and provided that the demand assessment database records other relevant information, it is also possible to output relevant information about the target search statement, such as: the ratio of clicks to impressions across the entire network, i.e., the result click-to-impression ratio; or, the ratio of clicks to impressions under a certain domain, i.e., the knowledge result click-to-impression ratio; or, the demand category level, the cluster title, etc.

[0176] The above-mentioned solution provided in this disclosure can generate demand assessment information that accurately reflects actual needs and provides a foundation for producing knowledge content that matches actual needs. Furthermore, it can also display target search statements and demand assessment information for those statements, thereby facilitating knowledge content producers to obtain the information they need.

[0177] According to embodiments of this disclosure, such as Figure 5 As shown, this disclosure also provides a demand assessment information generation apparatus, the apparatus comprising:

[0178] The first statement determination module 501 is used to determine the target retrieval statement to be analyzed.

[0179] The first information acquisition module 502 is used to acquire the search volume information of the target search statement within a first time period; wherein, the first time period is the time period before the current time, and the search volume information of any search statement within a time period includes: the search volume of the search statement in each statistical period within the time period.

[0180] The estimated quantity determination module 503 is used to determine the estimated quantity corresponding to the target search statement based on the acquired search volume information; wherein, the estimated quantity is used to characterize the search demand of the target search statement in the second time period, which is the time period after the current time.

[0181] The information generation module 504 is used to generate demand assessment information for the target search statement based on the estimated quantity corresponding to the target search statement.

[0182] Optional, the estimation determination module includes:

[0183] The data construction submodule is used to construct feature data of the target search statement within the first time period based on the acquired search volume information.

[0184] The model processing submodule is used to process the feature data of the target retrieval statement using a pre-trained prediction model to obtain the prediction value corresponding to the target retrieval statement.

[0185] The prediction model is trained based on sample data and corresponding labeled data. The sample data consists of the feature data of a specified search query within a sample time period, and the labeled data is used to characterize the search demand of the specified search query within a labeled time period. The sample time period is the time period before the baseline time, and the labeled time period is the time period after the baseline time.

[0186] Optionally, a data construction submodule is used to calculate the mean and / or variance of each search volume in the acquired search volume information; based on the search volume included in the acquired search volume information, and the calculated mean and / or variance, a feature vector is constructed as the feature data of the target search statement in the first time period.

[0187] Optionally, the device also includes:

[0188] The second information acquisition module is used to acquire, from the training dataset, the first retrieval volume information of the specified retrieval statement within the sample time period, and the second retrieval volume information of the specified retrieval statement within the labeled time period.

[0189] The data generation module is used to generate feature data of a specified search statement within a sample time period based on the first search volume information, as sample data, and to generate labeled data of the specified search statement within a labeled time period based on the second search volume information.

[0190] The data input module is used to input sample data into the neural network model to be trained, so that the neural network model can predict the estimated volume of the specified search statement within the labeled time period based on the sample data, and use it as prediction data.

[0191] Based on the predicted data and labeled data, calculate the loss function value of the neural network model;

[0192] Parameter tuning training is used to adjust the parameters of the neural network model based on the loss function value and to perform the next training iteration until all retrieval information in the training sample set has been utilized.

[0193] Optionally, the device also includes:

[0194] The second statement determination module is used to determine the various search statements that exist within the sample time period.

[0195] The third information acquisition module is used to acquire the first search volume information of each search statement within the sample time period, and the second search volume information within the labeled time period.

[0196] The dataset construction module is used to construct a training dataset using each search statement, as well as the first and second search volume information for each search statement.

[0197] Optionally, the first statement determination module is specifically used to filter out search statements with a search frequency greater than a preset frequency threshold from the search statements within the first time period, and use them as target search statements to be analyzed.

[0198] Optionally, the device also includes:

[0199] The information writing module is used to write the target search statement and its demand assessment information into the demand assessment database after the information generation module performs the step of generating demand assessment information based on the estimated quantity corresponding to the target search statement.

[0200] In the above-described solution provided by this disclosure, the search volume information of the target search statement in a first time period before the current time can be used to determine the estimated volume of the target search statement in a second time period after the current time. Then, based on the determined estimated volume, demand assessment information for the target search statement is generated. Since the estimated volume represents the search demand of the target search statement in the second time period, the demand assessment information can accurately reflect the actual demand of the target search statement in the future second time period. Therefore, the solution provided by this disclosure can solve the problem in related technologies where demand assessment information cannot accurately reflect actual demand.

[0201] Furthermore, since demand assessment information can accurately reflect actual needs, when using demand assessment information to guide knowledge content production, knowledge content that matches actual needs can be produced. The solution provided in this disclosure provides a foundation for producing knowledge content that matches actual needs.

[0202] According to embodiments of this disclosure, such as Figure 6 As shown, this disclosure also provides a demand assessment information display device, the device comprising:

[0203] The filtering information acquisition module 601 is used to acquire filtering information for the search query.

[0204] The statement filtering module 602 is used to filter target search statements that match the filtering information from the search statements stored in the demand assessment database; wherein, the demand assessment database stores multiple search statements and demand assessment information for each search statement, and the demand assessment information for each search statement is determined by the demand assessment information generation device provided in any of the present disclosure.

[0205] The information determination module 603 is used to determine the demand assessment information of the target retrieval statement from the demand assessment database;

[0206] The information output module 604 is used to output the target search statement and the demand assessment information for the target search statement.

[0207] The above-mentioned solution provided in this disclosure can generate demand assessment information that accurately reflects actual needs and provides a foundation for producing knowledge content that matches actual needs. Furthermore, it can also display target search statements and demand assessment information for those statements, thereby facilitating knowledge content producers to obtain the information they need.

[0208] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0209] This disclosure provides an electronic device, including:

[0210] At least one processor; and

[0211] A memory that is communicatively connected to at least one processor; wherein,

[0212] The memory stores instructions that can be executed by at least one processor, which enables the at least one processor to perform a method for generating or displaying requirements assessment information.

[0213] This disclosure discloses a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to execute a method for generating or displaying demand assessment information.

[0214] This disclosure discloses a computer program product, including a computer program that, when executed by a processor, implements a method for generating or displaying demand assessment information.

[0215] Figure 7 A 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.

[0216] Electronic devices can also refer to 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 examples and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0217] 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.

[0218] 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.

[0219] The computing unit 701 can be various 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 implementing a demand assessment information generation method or a demand assessment information display method. For example, in some embodiments, implementing the demand assessment information generation method or the demand assessment information display method can be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as storage unit 708. In some embodiments, part or all of the computer program can 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 implementing the demand assessment information generation method or the demand assessment information display method described above can be performed. Alternatively, in other embodiments, the computing unit 701 may be configured in any other suitable manner (e.g., by means of firmware) to execute a method for generating implementation requirement assessment information or a method for displaying requirement assessment information.

[0220] 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), payload-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.

[0221] 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.

[0222] 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.

[0223] 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).

[0224] 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.

[0225] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0226] 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.

[0227] 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. A method for generating demand assessment information, comprising: Determine the target search query to be analyzed; Obtain the search volume information of the target search statement within a first time period; wherein, the first time period is the time period before the current time, and the search volume information of any search statement within a time period includes: the search volume of the search statement in each statistical period within the time period. Calculate the mean and / or variance of each search quantity in the obtained search volume information; Based on the retrieved retrieval volume information, including the retrieval volume, and the calculated mean and / or variance, a feature vector is constructed as the feature data of the target retrieval statement within the first time period. Using a pre-trained prediction model, the feature data of the target search statement is processed to obtain the predicted value corresponding to the target search statement. The predicted value characterizes the search demand for the target search statement within a second time period, which is the time period following the current time. The predicted value is based on the trend of search volume changes reflected by the acquired search volume information. The prediction model is trained based on sample data and corresponding labeled data. The sample data consists of feature data of a specified search statement within a sample time period, and the labeled data characterizes the search demand for the specified search statement within a labeled time period. The sample time period is the time period before a baseline time, and the labeled time period is the time period after the baseline time. Based on the estimated quantity corresponding to the target retrieval statement, demand assessment information for the target retrieval statement is generated; wherein, the demand assessment information is: a demand level corresponding to the estimated quantity, determined based on the pre-constructed correspondence between the estimated quantity and the demand level, each demand level corresponds to a range of estimated quantities, and the estimated quantities within the range of estimated quantities all correspond to the demand level.

2. The method according to claim 1, wherein, The estimated prediction model is trained as follows: From the training dataset, obtain the first search volume information of the specified search statement within the sample time period, and the second search volume information of the specified search statement within the labeled time period; Based on the first search volume information, feature data of the specified search statement within the sample time period is generated as sample data, and based on the second search volume information, labeled data of the specified search statement within the labeled time period is generated. The sample data is input into the neural network model to be trained, so that the neural network model predicts the estimated volume of the specified search statement within the labeled time period based on the sample data, which is used as prediction data; Based on the predicted data and the labeled data, the loss function value of the neural network model is calculated; Based on the loss function value, the parameters of the neural network model are adjusted, and the next training is performed until all the retrieval information in the training sample set is utilized.

3. The method according to claim 2, wherein, The training dataset is constructed in the following ways: Identify each search statement that exists within the sample time period; Obtain the first search volume information for each search statement within the sample time period, and the second search volume information within the labeled time period; A training dataset is constructed using each search query, along with the first and second search volume information for each query.

4. The method according to any one of claims 1-3, wherein, The process of determining the target retrieval statement to be analyzed includes: From the search statements within the first time period, search statements with a search frequency greater than a preset frequency threshold are selected as target search statements to be analyzed.

5. The method according to any one of claims 1-3, after generating the demand assessment information for the target search statement based on the estimated quantity corresponding to the target search statement, further comprising: Write the target search statement and the requirement assessment information of the target search statement into the requirement assessment database.

6. A method for displaying demand assessment information, the method comprising: Obtain filtering information for the search query; From the various search statements stored in the demand assessment database, target search statements that match the filtering information are selected; wherein, the demand assessment database stores multiple search statements and demand assessment information for each search statement, and the demand assessment information for each search statement is determined according to the method according to any one of claims 1-5; Determine the demand assessment information for the target retrieval statement from the demand assessment database; Output the target search statement and the demand assessment information for the target search statement.

7. A demand assessment information generation device, comprising: The first statement determination module is used to determine the target retrieval statement to be analyzed. The first information acquisition module is used to acquire the search volume information of the target search statement within a first time period; wherein, the first time period is the time period before the current time, and the search volume information of any search statement within a time period includes: the search volume of the search statement in each statistical period within the time period. The data construction submodule is specifically used to calculate the mean and / or variance of each search quantity in the acquired search quantity information; based on the search quantity included in the acquired search quantity information, and the calculated mean and / or variance, a feature vector is constructed as the feature data of the target search statement in the first time period. The model processing submodule is used to process the feature data of the target search statement using a pre-trained prediction model to obtain the predicted value corresponding to the target search statement. The predicted value characterizes the search demand for the target search statement within a second time period, which is the time period after the current time. The predicted value is based on the trend of search volume changes reflected by the acquired search volume information. The prediction model is trained based on sample data and corresponding labeled data. The sample data consists of feature data of a specified search statement within a sample time period, and the labeled data characterizes the search demand for the specified search statement within a labeled time period. The sample time period is the time period before a baseline time, and the labeled time period is the time period after the baseline time. The information generation module is used to generate demand assessment information for the target search statement based on the estimated quantity corresponding to the target search statement; wherein, the demand assessment information is: a demand level corresponding to the estimated quantity, determined based on the pre-built correspondence between the estimated quantity and the demand level, each demand level corresponds to a range of estimated quantities, and the estimated quantities within the range of estimated quantities all correspond to the demand level.

8. The apparatus according to claim 7, further comprising: The second information acquisition module is used to acquire, from the training dataset, the first retrieval volume information of the specified retrieval statement within the sample time period, and the second retrieval volume information of the specified retrieval statement within the labeled time period; The data generation module is used to generate feature data of the specified search statement within the sample time period based on the first search volume information, as sample data, and to generate labeled data of the specified search statement within the labeled time period based on the second search volume information. The data input module is used to input the sample data into the neural network model to be trained, so that the neural network model can predict the estimated volume of the specified search statement within the labeled time period based on the sample data, as the prediction data; Based on the predicted data and the labeled data, the loss function value of the neural network model is calculated; Parameter adjustment training is used to adjust the parameters of the neural network model based on the loss function value and to perform the next training, until all retrieval information in the training sample set is utilized.

9. The apparatus according to claim 8, further comprising: The second statement determination module is used to determine each search statement that exists within the sample time period; The third information acquisition module is used to acquire the first search volume information of each search statement within the sample time period, and the second search volume information within the labeled time period. The dataset construction module is used to construct a training dataset using each search statement, as well as the first and second search volume information for each search statement.

10. The apparatus according to any one of claims 7-9, wherein, The first statement determination module is specifically used to select search statements with a search frequency greater than a preset frequency threshold from the search statements within the first time period, and use them as target search statements to be analyzed.

11. The apparatus according to any one of claims 7-9, wherein, The device further includes: The information writing module is used to write the target search statement and its demand assessment information into the demand assessment database after the information generation module performs the step of generating demand assessment information for the target search statement based on the estimated quantity corresponding to the target search statement.

12. A demand assessment information display device, the device comprising: The filter information acquisition module is used to acquire filter information for the search query. A statement filtering module is used to filter target search statements that match the filtering information from various search statements stored in a demand assessment database; wherein, the demand assessment database stores multiple search statements and demand assessment information for each search statement, and the demand assessment information for each search statement is determined by the apparatus according to any one of claims 7-11. The information determination module is used to determine the demand assessment information of the target retrieval statement from the demand assessment database; The information output module is used to output the target search statement and the demand evaluation information of the target search statement.

13. 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 1-5 or 6.

14. 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 1-5 or 6.

15. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-5 or 6.

Images